modelId
stringlengths 5
122
| author
stringlengths 2
42
| last_modified
unknown | downloads
int64 0
738M
| likes
int64 0
11k
| library_name
stringclasses 245
values | tags
sequencelengths 1
4.05k
| pipeline_tag
stringclasses 48
values | createdAt
unknown | card
stringlengths 1
901k
|
|---|---|---|---|---|---|---|---|---|---|
TheBloke/MLewd-ReMM-L2-Chat-20B-GGUF | TheBloke | "2023-09-27T12:53:58Z" | 1,684 | 33 | transformers | [
"transformers",
"gguf",
"llama",
"not-for-all-audiences",
"nsfw",
"base_model:Undi95/MLewd-ReMM-L2-Chat-20B",
"license:cc-by-nc-4.0",
"text-generation-inference",
"region:us"
] | null | "2023-09-22T23:37:48Z" | ---
license: cc-by-nc-4.0
tags:
- not-for-all-audiences
- nsfw
model_name: MLewd ReMM L2 Chat 20B
base_model: Undi95/MLewd-ReMM-L2-Chat-20B
inference: false
model_creator: Undi95
model_type: llama
prompt_template: 'Below is an instruction that describes a task. Write a response
that appropriately completes the request.
### Instruction:
{prompt}
### Response:
'
quantized_by: TheBloke
---
<!-- header start -->
<!-- 200823 -->
<div style="width: auto; margin-left: auto; margin-right: auto">
<img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
</div>
<div style="display: flex; justify-content: space-between; width: 100%;">
<div style="display: flex; flex-direction: column; align-items: flex-start;">
<p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://discord.gg/theblokeai">Chat & support: TheBloke's Discord server</a></p>
</div>
<div style="display: flex; flex-direction: column; align-items: flex-end;">
<p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p>
</div>
</div>
<div style="text-align:center; margin-top: 0em; margin-bottom: 0em"><p style="margin-top: 0.25em; margin-bottom: 0em;">TheBloke's LLM work is generously supported by a grant from <a href="https://a16z.com">andreessen horowitz (a16z)</a></p></div>
<hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
<!-- header end -->
# MLewd ReMM L2 Chat 20B - GGUF
- Model creator: [Undi95](https://huggingface.co/Undi95)
- Original model: [MLewd ReMM L2 Chat 20B](https://huggingface.co/Undi95/MLewd-ReMM-L2-Chat-20B)
<!-- description start -->
## Description
This repo contains GGUF format model files for [Undi95's MLewd ReMM L2 Chat 20B](https://huggingface.co/Undi95/MLewd-ReMM-L2-Chat-20B).
<!-- description end -->
<!-- README_GGUF.md-about-gguf start -->
### About GGUF
GGUF is a new format introduced by the llama.cpp team on August 21st 2023. It is a replacement for GGML, which is no longer supported by llama.cpp.
Here is an incomplate list of clients and libraries that are known to support GGUF:
* [llama.cpp](https://github.com/ggerganov/llama.cpp). The source project for GGUF. Offers a CLI and a server option.
* [text-generation-webui](https://github.com/oobabooga/text-generation-webui), the most widely used web UI, with many features and powerful extensions. Supports GPU acceleration.
* [KoboldCpp](https://github.com/LostRuins/koboldcpp), a fully featured web UI, with GPU accel across all platforms and GPU architectures. Especially good for story telling.
* [LM Studio](https://lmstudio.ai/), an easy-to-use and powerful local GUI for Windows and macOS (Silicon), with GPU acceleration.
* [LoLLMS Web UI](https://github.com/ParisNeo/lollms-webui), a great web UI with many interesting and unique features, including a full model library for easy model selection.
* [Faraday.dev](https://faraday.dev/), an attractive and easy to use character-based chat GUI for Windows and macOS (both Silicon and Intel), with GPU acceleration.
* [ctransformers](https://github.com/marella/ctransformers), a Python library with GPU accel, LangChain support, and OpenAI-compatible AI server.
* [llama-cpp-python](https://github.com/abetlen/llama-cpp-python), a Python library with GPU accel, LangChain support, and OpenAI-compatible API server.
* [candle](https://github.com/huggingface/candle), a Rust ML framework with a focus on performance, including GPU support, and ease of use.
<!-- README_GGUF.md-about-gguf end -->
<!-- repositories-available start -->
## Repositories available
* [AWQ model(s) for GPU inference.](https://huggingface.co/TheBloke/MLewd-ReMM-L2-Chat-20B-AWQ)
* [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/MLewd-ReMM-L2-Chat-20B-GPTQ)
* [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/MLewd-ReMM-L2-Chat-20B-GGUF)
* [Undi95's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/Undi95/MLewd-ReMM-L2-Chat-20B)
<!-- repositories-available end -->
<!-- prompt-template start -->
## Prompt template: Alpaca
```
Below is an instruction that describes a task. Write a response that appropriately completes the request.
### Instruction:
{prompt}
### Response:
```
<!-- prompt-template end -->
<!-- licensing start -->
## Licensing
The creator of the source model has listed its license as `cc-by-nc-4.0`, and this quantization has therefore used that same license.
As this model is based on Llama 2, it is also subject to the Meta Llama 2 license terms, and the license files for that are additionally included. It should therefore be considered as being claimed to be licensed under both licenses. I contacted Hugging Face for clarification on dual licensing but they do not yet have an official position. Should this change, or should Meta provide any feedback on this situation, I will update this section accordingly.
In the meantime, any questions regarding licensing, and in particular how these two licenses might interact, should be directed to the original model repository: [Undi95's MLewd ReMM L2 Chat 20B](https://huggingface.co/Undi95/MLewd-ReMM-L2-Chat-20B).
<!-- licensing end -->
<!-- compatibility_gguf start -->
## Compatibility
These quantised GGUFv2 files are compatible with llama.cpp from August 27th onwards, as of commit [d0cee0d](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221)
They are also compatible with many third party UIs and libraries - please see the list at the top of this README.
## Explanation of quantisation methods
<details>
<summary>Click to see details</summary>
The new methods available are:
* GGML_TYPE_Q2_K - "type-1" 2-bit quantization in super-blocks containing 16 blocks, each block having 16 weight. Block scales and mins are quantized with 4 bits. This ends up effectively using 2.5625 bits per weight (bpw)
* GGML_TYPE_Q3_K - "type-0" 3-bit quantization in super-blocks containing 16 blocks, each block having 16 weights. Scales are quantized with 6 bits. This end up using 3.4375 bpw.
* GGML_TYPE_Q4_K - "type-1" 4-bit quantization in super-blocks containing 8 blocks, each block having 32 weights. Scales and mins are quantized with 6 bits. This ends up using 4.5 bpw.
* GGML_TYPE_Q5_K - "type-1" 5-bit quantization. Same super-block structure as GGML_TYPE_Q4_K resulting in 5.5 bpw
* GGML_TYPE_Q6_K - "type-0" 6-bit quantization. Super-blocks with 16 blocks, each block having 16 weights. Scales are quantized with 8 bits. This ends up using 6.5625 bpw
Refer to the Provided Files table below to see what files use which methods, and how.
</details>
<!-- compatibility_gguf end -->
<!-- README_GGUF.md-provided-files start -->
## Provided files
| Name | Quant method | Bits | Size | Max RAM required | Use case |
| ---- | ---- | ---- | ---- | ---- | ----- |
| [mlewd-remm-l2-chat-20b.Q2_K.gguf](https://huggingface.co/TheBloke/MLewd-ReMM-L2-Chat-20B-GGUF/blob/main/mlewd-remm-l2-chat-20b.Q2_K.gguf) | Q2_K | 2 | 8.31 GB| 10.81 GB | smallest, significant quality loss - not recommended for most purposes |
| [mlewd-remm-l2-chat-20b.Q3_K_S.gguf](https://huggingface.co/TheBloke/MLewd-ReMM-L2-Chat-20B-GGUF/blob/main/mlewd-remm-l2-chat-20b.Q3_K_S.gguf) | Q3_K_S | 3 | 8.66 GB| 11.16 GB | very small, high quality loss |
| [mlewd-remm-l2-chat-20b.Q3_K_M.gguf](https://huggingface.co/TheBloke/MLewd-ReMM-L2-Chat-20B-GGUF/blob/main/mlewd-remm-l2-chat-20b.Q3_K_M.gguf) | Q3_K_M | 3 | 9.70 GB| 12.20 GB | very small, high quality loss |
| [mlewd-remm-l2-chat-20b.Q3_K_L.gguf](https://huggingface.co/TheBloke/MLewd-ReMM-L2-Chat-20B-GGUF/blob/main/mlewd-remm-l2-chat-20b.Q3_K_L.gguf) | Q3_K_L | 3 | 10.63 GB| 13.13 GB | small, substantial quality loss |
| [mlewd-remm-l2-chat-20b.Q4_0.gguf](https://huggingface.co/TheBloke/MLewd-ReMM-L2-Chat-20B-GGUF/blob/main/mlewd-remm-l2-chat-20b.Q4_0.gguf) | Q4_0 | 4 | 11.29 GB| 13.79 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| [mlewd-remm-l2-chat-20b.Q4_K_S.gguf](https://huggingface.co/TheBloke/MLewd-ReMM-L2-Chat-20B-GGUF/blob/main/mlewd-remm-l2-chat-20b.Q4_K_S.gguf) | Q4_K_S | 4 | 11.34 GB| 13.84 GB | small, greater quality loss |
| [mlewd-remm-l2-chat-20b.Q4_K_M.gguf](https://huggingface.co/TheBloke/MLewd-ReMM-L2-Chat-20B-GGUF/blob/main/mlewd-remm-l2-chat-20b.Q4_K_M.gguf) | Q4_K_M | 4 | 12.04 GB| 14.54 GB | medium, balanced quality - recommended |
| [mlewd-remm-l2-chat-20b.Q5_0.gguf](https://huggingface.co/TheBloke/MLewd-ReMM-L2-Chat-20B-GGUF/blob/main/mlewd-remm-l2-chat-20b.Q5_0.gguf) | Q5_0 | 5 | 13.77 GB| 16.27 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| [mlewd-remm-l2-chat-20b.Q5_K_S.gguf](https://huggingface.co/TheBloke/MLewd-ReMM-L2-Chat-20B-GGUF/blob/main/mlewd-remm-l2-chat-20b.Q5_K_S.gguf) | Q5_K_S | 5 | 13.77 GB| 16.27 GB | large, low quality loss - recommended |
| [mlewd-remm-l2-chat-20b.Q5_K_M.gguf](https://huggingface.co/TheBloke/MLewd-ReMM-L2-Chat-20B-GGUF/blob/main/mlewd-remm-l2-chat-20b.Q5_K_M.gguf) | Q5_K_M | 5 | 14.16 GB| 16.66 GB | large, very low quality loss - recommended |
| [mlewd-remm-l2-chat-20b.Q6_K.gguf](https://huggingface.co/TheBloke/MLewd-ReMM-L2-Chat-20B-GGUF/blob/main/mlewd-remm-l2-chat-20b.Q6_K.gguf) | Q6_K | 6 | 16.40 GB| 18.90 GB | very large, extremely low quality loss |
| [mlewd-remm-l2-chat-20b.Q8_0.gguf](https://huggingface.co/TheBloke/MLewd-ReMM-L2-Chat-20B-GGUF/blob/main/mlewd-remm-l2-chat-20b.Q8_0.gguf) | Q8_0 | 8 | 21.25 GB| 23.75 GB | very large, extremely low quality loss - not recommended |
**Note**: the above RAM figures assume no GPU offloading. If layers are offloaded to the GPU, this will reduce RAM usage and use VRAM instead.
<!-- README_GGUF.md-provided-files end -->
<!-- README_GGUF.md-how-to-download start -->
## How to download GGUF files
**Note for manual downloaders:** You almost never want to clone the entire repo! Multiple different quantisation formats are provided, and most users only want to pick and download a single file.
The following clients/libraries will automatically download models for you, providing a list of available models to choose from:
- LM Studio
- LoLLMS Web UI
- Faraday.dev
### In `text-generation-webui`
Under Download Model, you can enter the model repo: TheBloke/MLewd-ReMM-L2-Chat-20B-GGUF and below it, a specific filename to download, such as: mlewd-remm-l2-chat-20b.Q4_K_M.gguf.
Then click Download.
### On the command line, including multiple files at once
I recommend using the `huggingface-hub` Python library:
```shell
pip3 install huggingface-hub
```
Then you can download any individual model file to the current directory, at high speed, with a command like this:
```shell
huggingface-cli download TheBloke/MLewd-ReMM-L2-Chat-20B-GGUF mlewd-remm-l2-chat-20b.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
```
<details>
<summary>More advanced huggingface-cli download usage</summary>
You can also download multiple files at once with a pattern:
```shell
huggingface-cli download TheBloke/MLewd-ReMM-L2-Chat-20B-GGUF --local-dir . --local-dir-use-symlinks False --include='*Q4_K*gguf'
```
For more documentation on downloading with `huggingface-cli`, please see: [HF -> Hub Python Library -> Download files -> Download from the CLI](https://huggingface.co/docs/huggingface_hub/guides/download#download-from-the-cli).
To accelerate downloads on fast connections (1Gbit/s or higher), install `hf_transfer`:
```shell
pip3 install hf_transfer
```
And set environment variable `HF_HUB_ENABLE_HF_TRANSFER` to `1`:
```shell
HF_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download TheBloke/MLewd-ReMM-L2-Chat-20B-GGUF mlewd-remm-l2-chat-20b.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
```
Windows Command Line users: You can set the environment variable by running `set HF_HUB_ENABLE_HF_TRANSFER=1` before the download command.
</details>
<!-- README_GGUF.md-how-to-download end -->
<!-- README_GGUF.md-how-to-run start -->
## Example `llama.cpp` command
Make sure you are using `llama.cpp` from commit [d0cee0d](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221) or later.
```shell
./main -ngl 32 -m mlewd-remm-l2-chat-20b.Q4_K_M.gguf --color -c 4096 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "Below is an instruction that describes a task. Write a response that appropriately completes the request.\n\n### Instruction:\n{prompt}\n\n### Response:"
```
Change `-ngl 32` to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.
Change `-c 4096` to the desired sequence length. For extended sequence models - eg 8K, 16K, 32K - the necessary RoPE scaling parameters are read from the GGUF file and set by llama.cpp automatically.
If you want to have a chat-style conversation, replace the `-p <PROMPT>` argument with `-i -ins`
For other parameters and how to use them, please refer to [the llama.cpp documentation](https://github.com/ggerganov/llama.cpp/blob/master/examples/main/README.md)
## How to run in `text-generation-webui`
Further instructions here: [text-generation-webui/docs/llama.cpp.md](https://github.com/oobabooga/text-generation-webui/blob/main/docs/llama.cpp.md).
## How to run from Python code
You can use GGUF models from Python using the [llama-cpp-python](https://github.com/abetlen/llama-cpp-python) or [ctransformers](https://github.com/marella/ctransformers) libraries.
### How to load this model in Python code, using ctransformers
#### First install the package
Run one of the following commands, according to your system:
```shell
# Base ctransformers with no GPU acceleration
pip install ctransformers
# Or with CUDA GPU acceleration
pip install ctransformers[cuda]
# Or with AMD ROCm GPU acceleration (Linux only)
CT_HIPBLAS=1 pip install ctransformers --no-binary ctransformers
# Or with Metal GPU acceleration for macOS systems only
CT_METAL=1 pip install ctransformers --no-binary ctransformers
```
#### Simple ctransformers example code
```python
from ctransformers import AutoModelForCausalLM
# Set gpu_layers to the number of layers to offload to GPU. Set to 0 if no GPU acceleration is available on your system.
llm = AutoModelForCausalLM.from_pretrained("TheBloke/MLewd-ReMM-L2-Chat-20B-GGUF", model_file="mlewd-remm-l2-chat-20b.Q4_K_M.gguf", model_type="llama", gpu_layers=50)
print(llm("AI is going to"))
```
## How to use with LangChain
Here are guides on using llama-cpp-python and ctransformers with LangChain:
* [LangChain + llama-cpp-python](https://python.langchain.com/docs/integrations/llms/llamacpp)
* [LangChain + ctransformers](https://python.langchain.com/docs/integrations/providers/ctransformers)
<!-- README_GGUF.md-how-to-run end -->
<!-- footer start -->
<!-- 200823 -->
## Discord
For further support, and discussions on these models and AI in general, join us at:
[TheBloke AI's Discord server](https://discord.gg/theblokeai)
## Thanks, and how to contribute
Thanks to the [chirper.ai](https://chirper.ai) team!
Thanks to Clay from [gpus.llm-utils.org](llm-utils)!
I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training.
If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects.
Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits.
* Patreon: https://patreon.com/TheBlokeAI
* Ko-Fi: https://ko-fi.com/TheBlokeAI
**Special thanks to**: Aemon Algiz.
**Patreon special mentions**: Alicia Loh, Stephen Murray, K, Ajan Kanaga, RoA, Magnesian, Deo Leter, Olakabola, Eugene Pentland, zynix, Deep Realms, Raymond Fosdick, Elijah Stavena, Iucharbius, Erik Bjäreholt, Luis Javier Navarrete Lozano, Nicholas, theTransient, John Detwiler, alfie_i, knownsqashed, Mano Prime, Willem Michiel, Enrico Ros, LangChain4j, OG, Michael Dempsey, Pierre Kircher, Pedro Madruga, James Bentley, Thomas Belote, Luke @flexchar, Leonard Tan, Johann-Peter Hartmann, Illia Dulskyi, Fen Risland, Chadd, S_X, Jeff Scroggin, Ken Nordquist, Sean Connelly, Artur Olbinski, Swaroop Kallakuri, Jack West, Ai Maven, David Ziegler, Russ Johnson, transmissions 11, John Villwock, Alps Aficionado, Clay Pascal, Viktor Bowallius, Subspace Studios, Rainer Wilmers, Trenton Dambrowitz, vamX, Michael Levine, 준교 김, Brandon Frisco, Kalila, Trailburnt, Randy H, Talal Aujan, Nathan Dryer, Vadim, 阿明, ReadyPlayerEmma, Tiffany J. Kim, George Stoitzev, Spencer Kim, Jerry Meng, Gabriel Tamborski, Cory Kujawski, Jeffrey Morgan, Spiking Neurons AB, Edmond Seymore, Alexandros Triantafyllidis, Lone Striker, Cap'n Zoog, Nikolai Manek, danny, ya boyyy, Derek Yates, usrbinkat, Mandus, TL, Nathan LeClaire, subjectnull, Imad Khwaja, webtim, Raven Klaugh, Asp the Wyvern, Gabriel Puliatti, Caitlyn Gatomon, Joseph William Delisle, Jonathan Leane, Luke Pendergrass, SuperWojo, Sebastain Graf, Will Dee, Fred von Graf, Andrey, Dan Guido, Daniel P. Andersen, Nitin Borwankar, Elle, Vitor Caleffi, biorpg, jjj, NimbleBox.ai, Pieter, Matthew Berman, terasurfer, Michael Davis, Alex, Stanislav Ovsiannikov
Thank you to all my generous patrons and donaters!
And thank you again to a16z for their generous grant.
<!-- footer end -->
<!-- original-model-card start -->
# Original model card: Undi95's MLewd ReMM L2 Chat 20B
First :
```shell
layer_slices:
- model: Undi95/MLewd-L2-Chat-13B
start: 0
end: 16
- model: Undi95/MLewd-ReMM-L2-Chat-20B-Part1
start: 8
end: 20
- model: Undi95/MLewd-L2-Chat-13B
start: 17
end: 32
- model: Undi95/MLewd-ReMM-L2-Chat-20B-Part1
start: 21
end: 40
```
Inverted:
```shell
layer_slices:
- model: Undi95/MLewd-ReMM-L2-Chat-20B-Part1
start: 0
end: 16
- model: Undi95/MLewd-L2-Chat-13B
start: 8
end: 20
- model: Undi95/MLewd-ReMM-L2-Chat-20B-Part1
start: 17
end: 32
- model: Undi95/MLewd-L2-Chat-13B
start: 21
end: 40
```
Precise:
```shell
layer_slices:
- model: Undi95/MLewd-L2-Chat-13B
start: 0
end: 8
- model: Undi95/MLewd-ReMM-L2-Chat-20B-Part1
start: 4
end: 12
- model: Undi95/MLewd-L2-Chat-13B
start: 9
end: 16
- model: Undi95/MLewd-ReMM-L2-Chat-20B-Part1
start: 13
end: 22
- model: Undi95/MLewd-L2-Chat-13B
start: 17
end: 24
- model: Undi95/MLewd-ReMM-L2-Chat-20B-Part1
start: 23
end: 32
- model: Undi95/MLewd-L2-Chat-13B
start: 25
end: 32
- model: Undi95/MLewd-ReMM-L2-Chat-20B-Part1
start: 33
end: 40
```
PreciseInverted:
```shell
layer_slices:
- model: Undi95/MLewd-ReMM-L2-Chat-20B-Part1
start: 0
end: 8
- model: Undi95/MLewd-L2-Chat-13B
start: 4
end: 12
- model: Undi95/MLewd-ReMM-L2-Chat-20B-Part1
start: 9
end: 16
- model: Undi95/MLewd-L2-Chat-13B
start: 13
end: 22
- model: Undi95/MLewd-ReMM-L2-Chat-20B-Part1
start: 17
end: 24
- model: Undi95/MLewd-L2-Chat-13B
start: 23
end: 32
- model: Undi95/MLewd-ReMM-L2-Chat-20B-Part1
start: 25
end: 32
- model: Undi95/MLewd-L2-Chat-13B
start: 33
end: 40
```
Part1 = ReMM v2.1 merged /w MLewd low weight to keep consistency. I call this "dilution" and result show consistency and coherency without repeat/loop beside the small amount of duplicated datas.
The goal is to find the best way to interlace layers the best way possible to have a sweetspot between 13B and +30B.
Normal/Inverted is by chunk of 16 layers and Precise/PreciseInverted is by chunk of 8 layers.
All the models are made of 64(+1) layers. Need testing.
## Prompt template: Alpaca
```
Below is an instruction that describes a task. Write a response that completes the request.
### Instruction:
{prompt}
### Response:
```
<!-- original-model-card end -->
|
cloudyu/Yi-34Bx2-MOE-200K | cloudyu | "2024-03-25T10:46:33Z" | 1,684 | 2 | transformers | [
"transformers",
"safetensors",
"mixtral",
"text-generation",
"conversational",
"license:other",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-03-23T11:06:12Z" | ---
license: other
---
try to build a 200K context length MoE Yi based chat model.
[[GGUF 4bit is here ]https://huggingface.co/cloudyu/Yi-34Bx2-MOE-200K-gguf ]
* Metrics
metrics :
code example
```
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
import math
##
model_path = "cloudyu/Yi-34Bx2-MOE-200K"
tokenizer = AutoTokenizer.from_pretrained(model_path, use_default_system_prompt=False)
model = AutoModelForCausalLM.from_pretrained(
model_path, torch_dtype=torch.float32, device_map='auto',local_files_only=False, load_in_4bit=True
)
print(model)
prompt = input("please input prompt:")
while len(prompt) > 0:
input_ids = tokenizer(prompt, return_tensors="pt").input_ids.to("cuda")
generation_output = model.generate(
input_ids=input_ids, max_new_tokens=500,repetition_penalty=1.2
)
print(tokenizer.decode(generation_output[0]))
prompt = input("please input prompt:")
``` |
NikolayKozloff/MKLLM-7B-Q8_0-GGUF | NikolayKozloff | "2024-06-24T16:11:28Z" | 1,684 | 1 | null | [
"gguf",
"axolotl",
"llama-cpp",
"gguf-my-repo",
"mk",
"en",
"base_model:trajkovnikola/MKLLM-7B",
"license:apache-2.0",
"region:us"
] | null | "2024-06-24T16:10:57Z" | ---
base_model: trajkovnikola/MKLLM-7B
language:
- mk
- en
license: apache-2.0
tags:
- axolotl
- llama-cpp
- gguf-my-repo
---
# NikolayKozloff/MKLLM-7B-Q8_0-GGUF
This model was converted to GGUF format from [`trajkovnikola/MKLLM-7B`](https://huggingface.co/trajkovnikola/MKLLM-7B) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
Refer to the [original model card](https://huggingface.co/trajkovnikola/MKLLM-7B) for more details on the model.
## Use with llama.cpp
Install llama.cpp through brew (works on Mac and Linux)
```bash
brew install llama.cpp
```
Invoke the llama.cpp server or the CLI.
### CLI:
```bash
llama-cli --hf-repo NikolayKozloff/MKLLM-7B-Q8_0-GGUF --hf-file mkllm-7b-q8_0.gguf -p "The meaning to life and the universe is"
```
### Server:
```bash
llama-server --hf-repo NikolayKozloff/MKLLM-7B-Q8_0-GGUF --hf-file mkllm-7b-q8_0.gguf -c 2048
```
Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well.
Step 1: Clone llama.cpp from GitHub.
```
git clone https://github.com/ggerganov/llama.cpp
```
Step 2: Move into the llama.cpp folder and build it with `LLAMA_CURL=1` flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux).
```
cd llama.cpp && LLAMA_CURL=1 make
```
Step 3: Run inference through the main binary.
```
./llama-cli --hf-repo NikolayKozloff/MKLLM-7B-Q8_0-GGUF --hf-file mkllm-7b-q8_0.gguf -p "The meaning to life and the universe is"
```
or
```
./llama-server --hf-repo NikolayKozloff/MKLLM-7B-Q8_0-GGUF --hf-file mkllm-7b-q8_0.gguf -c 2048
```
|
timm/eva02_base_patch14_448.mim_in22k_ft_in1k | timm | "2024-02-10T23:37:30Z" | 1,683 | 2 | timm | [
"timm",
"pytorch",
"safetensors",
"image-classification",
"dataset:imagenet-1k",
"dataset:imagenet-22k",
"arxiv:2303.11331",
"arxiv:2303.15389",
"license:mit",
"region:us"
] | image-classification | "2023-03-31T04:14:40Z" | ---
license: mit
library_name: timm
tags:
- image-classification
- timm
datasets:
- imagenet-1k
- imagenet-22k
---
# Model card for eva02_base_patch14_448.mim_in22k_ft_in1k
An EVA02 image classification model. Pretrained on ImageNet-22k with masked image modeling (using EVA-CLIP as a MIM teacher) and fine-tuned on ImageNet-1k by paper authors.
EVA-02 models are vision transformers with mean pooling, SwiGLU, Rotary Position Embeddings (ROPE), and extra LN in MLP (for Base & Large).
NOTE: `timm` checkpoints are float32 for consistency with other models. Original checkpoints are float16 or bfloat16 in some cases, see originals if that's preferred.
## Model Details
- **Model Type:** Image classification / feature backbone
- **Model Stats:**
- Params (M): 87.1
- GMACs: 107.1
- Activations (M): 259.1
- Image size: 448 x 448
- **Papers:**
- EVA-02: A Visual Representation for Neon Genesis: https://arxiv.org/abs/2303.11331
- EVA-CLIP: Improved Training Techniques for CLIP at Scale: https://arxiv.org/abs/2303.15389
- **Original:**
- https://github.com/baaivision/EVA
- https://huggingface.co/Yuxin-CV/EVA-02
- **Pretrain Dataset:** ImageNet-22k
- **Dataset:** ImageNet-1k
## Model Usage
### Image Classification
```python
from urllib.request import urlopen
from PIL import Image
import timm
img = Image.open(urlopen(
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
model = timm.create_model('eva02_base_patch14_448.mim_in22k_ft_in1k', pretrained=True)
model = model.eval()
# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(img).unsqueeze(0)) # unsqueeze single image into batch of 1
top5_probabilities, top5_class_indices = torch.topk(output.softmax(dim=1) * 100, k=5)
```
### Image Embeddings
```python
from urllib.request import urlopen
from PIL import Image
import timm
img = Image.open(urlopen(
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
model = timm.create_model(
'eva02_base_patch14_448.mim_in22k_ft_in1k',
pretrained=True,
num_classes=0, # remove classifier nn.Linear
)
model = model.eval()
# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(img).unsqueeze(0)) # output is (batch_size, num_features) shaped tensor
# or equivalently (without needing to set num_classes=0)
output = model.forward_features(transforms(img).unsqueeze(0))
# output is unpooled, a (1, 1025, 768) shaped tensor
output = model.forward_head(output, pre_logits=True)
# output is a (1, num_features) shaped tensor
```
## Model Comparison
Explore the dataset and runtime metrics of this model in timm [model results](https://github.com/huggingface/pytorch-image-models/tree/main/results).
|model |top1 |top5 |param_count|img_size|
|-----------------------------------------------|------|------|-----------|--------|
|eva02_large_patch14_448.mim_m38m_ft_in22k_in1k |90.054|99.042|305.08 |448 |
|eva02_large_patch14_448.mim_in22k_ft_in22k_in1k|89.946|99.01 |305.08 |448 |
|eva_giant_patch14_560.m30m_ft_in22k_in1k |89.792|98.992|1014.45 |560 |
|eva02_large_patch14_448.mim_in22k_ft_in1k |89.626|98.954|305.08 |448 |
|eva02_large_patch14_448.mim_m38m_ft_in1k |89.57 |98.918|305.08 |448 |
|eva_giant_patch14_336.m30m_ft_in22k_in1k |89.56 |98.956|1013.01 |336 |
|eva_giant_patch14_336.clip_ft_in1k |89.466|98.82 |1013.01 |336 |
|eva_large_patch14_336.in22k_ft_in22k_in1k |89.214|98.854|304.53 |336 |
|eva_giant_patch14_224.clip_ft_in1k |88.882|98.678|1012.56 |224 |
|eva02_base_patch14_448.mim_in22k_ft_in22k_in1k |88.692|98.722|87.12 |448 |
|eva_large_patch14_336.in22k_ft_in1k |88.652|98.722|304.53 |336 |
|eva_large_patch14_196.in22k_ft_in22k_in1k |88.592|98.656|304.14 |196 |
|eva02_base_patch14_448.mim_in22k_ft_in1k |88.23 |98.564|87.12 |448 |
|eva_large_patch14_196.in22k_ft_in1k |87.934|98.504|304.14 |196 |
|eva02_small_patch14_336.mim_in22k_ft_in1k |85.74 |97.614|22.13 |336 |
|eva02_tiny_patch14_336.mim_in22k_ft_in1k |80.658|95.524|5.76 |336 |
## Citation
```bibtex
@article{EVA02,
title={EVA-02: A Visual Representation for Neon Genesis},
author={Fang, Yuxin and Sun, Quan and Wang, Xinggang and Huang, Tiejun and Wang, Xinlong and Cao, Yue},
journal={arXiv preprint arXiv:2303.11331},
year={2023}
}
```
```bibtex
@article{EVA-CLIP,
title={EVA-02: A Visual Representation for Neon Genesis},
author={Sun, Quan and Fang, Yuxin and Wu, Ledell and Wang, Xinlong and Cao, Yue},
journal={arXiv preprint arXiv:2303.15389},
year={2023}
}
```
```bibtex
@misc{rw2019timm,
author = {Ross Wightman},
title = {PyTorch Image Models},
year = {2019},
publisher = {GitHub},
journal = {GitHub repository},
doi = {10.5281/zenodo.4414861},
howpublished = {\url{https://github.com/huggingface/pytorch-image-models}}
}
```
|
Monero/WizardLM-30B-Uncensored-Guanaco-SuperCOT-30b | Monero | "2023-05-26T08:15:41Z" | 1,683 | 24 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"uncensored",
"dataset:ehartford/WizardLM_alpaca_evol_instruct_70k_unfiltered",
"dataset:kaiokendev/SuperCOT-dataset",
"dataset:neulab/conala",
"dataset:yahma/alpaca-cleaned",
"dataset:QingyiSi/Alpaca-CoT",
"dataset:timdettmers/guanaco-33b",
"dataset:JosephusCheung/GuanacoDataset",
"license:other",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-05-26T02:31:43Z" | ---
license: other
datasets:
- ehartford/WizardLM_alpaca_evol_instruct_70k_unfiltered
- kaiokendev/SuperCOT-dataset
- neulab/conala
- yahma/alpaca-cleaned
- QingyiSi/Alpaca-CoT
- timdettmers/guanaco-33b
- JosephusCheung/GuanacoDataset
tags:
- uncensored
---
<center><h1><b>WizardLM 30b + SuperCOT + Guacano</b></h1></center>
<html>
<head>
<style>
table {
border:1px solid #b3adad;
border-collapse:collapse;
padding:5px;
}
table th {
border:1px solid #b3adad;
padding:5px;
background: #f0f0f0;
color: #313030;
}
table td {
border:1px solid #b3adad;
text-align:center;
padding:5px;
background: #ffffff;
color: #313030;
}
</style>
</head>
<body>
<table>
<thead>
<tr>
<th>Model:</th>
<th>Wikitext2</th>
<th>Ptb-New</th>
<th>C4-New</th>
</tr>
</thead>
<tbody>
<tr>
<td>WizardLM-30B-Uncensored-Guanaco-SuperCOT-30b</td>
<td></td>
<td></td>
<td></td>
</tr>
</tbody>
</table>
</body>
</html>
### Guanaco SuperCOT
Guanaco SuperCOT is trained with the aim of making LLaMa follow prompts for Langchain better, by infusing chain-of-thought datasets, code explanations and instructions, snippets, logical deductions and Alpaca GPT-4 prompts. It's also an advanced instruction-following language model built on Meta's LLaMA 33B model. Expanding upon the initial 52K dataset from the Alpaca model, an additional 534,530 entries have been incorporated, covering English, Simplified Chinese, Traditional Chinese (Taiwan), Traditional Chinese (Hong Kong), Japanese, Deutsch, and various linguistic and grammatical tasks. This wealth of data enables Guanaco to perform exceptionally well in multilingual environments.
It uses a mixture of the following datasets:
[https://huggingface.co/datasets/QingyiSi/Alpaca-CoT](https://huggingface.co/datasets/QingyiSi/Alpaca-CoT)
- Chain of thought QED
- Chain of thought Aqua
- CodeAlpaca
[https://huggingface.co/datasets/neulab/conala](https://huggingface.co/datasets/neulab/conala)
- Code snippets
[https://huggingface.co/datasets/yahma/alpaca-cleaned](https://huggingface.co/datasets/yahma/alpaca-cleaned)
- Alpaca GPT4
- [https://huggingface.co/datasets/JosephusCheung/GuanacoDataset](https://huggingface.co/datasets/JosephusCheung/GuanacoDataset)
- Guacano
- [https://huggingface.co/timdettmers/guanaco-33b](https://huggingface.co/timdettmers/guanaco-33b)
- Guacano 33b LoRa
- [https://huggingface.co/kaiokendev/SuperCOT-LoRA](https://huggingface.co/kaiokendev/SuperCOT-LoRA)
- SuperChain-of-Thought LoRa
- [https://huggingface.co/ehartford/WizardLM-30B-Uncensored/](https://huggingface.co/ehartford/WizardLM-30B-Uncensored/)
- WizardLM 30B Uncensored
1\. Prompting
-------------------------
You should prompt the LoRA the same way you would prompt Alpaca or Alpacino.
The new format is designed to be similar to ChatGPT, allowing for better integration with the Alpaca format and enhancing the overall user experience.
Instruction is utilized as a few-shot context to support diverse inputs and responses, making it easier for the model to understand and provide accurate responses to user queries.
The format is as follows:
```
### Instruction:
User: History User Input
Assistant: History Assistant Answer
### Input:
System: Knowledge
User: New User Input
### Response:
New Assistant Answer
```
This structured format allows for easier tracking of the conversation history and maintaining context throughout a multi-turn dialogue.
```
Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.
### Instruction:
<instruction>
### Input:
<any additional context. Remove this if it's not neccesary>
### Response:
<make sure to leave a single new-line here for optimal results>
```
Remember that with lower parameter sizes, the structure of the prompt becomes more important. The same prompt worded differently can give wildly different answers. Consider using the following suggestion suffixes to improve output quality:
- "Think through this step by step"
- "Let's think about this logically"
- "Explain your reasoning"
- "Provide details to support your answer"
- "Compare and contrast your answer with alternatives"
2\. Role-playing support:
-------------------------
Guanaco now offers advanced role-playing support, similar to Character.AI, in English, Simplified Chinese, Traditional Chinese, Japanese, and Deutsch, making it more versatile for users from different linguistic backgrounds.
Users can instruct the model to assume specific roles, historical figures, or fictional characters, as well as personalities based on their input. This allows for more engaging and immersive conversations.
The model can use various sources of information to provide knowledge and context for the character's background and behavior, such as encyclopedic entries, first-person narrations, or a list of personality traits.
The model will consistently output responses in the format "Character Name: Reply" to maintain the chosen role throughout the conversation, enhancing the user's experience.
3\. Continuation of responses for ongoing topics:
-------------------------------------------------
The Guanaco model can now continue answering questions or discussing topics upon the user's request, making it more adaptable and better suited for extended conversations.
The contextual structure consisting of System, Assistant, and User roles allows the model to engage in multi-turn dialogues, maintain context-aware conversations, and provide more coherent responses.
The model can now accommodate role specification and character settings, providing a more immersive and tailored conversational experience based on the user's preferences.
It is important to remember that Guanaco is a 33B-parameter model, and any knowledge-based content should be considered potentially inaccurate. We strongly recommend providing verifiable sources, such as Wikipedia, for knowledge-based answers. In the absence of sources, it is crucial to inform users of this limitation to prevent the dissemination of false information and to maintain transparency.
### Citations
Alpaca COT datasets
```
@misc{alpaca-cot,
author = {Qingyi Si, Zheng Lin },
school = {Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China},
title = {Alpaca-CoT: An Instruction Fine-Tuning Platform with Instruction Data Collection and Unified Large Language Models Interface},
year = {2023},
publisher = {GitHub},
journal = {GitHub repository},
howpublished = {\url{https://github.com/PhoebusSi/alpaca-CoT}},
}
```
Stanford Alpaca
```
@misc{alpaca,
author = {Rohan Taori and Ishaan Gulrajani and Tianyi Zhang and Yann Dubois and Xuechen Li and Carlos Guestrin and Percy Liang and Tatsunori B. Hashimoto },
title = {Stanford Alpaca: An Instruction-following LLaMA model},
year = {2023},
publisher = {GitHub},
journal = {GitHub repository},
howpublished = {\url{https://github.com/tatsu-lab/stanford_alpaca}},
}
```
Google FLAN
```
@inproceedings{weifinetuned,
title={Finetuned Language Models are Zero-Shot Learners},
author={Wei, Jason and Bosma, Maarten and Zhao, Vincent and Guu, Kelvin and Yu, Adams Wei and Lester, Brian and Du, Nan and Dai, Andrew M and Le, Quoc V},
booktitle={International Conference on Learning Representations}
}
Note:
An uncensored model has no guardrails.
You are responsible for anything you do with the model, just as you are responsible for anything you do with any dangerous object such as a knife, gun, lighter, or car.
Publishing anything this model generates is the same as publishing it yourself.
You are responsible for the content you publish, and you cannot blame the model any more than you can blame the knife, gun, lighter, or car for what you do with it.
``` |
euclaise/gpt-neox-122m-minipile-digits | euclaise | "2023-12-14T23:46:55Z" | 1,683 | 2 | transformers | [
"transformers",
"pytorch",
"safetensors",
"gpt_neox",
"text-generation",
"en",
"dataset:JeanKaddour/minipile",
"license:cc0-1.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-06-09T13:26:11Z" | ---
license: cc0-1.0
datasets:
- JeanKaddour/minipile
language:
- en
library_name: transformers
---
GPT-NeoX trained on MiniPile, for a baseline to compare my MANN models against. Uses [NeelNanda/gpt-neox-tokenizer-digits](https://huggingface.co/NeelNanda/gpt-neox-tokenizer-digits) for tokenization.
The exact model configuration is as follows:
```
cfg = GPTNeoXConfig(
vocab_size = len(tokenizer),
hidden_size = 768,
intermediate_size = 768*4,
num_hidden_layers = 12,
num_attention_heads = 12,
tie_word_embeddings = True,
hidden_act = "gelu_new",
tokenizer = "NeelNanda/gpt-neox-tokenizer-digits"
)
```
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_euclaise__gpt-neox-122m-minipile-digits)
| Metric | Value |
|-----------------------|---------------------------|
| Avg. | 25.1 |
| ARC (25-shot) | 20.73 |
| HellaSwag (10-shot) | 27.03 |
| MMLU (5-shot) | 25.31 |
| TruthfulQA (0-shot) | 49.19 |
| Winogrande (5-shot) | 52.33 |
| GSM8K (5-shot) | 0.0 |
| DROP (3-shot) | 1.09 |
|
ehsanaghaei/SecureBERT_Plus | ehsanaghaei | "2023-12-21T19:10:23Z" | 1,683 | 3 | transformers | [
"transformers",
"pytorch",
"roberta",
"fill-mask",
"cybersecurity",
"en",
"license:cc-by-nc-4.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | fill-mask | "2023-08-09T08:49:03Z" | ---
license: cc-by-nc-4.0
language:
- en
tags:
- cybersecurity
widget:
- text: "Native API functions such as <mask>, may be directed invoked via system calls/syscalls, but these features are also often exposed to user-mode applications via interfaces and libraries.."
example_title: Native API functions
- text: "One way of explicitly assigning the PPID of a new process is via the <mask> API call, which supports a parameter that defines the PPID to use."
example_title: Assigning the PPID of a new process
- text: "Enable Safe DLL Search Mode to force search for system DLLs in directories with greater restrictions (e.g. %<mask>%) to be used before local directory DLLs (e.g. a user's home directory)"
example_title: Enable Safe DLL Search Mode
- text: "GuLoader is a file downloader that has been used since at least December 2019 to distribute a variety of <mask>, including NETWIRE, Agent Tesla, NanoCore, and FormBook."
example_title: GuLoader is a file downloader
---
# SecureBERT+
This model represents an improved version of the [SecureBERT](https://huggingface.co/ehsanaghaei/SecureBERT) model, trained on a corpus eight times larger than its predecessor, leveraging the computational power of 8xA100 GPUs. This version, known as SecureBERT+, brings forth an average improvment of 9% in the performance of the Masked Language Model (MLM) task. This advancement signifies a substantial stride towards achieving heightened proficiency in language understanding and representation learning within the cybersecurity domain.
SecureBERT is a domain-specific language model based on RoBERTa which is trained on a huge amount of cybersecurity data and fine-tuned/tweaked to understand/represent cybersecurity textual data.
## Dataset
## Load Model
SecureBER+T has been uploaded to [Huggingface](https://huggingface.co/ehsanaghaei/SecureBERT_Plus) framework.
```python
from transformers import RobertaTokenizer, RobertaModel
import torch
tokenizer = RobertaTokenizer.from_pretrained("ehsanaghaei/SecureBERT_Plus")
model = RobertaModel.from_pretrained("ehsanaghaei/SecureBERT_Plus")
inputs = tokenizer("This is SecureBERT Plus!", return_tensors="pt")
outputs = model(**inputs)
last_hidden_states = outputs.last_hidden_state
```
## Fill Mask (MLM)
Use the code below to predict the masked word within the given sentences:
```python
#!pip install transformers
#!pip install torch
#!pip install tokenizers
import torch
import transformers
from transformers import RobertaTokenizer, RobertaTokenizerFast
tokenizer = RobertaTokenizerFast.from_pretrained("ehsanaghaei/SecureBERT_Plus")
model = transformers.RobertaForMaskedLM.from_pretrained("ehsanaghaei/SecureBERT_Plus")
def predict_mask(sent, tokenizer, model, topk =10, print_results = True):
token_ids = tokenizer.encode(sent, return_tensors='pt')
masked_position = (token_ids.squeeze() == tokenizer.mask_token_id).nonzero()
masked_pos = [mask.item() for mask in masked_position]
words = []
with torch.no_grad():
output = model(token_ids)
last_hidden_state = output[0].squeeze()
list_of_list = []
for index, mask_index in enumerate(masked_pos):
mask_hidden_state = last_hidden_state[mask_index]
idx = torch.topk(mask_hidden_state, k=topk, dim=0)[1]
words = [tokenizer.decode(i.item()).strip() for i in idx]
words = [w.replace(' ','') for w in words]
list_of_list.append(words)
if print_results:
print("Mask ", "Predictions: ", words)
best_guess = ""
for j in list_of_list:
best_guess = best_guess + "," + j[0]
return words
while True:
sent = input("Text here: \t")
print("SecureBERT: ")
predict_mask(sent, tokenizer, model)
print("===========================\n")
```
Other model variants:
[SecureGPT](https://huggingface.co/ehsanaghaei/SecureGPT)
[SecureDeBERTa](https://huggingface.co/ehsanaghaei/SecureDeBERTa)
[SecureBERT](https://huggingface.co/ehsanaghaei/SecureBERT)
# Reference
@inproceedings{aghaei2023securebert,
title={SecureBERT: A Domain-Specific Language Model for Cybersecurity},
author={Aghaei, Ehsan and Niu, Xi and Shadid, Waseem and Al-Shaer, Ehab},
booktitle={Security and Privacy in Communication Networks:
18th EAI International Conference, SecureComm 2022, Virtual Event,
October 2022,
Proceedings},
pages={39--56},
year={2023},
organization={Springer} }
|
HWERI/pythia-1.4b-deduped-sharegpt | HWERI | "2023-11-17T23:04:07Z" | 1,683 | 2 | transformers | [
"transformers",
"pytorch",
"safetensors",
"gpt_neox",
"text-generation",
"zh",
"en",
"ko",
"ja",
"dataset:shibing624/sharegpt_gpt4",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-08-10T10:27:20Z" | ---
license: apache-2.0
datasets:
- shibing624/sharegpt_gpt4
language:
- zh
- en
- ko
- ja
pipeline_tag: text-generation
---
# Model Card for Model ID
This model is a pythia 1.4B finetuned on the sharegpt dataset.
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_HWERI__pythia-1.4b-deduped-sharegpt)
| Metric | Value |
|-----------------------|---------------------------|
| Avg. | 30.79 |
| ARC (25-shot) | 34.3 |
| HellaSwag (10-shot) | 54.49 |
| MMLU (5-shot) | 24.0 |
| TruthfulQA (0-shot) | 41.81 |
| Winogrande (5-shot) | 55.25 |
| GSM8K (5-shot) | 0.83 |
| DROP (3-shot) | 4.88 |
|
Severian/ANIMA-Phi-Neptune-Mistral-7B | Severian | "2024-03-18T11:14:04Z" | 1,683 | 29 | transformers | [
"transformers",
"pytorch",
"mistral",
"text-generation",
"chemistry",
"biology",
"climate",
"science",
"philosophy",
"nature",
"ecology",
"biomimicry",
"fauna",
"flora",
"dataset:Severian/Biomimicry",
"dataset:emrgnt-cmplxty/sciphi-textbooks-are-all-you-need",
"dataset:fmars/wiki_stem",
"dataset:fblgit/tree-of-knowledge",
"dataset:Severian/Bio-Design-Process",
"license:artistic-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-10-11T22:48:16Z" | ---
license: artistic-2.0
tags:
- chemistry
- biology
- climate
- science
- philosophy
- nature
- ecology
- biomimicry
- fauna
- flora
datasets:
- Severian/Biomimicry
- emrgnt-cmplxty/sciphi-textbooks-are-all-you-need
- fmars/wiki_stem
- fblgit/tree-of-knowledge
- Severian/Bio-Design-Process
metrics:
- accuracy
pipeline_tag: text-generation
model-index:
- name: ANIMA-Phi-Neptune-Mistral-7B-v4
results:
- task:
type: text-generation
name: Text Generation
dataset:
name: AI2 Reasoning Challenge (25-Shot)
type: ai2_arc
config: ARC-Challenge
split: test
args:
num_few_shot: 25
metrics:
- type: acc_norm
value: 55.46
name: normalized accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Severian/ANIMA-Phi-Neptune-Mistral-7B-v4
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: HellaSwag (10-Shot)
type: hellaswag
split: validation
args:
num_few_shot: 10
metrics:
- type: acc_norm
value: 77.63
name: normalized accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Severian/ANIMA-Phi-Neptune-Mistral-7B-v4
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: MMLU (5-Shot)
type: cais/mmlu
config: all
split: test
args:
num_few_shot: 5
metrics:
- type: acc
value: 53.12
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Severian/ANIMA-Phi-Neptune-Mistral-7B-v4
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: TruthfulQA (0-shot)
type: truthful_qa
config: multiple_choice
split: validation
args:
num_few_shot: 0
metrics:
- type: mc2
value: 59.01
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Severian/ANIMA-Phi-Neptune-Mistral-7B-v4
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: Winogrande (5-shot)
type: winogrande
config: winogrande_xl
split: validation
args:
num_few_shot: 5
metrics:
- type: acc
value: 73.48
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Severian/ANIMA-Phi-Neptune-Mistral-7B-v4
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: GSM8k (5-shot)
type: gsm8k
config: main
split: test
args:
num_few_shot: 5
metrics:
- type: acc
value: 14.94
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Severian/ANIMA-Phi-Neptune-Mistral-7B-v4
name: Open LLM Leaderboard
---
# ANIMA-Phi-Neptune-Mistral-7B: Biomimicry Enhanced LLM
<img src="https://cdn-uploads.huggingface.co/production/uploads/64740cf7485a7c8e1bd51ac9/JZH6p50t_j3-OUph4Wq6y.png" width="500">
## Overview
**ANIMA** (Advanced Nature Inspired Multidisciplinary Assistant) is an expert in various scientific disciplines, including but not limited to biomimicry, biology, and environmental science.
**Instagram: [@anima_llm](https://www.instagram.com/anima_llm)**
---
## Model Description
ANIMA is fine-tuned on a rich dataset encompassing:
- 4,000+ Nature-Biomimicry examples
- 60k Biomimicry Design Process examples
- 600k STEM facts from Wikipedia
- Science/Philosophy focused 'All-You-Need-Is-Textbooks' dataset
- Additional Tree of Knowledge + Biomimicry data combined fine-tuning
The model aims to assist users in solving problems using nature-inspired strategies and concepts.
### Special Features
- **Multi-disciplinary Expertise**: Knowledge across various scientific and philosophical domains.
- **Biomimicry Design Process**: Incorporates a dataset generated by Mistral and Minotaur-15B. The dataset was then intricately processed by a real person to ensure factuality and grounding.
---
- Here is a link to The Bloke's GGUF version: [ANIMA-Phi-Neptune-Mistral-7B-GGUF](https://huggingface.co/TheBloke/ANIMA-Phi-Neptune-Mistral-7B-GGUF)
- ANIMA is also available using Ollama - Download the [OLLAMA](https://ollama.ai/) App (MacOS & Linux) and then run this command in your Terminal '**ollama pull severian/anima**' to download the model and then run this command '**ollama run severian/anima**' to load the model and start talking.
- You can also download and use the model with [LM Studio](https://lmstudio.ai/) (All OS systems). Just download the app and then search for 'ANIMA GGUF' in the search bar and you will have a list of versions to choose from.
- Want to test ANIMA + Ollama and chat right away? Download the model from Ollama and head here to chat with ANIMA right in your browser! [ANIMA - Chat](https://severian42.github.io/ANIMA-Chat/)
- Have a PDF you want to discuss with ANIMA + Ollama? Head here and you can do just that in your browser, 100% locally. [ANIMA - Locally Chat over your PDF](https://ANIMA-pdf-chat.vercel.app/)
- ANIMA is also being hosted on a Hugging Face Space if you'd like to try it there (It may be slow to generate a respone but it still works just fine) [ANIMA - HF Space](https://huggingface.co/spaces/Severian/ANIMA-7B-Biomimicry-LLM)
- **Contact**
If you want to discuss the model/dataset/concept further, have any cool ideas, want to collaborate or if you run into any issues with the model, please don't hesitate to reach out at [email protected]
## Datasets
- `Severian/Biomimicry` (1st Fine-Tune)
- `emrgnt-cmplxty/sciphi-textbooks-are-all-you-need` (2nd Fine-Tune)
- `Severian/Bio-Design-Process` & `fmars/wiki_stem` (3rd Fine-Tune)
- `fblgit/tree-of-knowledge` & `Severian/Biomimicry` (4th Fine-Tune)
- `Combined all previous datasets` into one giant dataset for a quick fine-tuning for a total of 730k data points (5th Fine-Tune)
## Training Stages
1. **Base Model**: `ehartford/dolphin-2.0-mistral-7b`
2. **1st Fine-Tune**: `ANIMA-Echo-Mistral-7B-v1` - 1 Epoch x 5hrs on 1 x T4 Small
3. **2nd Fine-Tune**: `ANIMA-Phi-Neptune-Mistral-v1`-: 1 Epoch x 1hr on 1 x A100
4. **3rd Fine-Tune**: `ANIMA-Phi-Neptune-Mistral-7B-v2` - 1 Epoch x 1hr on 1 x A100
5. **4th Fine-Tune**: `ANIMA-Phi-Neptune-Mistral-7B-v3` - 1 Epoch x 1hr on 1 x A100
6. **5th Fine-Tune**: `ANIMA-Phi-Neptune-Mistral-7B-v4` - 1 Epoch x 15mins on 1 x A100
---
## 📝 Usage
ANIMA is designed around the Biomimicry Design Process to guide users in solving problems through biomimicry. For more information and examples, please visit [Biomimicry Design Process](https://toolbox.biomimicry.org/methods/process/).
## 🏁 Benchmarks
- Average - 62.22
- ARC - 56.83
- HellaSwag - 78.82
- MMLU - 53.84
- TruthfulQA - 59.40
---
- **EXAMPLE OUTPUT**
[INST] How can biomimicry help in water purification? [/INST]
Biomimicry plays a significant role in water purification by taking
inspiration from natural processes and organisms to develop sustainable
and efficient solutions. Here's a comprehensive overview of how biomimicry
can help in water purification:
1. Microbial filtration:
- Bacteriophages (viruses that infect bacteria) can effectively target
contaminants in water systems, such as Escherichia coli and Staphylococcus
aureus. By mimicking the natural defense mechanisms of bacteriophages, we
can develop efficient filtration systems that remove pollutants from water
sources.
- Some fungi, such as Trametes versicolor, can break down organic
pollutants in water using enzymes. This process helps make contaminated
water safe for consumption. By studying and replicating these natural
processes, we can develop sustainable filtration systems that remove
pollutants from water sources effectively.
2. Biofilm-based filtration:
- Microorganisms form biofilms on surfaces to protect themselves from
environmental threats like predators or contaminants. By mimicking the
natural formation of biofilms, we can develop sustainable filtration
systems that use bacteria or fungi to remove pollutants from water
sources.
- For example, a study has shown how Pseudomonas putida could
be used to biodegrade petroleum hydrocarbons in contaminated water sources
using a biofilm-based system. This method offers an eco-friendly
alternative to conventional chemical treatments for oil spills.
3. Wetland-based filtration:
- Wetlands act as natural filters for water by retaining sediments and
organic matter, which helps remove contaminants. By mimicking the natural
processes of a wetland, we can design effective water purification systems
that use sand filters or engineered wetlands to remove pollutants. For
instance, a study has shown how reed beds can be used for water filtration
by using them as a natural treatment system for agricultural wastewater.
4. Sponge filtration:
- Some marine sponges (e.g., sea sponge) have evolved sophisticated
mechanisms to filter out particles and contaminants from the surrounding
water. By studying these natural filtration processes, we can develop
efficient and sustainable filtration systems that remove pollutants
effectively. For example, a study has shown how sea sponges can be used as
a model for designing a low-cost, self-sustaining water purification
system that uses solar energy to disinfect contaminated water.
5. Biodegradable materials:
- Natural organisms have evolved biodegradable materials to protect
themselves from predators or environmental threats. For instance, some
insects produce natural pesticides (such as alkaloids) to defend
themselves against predators. Similarly, we can develop biodegradable
materials that release these natural pesticides in contaminated water
sources, killing off contaminants and restoring the environment's health.
- For example, a study has shown how bacterial cells can be used as a
natural filtration system to remove contaminants from water sources by
incorporating them into membranes that selectively remove organic
pollutants.
In conclusion, biomimicry plays a vital role in water purification by
using natural processes and organisms as inspiration for developing
sustainable and efficient solutions. By studying the natural filtration
mechanisms of microorganisms, plants, animals, and other living organisms,
we can design eco-friendly and cost-effective water purification systems
that help protect our environment from contamination.
---
### ***[Help Support ANIMA](https://www.buymeacoffee.com/anima7b)***
---
- **KNOWN ISSUES**
The model will sometimes respond to itself and continue the conversation taking both the user and AI roles. This is a known issue in the Mistral model but does not happen very often.
## 📜 License
This project is licensed under Artistic-2.0
**This model is for research purposes only and restricted from any commercial use**
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_Severian__ANIMA-Phi-Neptune-Mistral-7B-v4)
| Metric |Value|
|---------------------------------|----:|
|Avg. |55.61|
|AI2 Reasoning Challenge (25-Shot)|55.46|
|HellaSwag (10-Shot) |77.63|
|MMLU (5-Shot) |53.12|
|TruthfulQA (0-shot) |59.01|
|Winogrande (5-shot) |73.48|
|GSM8k (5-shot) |14.94|
|
togethercomputer/RedPajama-INCITE-7B-Chat | togethercomputer | "2023-06-05T03:22:54Z" | 1,682 | 92 | transformers | [
"transformers",
"pytorch",
"gpt_neox",
"text-generation",
"en",
"dataset:togethercomputer/RedPajama-Data-1T",
"dataset:OpenAssistant/oasst1",
"dataset:databricks/databricks-dolly-15k",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-05-04T20:24:59Z" | ---
license: apache-2.0
language:
- en
datasets:
- togethercomputer/RedPajama-Data-1T
- OpenAssistant/oasst1
- databricks/databricks-dolly-15k
widget:
- text: "<human>: Write an email to my friends inviting them to come to my home on Friday for a dinner party, bring their own food to share.\n<bot>:"
example_title: "Email Writing"
- text: "<human>: Create a list of things to do in San Francisco\n<bot>:"
example_title: "Brainstorming"
inference:
parameters:
temperature: 0.7
top_p: 0.7
top_k: 50
max_new_tokens: 128
---
# RedPajama-INCITE-7B-Chat
RedPajama-INCITE-7B-Chat was developed by Together and leaders from the open-source AI community including Ontocord.ai, ETH DS3Lab, AAI CERC, Université de Montréal, MILA - Québec AI Institute, Stanford Center for Research on Foundation Models (CRFM), Stanford Hazy Research research group and LAION.
It is fine-tuned on OASST1 and Dolly2 to enhance chatting ability.
- Base Model: [RedPajama-INCITE-7B-Base](https://huggingface.co/togethercomputer/RedPajama-INCITE-7B-Base)
- Instruction-tuned Version: [RedPajama-INCITE-7B-Instruct](https://huggingface.co/togethercomputer/RedPajama-INCITE-7B-Instruct)
- Chat Version: [RedPajama-INCITE-7B-Chat](https://huggingface.co/togethercomputer/RedPajama-INCITE-7B-Chat)
## Model Details
- **Developed by**: Together Computer.
- **Model type**: Language Model
- **Language(s)**: English
- **License**: Apache 2.0
- **Model Description**: A 6.9B parameter pretrained language model.
# Quick Start
Please note that the model requires `transformers` version >= 4.25.1.
To prompt the chat model, use the following format:
```
<human>: [Instruction]
<bot>:
```
## GPU Inference
This requires a GPU with 16GB memory.
```python
import torch
import transformers
from transformers import AutoTokenizer, AutoModelForCausalLM
MIN_TRANSFORMERS_VERSION = '4.25.1'
# check transformers version
assert transformers.__version__ >= MIN_TRANSFORMERS_VERSION, f'Please upgrade transformers to version {MIN_TRANSFORMERS_VERSION} or higher.'
# init
tokenizer = AutoTokenizer.from_pretrained("togethercomputer/RedPajama-INCITE-7B-Chat")
model = AutoModelForCausalLM.from_pretrained("togethercomputer/RedPajama-INCITE-7B-Chat", torch_dtype=torch.float16)
model = model.to('cuda:0')
# infer
prompt = "<human>: Who is Alan Turing?\n<bot>:"
inputs = tokenizer(prompt, return_tensors='pt').to(model.device)
input_length = inputs.input_ids.shape[1]
outputs = model.generate(
**inputs, max_new_tokens=128, do_sample=True, temperature=0.7, top_p=0.7, top_k=50, return_dict_in_generate=True
)
token = outputs.sequences[0, input_length:]
output_str = tokenizer.decode(token)
print(output_str)
"""
Alan Mathison Turing (23 June 1912 7 June 1954) was an English computer scientist, mathematician, logician, cryptanalyst, philosopher, mathematician, and theoretical biologist.
"""
```
## GPU Inference in Int8
This requires a GPU with 12GB memory.
To run inference with int8, please ensure you have installed accelerate and bitandbytes. You can install them with the following command:
```bash
pip install accelerate
pip install bitsandbytes
```
Then you can run inference with int8 as follows:
```python
import torch
import transformers
from transformers import AutoTokenizer, AutoModelForCausalLM
MIN_TRANSFORMERS_VERSION = '4.25.1'
# check transformers version
assert transformers.__version__ >= MIN_TRANSFORMERS_VERSION, f'Please upgrade transformers to version {MIN_TRANSFORMERS_VERSION} or higher.'
# init
tokenizer = AutoTokenizer.from_pretrained("togethercomputer/RedPajama-INCITE-7B-Chat")
model = AutoModelForCausalLM.from_pretrained("togethercomputer/RedPajama-INCITE-7B-Chat", device_map='auto', torch_dtype=torch.float16, load_in_8bit=True)
# infer
prompt = "<human>: Who is Alan Turing?\n<bot>:"
inputs = tokenizer(prompt, return_tensors='pt').to(model.device)
input_length = inputs.input_ids.shape[1]
outputs = model.generate(
**inputs, max_new_tokens=128, do_sample=True, temperature=0.7, top_p=0.7, top_k=50, return_dict_in_generate=True
)
token = outputs.sequences[0, input_length:]
output_str = tokenizer.decode(token)
print(output_str)
"""
Alan Mathison Turing (23 June 1912 – 7 June 1954) was an English computer scientist, mathematician, logician, cryptanalyst, philosopher, and theoretical biologist.
"""
```
## CPU Inference
```python
import torch
import transformers
from transformers import AutoTokenizer, AutoModelForCausalLM
MIN_TRANSFORMERS_VERSION = '4.25.1'
# check transformers version
assert transformers.__version__ >= MIN_TRANSFORMERS_VERSION, f'Please upgrade transformers to version {MIN_TRANSFORMERS_VERSION} or higher.'
# init
tokenizer = AutoTokenizer.from_pretrained("togethercomputer/RedPajama-INCITE-7B-Chat")
model = AutoModelForCausalLM.from_pretrained("togethercomputer/RedPajama-INCITE-7B-Chat", torch_dtype=torch.bfloat16)
# infer
prompt = "<human>: Who is Alan Turing?\n<bot>:"
inputs = tokenizer(prompt, return_tensors='pt').to(model.device)
input_length = inputs.input_ids.shape[1]
outputs = model.generate(
**inputs, max_new_tokens=128, do_sample=True, temperature=0.7, top_p=0.7, top_k=50, return_dict_in_generate=True
)
token = outputs.sequences[0, input_length:]
output_str = tokenizer.decode(token)
print(output_str)
"""
Alan Mathison Turing, OBE, FRS, (23 June 1912 – 7 June 1954) was an English computer scientist, mathematician, logician, cryptanalyst, philosopher, and theoretical biologist.
"""
```
Please note that since `LayerNormKernelImpl` is not implemented in fp16 for CPU, we use `bfloat16` for CPU inference.
# Uses
## Direct Use
Excluded uses are described below.
### Misuse, Malicious Use, and Out-of-Scope Use
It is the responsibility of the end user to ensure that the model is used in a responsible and ethical manner.
#### Out-of-Scope Use
`RedPajama-INCITE-7B-Chat` is a language model and may not perform well for other use cases outside of its intended scope.
For example, it may not be suitable for use in safety-critical applications or for making decisions that have a significant impact on individuals or society.
It is important to consider the limitations of the model and to only use it for its intended purpose.
#### Misuse and Malicious Use
`RedPajama-INCITE-7B-Chat` is designed for language modeling.
Misuse of the model, such as using it to engage in illegal or unethical activities, is strictly prohibited and goes against the principles of the project.
Using the model to generate content that is cruel to individuals is a misuse of this model. This includes, but is not limited to:
- Generating fake news, misinformation, or propaganda
- Promoting hate speech, discrimination, or violence against individuals or groups
- Impersonating individuals or organizations without their consent
- Engaging in cyberbullying or harassment
- Defamatory content
- Spamming or scamming
- Sharing confidential or sensitive information without proper authorization
- Violating the terms of use of the model or the data used to train it
- Creating automated bots for malicious purposes such as spreading malware, phishing scams, or spamming
## Limitations
`RedPajama-INCITE-7B-Chat`, like other language models, has limitations that should be taken into consideration.
For example, the model may not always provide accurate or relevant answers, particularly for questions that are complex, ambiguous, or outside of its training data.
We therefore welcome contributions from individuals and organizations, and encourage collaboration towards creating a more robust and inclusive chatbot.
## Training
**Training Data**
Please refer to [togethercomputer/RedPajama-Data-1T](https://huggingface.co/datasets/togethercomputer/RedPajama-Data-1T)
**Training Procedure**
- **Hardware:** 8 A100
- **Optimizer:** Adam
- **Gradient Accumulations**: 1
- **Num of Tokens:** 79M tokens
- **Learning rate:** 1e-5
## Community
Join us on [Together Discord](https://discord.gg/6ZVDU8tTD4) |
Mikael110/llama-2-13b-guanaco-fp16 | Mikael110 | "2023-07-20T00:16:26Z" | 1,682 | 11 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"llama-2",
"text-classification",
"en",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-classification | "2023-07-19T21:47:49Z" | ---
language:
- en
pipeline_tag: text-classification
tags:
- llama-2
---
This is a Llama-2 version of [Guanaco](https://huggingface.co/timdettmers/guanaco-13b). It was finetuned from the base [Llama-13b](https://huggingface.co/meta-llama/Llama-2-13b-hf) model using the official training scripts found in the [QLoRA repo](https://github.com/artidoro/qlora). I wanted it to be as faithful as possible and therefore changed nothing in the training script beyond the model it was pointing to. The model prompt is therefore also the same as the original Guanaco model.
This repo contains the merged f16 model. The QLoRA adaptor can be found [here](https://huggingface.co/Mikael110/llama-2-13b-guanaco-qlora).
A 7b version of the model can be found [here](https://huggingface.co/Mikael110/llama-2-7b-guanaco-fp16).
**Legal Disclaimer: This model is bound by the usage restrictions of the original Llama-2 model. And comes with no warranty or gurantees of any kind.** |
OpenLemur/lemur-70b-v1 | OpenLemur | "2023-10-13T06:59:24Z" | 1,682 | 45 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"code",
"en",
"arxiv:2310.06830",
"license:llama2",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-08-23T11:44:09Z" | ---
pipeline_tag: text-generation
inference: true
widget:
- text: 'def factorial(n):'
example_title: Factorial
group: Python
- text: 'def recur_fibo(n):'
example_title: Recursive Fibonacci
group: Python
license: llama2
library_name: transformers
tags:
- text-generation
- code
language:
- en
---
# lemur-70b-v1
<p align="center">
<img src="https://huggingface.co/datasets/OpenLemur/assets/resolve/main/lemur_icon.png" width="300" height="300" alt="Lemur">
</p>
<div align="center">
<img src="https://huggingface.co/datasets/OpenLemur/assets/resolve/main/lemur_base_radar.png">
</div>
📄Paper: https://arxiv.org/abs/2310.06830
👩💻Code: https://github.com/OpenLemur/Lemur
## Use
### Setup
First, we have to install all the libraries listed in `requirements.txt` in [GitHub](https://github.com/OpenLemur/lemur-v1):
```bash
pip install -r requirements.txt
```
### Intended use
Since it is not trained on instruction following corpus, it won't respond well to questions like "What is the Python code to do quick sort?".
### Generation
```python
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("OpenLemur/lemur-70b-v1")
model = AutoModelForCausalLM.from_pretrained("OpenLemur/lemur-70b-v1", device_map="auto", load_in_8bit=True)
# Text Generation Example
prompt = "The world is "
input = tokenizer(prompt, return_tensors="pt")
output = model.generate(**input, max_length=50, num_return_sequences=1)
generated_text = tokenizer.decode(output[0], skip_special_tokens=True)
print(generated_text)
# Code Generation Example
prompt = """
def factorial(n):
if n == 0:
return 1
"""
input = tokenizer(prompt, return_tensors="pt")
output = model.generate(**input, max_length=200, num_return_sequences=1)
generated_code = tokenizer.decode(output[0], skip_special_tokens=True)
print(generated_code)
```
# License
The model is licensed under the Llama-2 community license agreement.
# Acknowledgements
The Lemur project is an open collaborative research effort between [XLang Lab](https://www.xlang.ai/) and Salesforce Research. We thank Salesforce, Google Research and Amazon AWS for their gift support. |
andrijdavid/CarbonVillain-en-10.7B-v2-GGUF | andrijdavid | "2024-01-01T18:20:39Z" | 1,682 | 0 | transformers | [
"transformers",
"safetensors",
"gguf",
"llama",
"text-generation",
"GGUF",
"conversational",
"en",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-01-01T17:10:56Z" | ---
language:
- en
license: mit
tags:
- GGUF
quantized_by: andrijdavid
---
# CarbonVillain-en-10.7B-v2-GGUF
- Original model: [CarbonVillain-en-10.7B-v2](https://huggingface.co/jeonsworld/CarbonVillain-en-10.7B-v2)
<!-- description start -->
## Description
This repo contains GGUF format model files for [CarbonVillain-en-10.7B-v2](https://huggingface.co/jeonsworld/CarbonVillain-en-10.7B-v2).
<!-- description end -->
<!-- README_GGUF.md-about-gguf start -->
### About GGUF
GGUF is a new format introduced by the llama.cpp team on August 21st 2023. It is a replacement for GGML, which is no longer supported by llama.cpp.
Here is an incomplete list of clients and libraries that are known to support GGUF:
* [llama.cpp](https://github.com/ggerganov/llama.cpp). This is the source project for GGUF, providing both a Command Line Interface (CLI) and a server option.
* [text-generation-webui](https://github.com/oobabooga/text-generation-webui), Known as the most widely used web UI, this project boasts numerous features and powerful extensions, and supports GPU acceleration.
* [Ollama](https://github.com/jmorganca/ollama) Ollama is a lightweight and extensible framework designed for building and running language models locally. It features a simple API for creating, managing, and executing models, along with a library of pre-built models for use in various applications
* [KoboldCpp](https://github.com/LostRuins/koboldcpp), A comprehensive web UI offering GPU acceleration across all platforms and architectures, particularly renowned for storytelling.
* [GPT4All](https://gpt4all.io), This is a free and open source GUI that runs locally, supporting Windows, Linux, and macOS with full GPU acceleration.
* [LM Studio](https://lmstudio.ai/) An intuitive and powerful local GUI for Windows and macOS (Silicon), featuring GPU acceleration.
* [LoLLMS Web UI](https://github.com/ParisNeo/lollms-webui). A notable web UI with a variety of unique features, including a comprehensive model library for easy model selection.
* [Faraday.dev](https://faraday.dev/), An attractive, user-friendly character-based chat GUI for Windows and macOS (both Silicon and Intel), also offering GPU acceleration.
* [llama-cpp-python](https://github.com/abetlen/llama-cpp-python), A Python library equipped with GPU acceleration, LangChain support, and an OpenAI-compatible API server.
* [candle](https://github.com/huggingface/candle), A Rust-based ML framework focusing on performance, including GPU support, and designed for ease of use.
* [ctransformers](https://github.com/marella/ctransformers), A Python library featuring GPU acceleration, LangChain support, and an OpenAI-compatible AI server.
* [localGPT](https://github.com/PromtEngineer/localGPT) An open-source initiative enabling private conversations with documents.
<!-- README_GGUF.md-about-gguf end -->
<!-- compatibility_gguf start -->
## Explanation of quantisation methods
<details>
<summary>Click to see details</summary>
The new methods available are:
* GGML_TYPE_Q2_K - "type-1" 2-bit quantization in super-blocks containing 16 blocks, each block having 16 weight. Block scales and mins are quantized with 4 bits. This ends up effectively using 2.5625 bits per weight (bpw)
* GGML_TYPE_Q3_K - "type-0" 3-bit quantization in super-blocks containing 16 blocks, each block having 16 weights. Scales are quantized with 6 bits. This end up using 3.4375 bpw.
* GGML_TYPE_Q4_K - "type-1" 4-bit quantization in super-blocks containing 8 blocks, each block having 32 weights. Scales and mins are quantized with 6 bits. This ends up using 4.5 bpw.
* GGML_TYPE_Q5_K - "type-1" 5-bit quantization. Same super-block structure as GGML_TYPE_Q4_K resulting in 5.5 bpw
* GGML_TYPE_Q6_K - "type-0" 6-bit quantization. Super-blocks with 16 blocks, each block having 16 weights. Scales are quantized with 8 bits. This ends up using 6.5625 bpw.
</details>
<!-- compatibility_gguf end -->
<!-- README_GGUF.md-how-to-download start -->
## How to download GGUF files
**Note for manual downloaders:** You almost never want to clone the entire repo! Multiple different quantisation formats are provided, and most users only want to pick and download a single file.
The following clients/libraries will automatically download models for you, providing a list of available models to choose from:
* LM Studio
* LoLLMS Web UI
* Faraday.dev
### In `text-generation-webui`
Under Download Model, you can enter the model repo: andrijdavid/CarbonVillain-en-10.7B-v2-GGUF and below it, a specific filename to download, such as: CarbonVillain-en-10.7B-v2-f16.gguf.
Then click Download.
### On the command line, including multiple files at once
I recommend using the `huggingface-hub` Python library:
```shell
pip3 install huggingface-hub
```
Then you can download any individual model file to the current directory, at high speed, with a command like this:
```shell
huggingface-cli download andrijdavid/CarbonVillain-en-10.7B-v2-GGUF CarbonVillain-en-10.7B-v2-f16.gguf --local-dir . --local-dir-use-symlinks False
```
<details>
<summary>More advanced huggingface-cli download usage (click to read)</summary>
You can also download multiple files at once with a pattern:
```shell
huggingface-cli download andrijdavid/CarbonVillain-en-10.7B-v2-GGUF --local-dir . --local-dir-use-symlinks False --include='*Q4_K*gguf'
```
For more documentation on downloading with `huggingface-cli`, please see: [HF -> Hub Python Library -> Download files -> Download from the CLI](https://huggingface.co/docs/huggingface_hub/guides/download#download-from-the-cli).
To accelerate downloads on fast connections (1Gbit/s or higher), install `hf_transfer`:
```shell
pip3 install hf_transfer
```
And set environment variable `HF_HUB_ENABLE_HF_TRANSFER` to `1`:
```shell
HF_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download andrijdavid/CarbonVillain-en-10.7B-v2-GGUF CarbonVillain-en-10.7B-v2-f16.gguf --local-dir . --local-dir-use-symlinks False
```
Windows Command Line users: You can set the environment variable by running `set HF_HUB_ENABLE_HF_TRANSFER=1` before the download command.
</details>
<!-- README_GGUF.md-how-to-download end -->
<!-- README_GGUF.md-how-to-run start -->
## Example `llama.cpp` command
Make sure you are using `llama.cpp` from commit [d0cee0d](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221) or later.
```shell
./main -ngl 35 -m CarbonVillain-en-10.7B-v2-f16.gguf --color -c 4096 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "<PROMPT>"
```
Change `-ngl 32` to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.
Change `-c 4096` to the desired sequence length. For extended sequence models - eg 8K, 16K, 32K - the necessary RoPE scaling parameters are read from the GGUF file and set by llama.cpp automatically. Note that longer sequence lengths require much more resources, so you may need to reduce this value.
If you want to have a chat-style conversation, replace the `-p <PROMPT>` argument with `-i -ins`
For other parameters and how to use them, please refer to [the llama.cpp documentation](https://github.com/ggerganov/llama.cpp/blob/master/examples/main/README.md)
## How to run in `text-generation-webui`
Further instructions can be found in the text-generation-webui documentation, here: [text-generation-webui/docs/04 ‐ Model Tab.md](https://github.com/oobabooga/text-generation-webui/blob/main/docs/04%20%E2%80%90%20Model%20Tab.md#llamacpp).
## How to run from Python code
You can use GGUF models from Python using the [llama-cpp-python](https://github.com/abetlen/llama-cpp-python) or [ctransformers](https://github.com/marella/ctransformers) libraries. Note that at the time of writing (Nov 27th 2023), ctransformers has not been updated for some time and is not compatible with some recent models. Therefore I recommend you use llama-cpp-python.
### How to load this model in Python code, using llama-cpp-python
For full documentation, please see: [llama-cpp-python docs](https://abetlen.github.io/llama-cpp-python/).
#### First install the package
Run one of the following commands, according to your system:
```shell
# Base ctransformers with no GPU acceleration
pip install llama-cpp-python
# With NVidia CUDA acceleration
CMAKE_ARGS="-DLLAMA_CUBLAS=on" pip install llama-cpp-python
# Or with OpenBLAS acceleration
CMAKE_ARGS="-DLLAMA_BLAS=ON -DLLAMA_BLAS_VENDOR=OpenBLAS" pip install llama-cpp-python
# Or with CLBLast acceleration
CMAKE_ARGS="-DLLAMA_CLBLAST=on" pip install llama-cpp-python
# Or with AMD ROCm GPU acceleration (Linux only)
CMAKE_ARGS="-DLLAMA_HIPBLAS=on" pip install llama-cpp-python
# Or with Metal GPU acceleration for macOS systems only
CMAKE_ARGS="-DLLAMA_METAL=on" pip install llama-cpp-python
# In windows, to set the variables CMAKE_ARGS in PowerShell, follow this format; eg for NVidia CUDA:
$env:CMAKE_ARGS = "-DLLAMA_OPENBLAS=on"
pip install llama-cpp-python
```
#### Simple llama-cpp-python example code
```python
from llama_cpp import Llama
# Set gpu_layers to the number of layers to offload to GPU. Set to 0 if no GPU acceleration is available on your system.
llm = Llama(
model_path="./CarbonVillain-en-10.7B-v2-f16.gguf", # Download the model file first
n_ctx=32768, # The max sequence length to use - note that longer sequence lengths require much more resources
n_threads=8, # The number of CPU threads to use, tailor to your system and the resulting performance
n_gpu_layers=35 # The number of layers to offload to GPU, if you have GPU acceleration available
)
# Simple inference example
output = llm(
"<PROMPT>", # Prompt
max_tokens=512, # Generate up to 512 tokens
stop=["</s>"], # Example stop token - not necessarily correct for this specific model! Please check before using.
echo=True # Whether to echo the prompt
)
# Chat Completion API
llm = Llama(model_path="./CarbonVillain-en-10.7B-v2-f16.gguf", chat_format="llama-2") # Set chat_format according to the model you are using
llm.create_chat_completion(
messages = [
{"role": "system", "content": "You are a story writing assistant."},
{
"role": "user",
"content": "Write a story about llamas."
}
]
)
```
## How to use with LangChain
Here are guides on using llama-cpp-python and ctransformers with LangChain:
* [LangChain + llama-cpp-python](https://python.langchain.com/docs/integrations/llms/llamacpp)
* [LangChain + ctransformers](https://python.langchain.com/docs/integrations/providers/ctransformers)
<!-- README_GGUF.md-how-to-run end -->
<!-- footer end -->
<!-- original-model-card start -->
# Original model card: CarbonVillain-en-10.7B-v2
# CarbonVillain
**This is a model created without learning to oppose indiscriminate carbon emissions.**
This model is an experimental version created using [mergekit](https://github.com/cg123/mergekit).
- merge models
- Weyaxi/SauerkrautLM-UNA-SOLAR-Instruct
- kyujinpy/Sakura-SOLAR-Instruct
- method: slerp
# Prompt Template(s)
```
### User:
{user}
### Assistant:
{asistant}
```
# Evaluation
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_jeonsworld__CarbonVillain-en-10.7B-v2)
| Metric | Value |
| - | ----- |
| Avg. | 74.42 |
| ARC (25-shot) | 71.25 |
| HellaSwag (10-shot) | 88.4 |
| MMLU (5-shot) | 66.31 |
| TruthfulQA (0-shot) | 71.94 |
| Winogrande (5-shot) | 83.35 |
| GSM8K (5-shot) | 65.28 |
<!-- original-model-card end --> |
IndexTeam/Index-1.9B-Character-GGUF | IndexTeam | "2024-06-26T08:01:26Z" | 1,682 | 0 | null | [
"gguf",
"license:other",
"region:us"
] | null | "2024-06-25T06:13:15Z" | ---
license: other
license_name: license
license_link: LICENSE
---
<div align="center">
<h1>
Index-1.9B-Character-GGUF
</h1>
</div>
This repository is the GGUF version of [Index-1.9B-Character](https://huggingface.co/IndexTeam/Index-1.9B-Character), which adapts to llama.cpp and also provides ModelFile adaptation for Ollma.
For usage and related codes, please see [Index-1.9B/roleplay](https://github.com/bilibili/Index-1.9B/tree/main/roleplay)
For more details, see our [GitHub](https://github.com/bilibili/Index-1.9B) and [Index-1.9B Technical Report](https://github.com/bilibili/Index-1.9B/blob/main/Index-1.9B%20%E6%8A%80%E6%9C%AF%E6%8A%A5%E5%91%8A.pdf)
|
Crosstyan/BPModel | Crosstyan | "2023-05-31T10:02:50Z" | 1,681 | 150 | diffusers | [
"diffusers",
"stable-diffusion",
"stable-diffusion-diffusers",
"text-to-image",
"safetensors",
"en",
"dataset:Crosstyan/BPDataset",
"arxiv:2212.03860",
"doi:10.57967/hf/0223",
"license:creativeml-openrail-m",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
] | text-to-image | "2022-12-20T11:55:42Z" | ---
language:
- en
license: creativeml-openrail-m
tags:
- stable-diffusion
- stable-diffusion-diffusers
- text-to-image
- safetensors
inference: true
thumbnail: https://s2.loli.net/2023/05/31/bl27yWANrT3asoG.png
widget:
- text: >-
1girl with blonde two side up disheveled hair red eyes in black serafuku red
ribbon, upper body, simple background, grey background, collarbone
example_title: example 1girl
datasets:
- Crosstyan/BPDataset
library_name: diffusers
---
# BPModel
## Update
**2023-01-02:** I wasted more GPU hours to train it a little bit more overfitting. Check out [bp_mk3.safetensors](bp_mk3.safetensors) and [bp_mk5.safetensors](bp_mk5.safetensors). Prepare yourself own VAE! Update your WebUI if you can't load [safetensors](https://github.com/huggingface/safetensors). Adds lots of samples in `images` folder!
**2023-01-06:** Checkout [NMFSAN](NMFSAN/README.md) for a new model trained with custom embeddings.
## Introduction
BPModel is an experimental Stable Diffusion model based on [ACertainty](https://huggingface.co/JosephusCheung/ACertainty) from [Joseph Cheung](https://huggingface.co/JosephusCheung).
Why is the Model even existing? There are loads of Stable Diffusion model out there, especially anime style models.
Well, is there any models trained with resolution base resolution (`base_res`) 768 even 1024 before? Don't think so.
Here it is, the BPModel, a Stable Diffusion model you may love or hate.
Trained with 5k high quality images that suit my taste (not necessary yours unfortunately) from [Sankaku Complex](https://chan.sankakucomplex.com) with annotations.
The dataset is public in [Crosstyan/BPDataset](https://huggingface.co/datasets/Crosstyan/BPDataset) for the sake of full disclosure .
Pure combination of tags may not be the optimal way to describe the image,
but I don't need to do extra work.
And no, I won't feed any AI generated image
to the model even it might outlaw the model from being used in some countries.
The training of a high resolution model requires a significant amount of GPU
hours and can be costly. In this particular case, 10 V100 GPU hours were spent
on training 30 epochs with a resolution of 512, while 60 V100 GPU hours were spent
on training 30 epochs with a resolution of 768. An additional 100 V100 GPU hours
were also spent on training a model with a resolution of 1024, although **ONLY** 10
epochs were run. The results of the training on the 1024 resolution model did
not show a significant improvement compared to the 768 resolution model, and the
resource demands, achieving a batch size of 1 on a V100 with 32G VRAM, were
high. However, training on the 768 resolution did yield better results than
training on the 512 resolution, and it is worth considering as an option. It is
worth noting that Stable Diffusion 2.x also chose to train on a 768 resolution
model. However, it may be more efficient to start with training on a 512
resolution model due to the slower training process and the need for additional
prior knowledge to speed up the training process when working with a 768
resolution.
[Mikubill/naifu-diffusion](https://github.com/Mikubill/naifu-diffusion) is used as training script and I also recommend to
checkout [CCRcmcpe/scal-sdt](https://github.com/CCRcmcpe/scal-sdt).
The configuration for 1024 and 768 resolution with aspect ratio bucket is presented here.
```yaml
# 768
arb:
enabled: true
debug: false
base_res: [768, 768]
max_size: [1152, 768]
divisible: 64
max_ar_error: 4
min_dim: 512
dim_limit: 1792
# 1024
arb:
enabled: true
debug: false
base_res: [1024, 1024]
max_size: [1536, 1024]
divisible: 64
max_ar_error: 4
min_dim: 960
dim_limit: 2389
```
## Limitation
The limitation described in [SCAL-SDT Wiki](https://github.com/CCRcmcpe/scal-sdt/wiki#what-you-should-expect)
is still applied.
> SD cannot generate human body properly, like generating 6 fingers on one hand.
BPModel can generate [more proper kitty cat](https://twitter.com/crosstyan/status/1606026536246685696) (if you know what I mean) than other anime model,
but it's still not perfect. As results presented in [Diffusion Art or Digital Forgery? Investigating Data Replication in Diffusion Models](https://arxiv.org/abs/2212.03860), the copy and paste effect is still observed.
Anything v3™ has been proven to be the most popular anime model in the community, but it's not perfect either as
described in [JosephusCheung/ACertainThing](https://huggingface.co/JosephusCheung/ACertainThing)
> It does not always stay true to your prompts; it adds irrelevant details, and sometimes these details are highly homogenized.
BPModel, which has been fine-tuned on a relatively small dataset, is prone
to overfit inherently. This is not surprising given the size of the dataset, but the
strong prior knowledge of ACertainty (full Danbooru) and Stable Diffusion
(LAION) helps to minimize the impact of overfitting.
However I believe it would perform
better than some artist style DreamBooth model which only train with a few
hundred images or even less. I also oppose changing style by merging model since You
could apply different style by training with proper captions and prompting.
Besides some of images in my dataset have the artist name in the caption, however some artist name will
be misinterpreted by CLIP when tokenizing. For example, *as109* will be tokenized as `[as, 1, 0, 9]` and
*fuzichoco* will become `[fu, z, ic, hoco]`. Romanized Japanese suffers from the problem a lot and
I don't have a good solution to fix it other than changing the artist name in the caption, which is
time consuming and you can't promise the token you choose is unique enough. [Remember the sks?](https://www.reddit.com/r/StableDiffusion/comments/yju5ks/from_one_of_the_original_dreambooth_authors_stop/)
Language drift problem is still exist. There's nothing I can do unless I can find a way to
generate better caption or caption the image manually. [OFA](https://github.com/OFA-Sys/OFA)
combined with [convnext-tagger](https://huggingface.co/SmilingWolf/wd-v1-4-convnext-tagger) could
provide a better result for SFW content. However fine tune is necessary for NSFW content, which
I don't think anyone would like to do. (Could Unstable Diffusion give us surprise?)
## Cherry Picked Samples
Here're some **cherry picked** samples.
I were using [xformers](https://github.com/facebookresearch/xformers) when generating these sample
and it might yield slight different result even with the same seed (welcome to the non deterministic field).
"`Upscale latent space image when doing hires. fix`" is enabled also.
```txt
by (fkey:1) (shion:0.4) [sketch:0.75] (closed mouth expressionless:1) cat ears nekomimi 1girl, wearing a white sailor uniform with a short skirt and white pantyhose standing on the deck of a yacht, cowboy shot, and the sun setting behind her in the background, light particle, bokeh
Negative prompt: lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, worst quality, low quality, normal quality, lipstick, 2koma, 3koma, dutch angle, blush, from behind
Steps: 28, Sampler: Euler a, CFG scale: 12, Seed: 4236324744, Size: 960x1600, Model hash: 855959a4, Denoising strength: 0.7, Clip skip: 2, ENSD: 31337, First pass size: 0x0
```
```txt
1girl in black serafuku standing in a field solo, food, fruit, lemon, bubble, planet, moon, orange \(fruit\), lemon slice, leaf, fish, orange slice, by (tabi:1.25), spot color, looking at viewer, closeup cowboy shot
Negative prompt: (bad:0.81), (comic:0.81), (cropped:0.81), (error:0.81), (extra:0.81), (low:0.81), (lowres:0.81), (speech:0.81), (worst:0.81), (blush:0.9), 2koma, 3koma, 4koma, collage, lipstick
Steps: 18, Sampler: DDIM, CFG scale: 7, Seed: 2017390109, Size: 768x1600, Model hash: fed5b383, Batch size: 4, Batch pos: 1, Denoising strength: 0.7, Clip skip: 2, ENSD: 31337, First pass size: 0x0
```
```txt
[sketch:0.75] [(oil painting:0.5)::0.75] by (fuzichoco:0.8) shion (fkey:0.9), fang solo cat ears nekomimi girl with multicolor streaked messy hair blue [black|blue] long hair bangs blue eyes in blue sailor collar school uniform serafuku short sleeves hand on own cheek hand on own face sitting, upper body, strawberry sweets ice cream food fruit spoon orange parfait
Negative prompt: (bad:0.98), (normal:0.98), (comic:0.81), (cropped:0.81), (error:0.81), (extra:0.81), (low:0.81), (lowres:1), (speech:0.81), (worst:0.81), 2koma, 3koma, 4koma, collage, lipstick
Steps: 40, Sampler: Euler a, CFG scale: 8, Seed: 910302581, Size: 960x1600, Model hash: fed5b383, Batch size: 4, Batch pos: 2, Denoising strength: 0.7, Clip skip: 2, ENSD: 31337, First pass size: 0x0
```
```txt
(best:0.7), highly detailed,1girl,upper body,beautiful detailed eyes, medium_breasts, long hair,grey hair, grey eyes, curly hair, bangs,empty eyes,expressionless,twintails, beautiful detailed sky, beautiful detailed water, [cinematic lighting:0.6], upper body, school uniform,black ribbon,light smile
Negative prompt: (bad:0.98), (normal:0.98), (comic:0.81), (cropped:0.81), (error:0.81), (extra:0.81), (low:0.81), (lowres:1), (speech:0.81), (worst:0.81), 2koma, 3koma, 4koma, collage, lipstick
Steps: 40, Sampler: Euler, CFG scale: 8.5, Seed: 2311603025, Size: 960x1600, Model hash: fed5b383, Batch size: 4, Batch pos: 3, Denoising strength: 0.7, Clip skip: 2, ENSD: 31337, First pass size: 0x0
```
*I don't think other model can do that.*
```txt
by [shion (fkey:0.9):momoko \(momopoco\):0.15], fang solo cat ears nekomimi girl with multicolor streaked messy hair blue [black|blue] long hair bangs blue eyes in blue sailor collar school uniform serafuku short sleeves hand on own cheek (middle finger:1.1) sitting, upper body, strawberry sweets ice cream food fruit spoon orange parfait
Negative prompt: (bad:0.98), (normal:0.98), (comic:0.81), (cropped:0.81), (error:0.81), (extra:0.81), (low:0.81), (lowres:1), (speech:0.81), (worst:0.81), 2koma, 3koma, 4koma, collage, lipstick
Steps: 40, Sampler: Euler a, CFG scale: 8, Seed: 2496891010, Size: 960x1600, Model hash: fed5b383, Batch size: 4, Batch pos: 1, Denoising strength: 0.7, Clip skip: 2, ENSD: 31337, First pass size: 0x0
```
```txt
by [shion (fkey:0.9):momoko \(momopoco\):0.55], closed mouth fang solo cat ears nekomimi girl with multicolor streaked messy hair blue [black|blue] long hair bangs blue eyes in blue sailor collar school uniform serafuku short sleeves (middle finger:1.1) sitting, upper body, strawberry sweets ice cream food fruit spoon orange parfait
Negative prompt: (bad:0.98), (normal:0.98), (comic:0.81), (cropped:0.81), (error:0.81), (extra:0.81), (low:0.81), (lowres:1), (speech:0.81), (worst:0.81), 2koma, 3koma, 4koma, collage, lipstick, (chibi:0.8)
Steps: 40, Sampler: Euler a, CFG scale: 8, Seed: 2668993375, Size: 960x1600, Model hash: fed5b383, Batch size: 4, Batch pos: 3, Denoising strength: 0.7, Clip skip: 2, ENSD: 31337, First pass size: 0x0
```
more samples can be found in [images](images/00976-3769766671_20221226155509.png) folder.
## Usage
The [`bp_1024_e10.ckpt`](bp_1024_e10.ckpt) doesn't include any VAE and you should using other popular VAE in the community when using with [AUTOMATIC1111/stable-diffusion-webui](https://github.com/AUTOMATIC1111/stable-diffusion-webui) or you would see the
LaTeNt SpAcE!
Use [`bp_1024_with_vae_te.ckpt`](bp_1024_with_vae_te.ckpt) if you don't have VAE and text encoder with you, still
EMA weight is not included and it's fp16.
If you want to continue training, use [`bp_1024_e10_ema.ckpt`](bp_1024_e10_ema.ckpt) which is the ema unet weight
and with fp32 precision.
For better performance, it is strongly recommended to use Clip skip (CLIP stop at last layers) 2. It's also recommended to use turn on
"`Upscale latent space image when doing hires. fix`" in the settings of [AUTOMATIC1111/stable-diffusion-webui](https://github.com/AUTOMATIC1111/stable-diffusion-webui)
which adds intricate details when using `Highres. fix`.
## About the Model Name
I asked the [chatGPT](https://openai.com/blog/chatgpt/) what the proper explanation of abbreviation BP could be.
```txt
Here are a few more ideas for creative interpretations of the abbreviation "BP":
- Brightest Point - This could refer to a moment of exceptional brilliance or clarity.
- Brainpower - the abbreviation refers to something that requires a lot of mental effort or intelligence to accomplish.
- Bespoke Partition - A custom made section that separates two distinct areas.
- Bukkake Picchi - A Japanese style of rice dish.
- Bokeh Picker - A traditional Japanese photography technique that involves selecting points of light from a digital image.
- Bipolarity - Two distinct and opposing elements or perspectives.
Note that "BP" is often used as an abbreviation for "blood pressure," so it is important to context to determine the most appropriate interpretation of the abbreviation.
```
Personally, I would call it "Big Pot".
## License
This model is open access and available to all, with a CreativeML OpenRAIL-M license further specifying rights and usage. The CreativeML OpenRAIL License specifies:
1. You can't use the model to deliberately produce nor share illegal or harmful outputs or content
2. The authors claims no rights on the outputs you generate, you are free to use them and are accountable for their use which must not go against the provisions set in the license
3. You may re-distribute the weights and use the model commercially and/or as a service. If you do, please be aware you have to include the same use restrictions as the ones in the license and share a copy of the CreativeML OpenRAIL-M to all your users (please read the license entirely and carefully) Please read the full license [here](https://huggingface.co/spaces/CompVis/stable-diffusion-license/blob/main/license.txt) |
TehVenom/PPO_Pygway-V8p4_Dev-6b | TehVenom | "2023-05-19T18:01:37Z" | 1,681 | 7 | transformers | [
"transformers",
"pytorch",
"gptj",
"text-generation",
"en",
"license:apache-2.0",
"autotrain_compatible",
"region:us"
] | text-generation | "2023-03-17T13:08:51Z" | ---
language: en
license: apache-2.0
commercial: 'no'
inference: false
---
# GPT-J 6B - PPO_Pygway Mix
## Model description
This is a merged model, using a weighted parameter blend strategy at a (20:20:60) ratio between the models:
- [20%] - KoboldAI/GPT-J-6B-Janeway: https://huggingface.co/KoboldAI/GPT-J-6B-Janeway
- [20%] - reciprocate/ppo_hh_gpt-j: https://huggingface.co/reciprocate/ppo_hh_gpt-j
- [60%] - Pygmalion/Pygmalion-6b DEV (V8 / Part 4): https://huggingface.co/Pygmalion/Pygmalion-6b
By their respective authors.
**Warning: PPO_Pygway-V8p4_Dev-6b may generate NSFW or inappropriate content due to the base models (Mainly [Pygmalion/Pygmalion-6b V8P4](https://huggingface.co/Pygmalion/Pygmalion-6b)) being trained on general user logs, and internet archives.**
### Intended Use:
Research purposes only, intended for responsible use.
Express a conversation in natural language, and PPO_Pygmalion will pick up on the conversational format.
Try starting a two line prompt such as:
```
Bot: "Hello, how are you?"
You: "I am doing just fine, thank you."
```
Or any other topic, and the model will carry on in this back and forth style.
## Information:
For more details, check out the related source models, especially [Pygmalion/Pygmalion-6b V8P4](https://huggingface.co/Pygmalion/Pygmalion-6b) for more information on how to utilize the chat bot formatting expected.
In a similar manner to fine-tuning, merging weights does not add information but transforms it, therefore it is important to consider trade-offs.
PPO_Pygway combines `ppo_hh_gpt-j`, `Janeway-6b` and `Pygmalion-6b V8P4`; all three models were blended in a two step process using a simple weighted parameter method
```
(X*A + Y*B)
```
With X & Y being the model weighs, and A/B being how strongly they are represented within the final value.
The intent of this is to elevate the end-model by borrowing the strongly represented aspects out of each base model,
but may also weaken other faces of each model, which can be desirable if the base models have problematic traits that need to be worked on.
Blend was done in FP32 and output saved in FP16 for reduced storage needs.
## Limitations and biases
Based on known problems with NLP technology, potential relevant factors include bias (gender, profession, race and religion).
<ins>Warning: This model has a moderate NSFW bias.</ins>
### License
GPT-J-6b is licensed by EleutherAI under the apache-2.0 license. All Rights Reserved.
### BibTeX entry and citation info
```
@misc{gpt-j,
author = {Wang, Ben and Komatsuzaki, Aran},
title = {{GPT-J-6B: A 6 Billion Parameter Autoregressive Language Model}},
howpublished = {\url{https://github.com/kingoflolz/mesh-transformer-jax}},
year = 2021,
month = May
}
```
### Credits To:
Models involved:
- https://huggingface.co/EleutherAI/gpt-j-6B
- https://huggingface.co/Pygmalion/Pygmalion-6b
- https://huggingface.co/reciprocate/ppo_hh_gpt-j
- https://huggingface.co/KoboldAI/GPT-J-6B-Janeway
Average weights merging Script credit to Concedo:
- https://huggingface.co/concedo
### Related datasets and articles:
PPO_HH-GPT-J-6b's Dataset is a variant of the Helpful Harmless assistant themed
dataset and Proximal Policy Optimization, specific datasets
used are unknown; listed repo datasets include:
- https://huggingface.co/datasets/reciprocate/summarize_eval_ilql
- https://huggingface.co/datasets/reciprocate/hh_eval_ilql
PPO explained:
- https://paperswithcode.com/method/ppo
Potential HH-type datasets utilized:
- https://huggingface.co/HuggingFaceH4
- https://huggingface.co/datasets/Anthropic/hh-rlhf
No formal evaluation is available for this model at this time.
It is recommend to use this model with the KoboldAI software. All feedback and comments can be directed to TeH_Venom on the KoboldAI discord.
|
chestnutlzj/ChatLaw-Text2Vec | chestnutlzj | "2023-06-29T05:12:16Z" | 1,681 | 101 | transformers | [
"transformers",
"pytorch",
"bert",
"feature-extraction",
"sentence-similarity",
"zh",
"arxiv:2306.16092",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | sentence-similarity | "2023-06-17T05:07:53Z" | ---
license: apache-2.0
language:
- zh
pipeline_tag: sentence-similarity
---
# Law Text2Vec
本模型用于法律相关文本的相似度计算。可用于制作向量数据库等。
# Dataset
本模型利用936727条全国案例库数据集训练，数据集样本如下：
| sentence1 | sentence2 | score |
| -------- | -------- | -------- |
|股权转让合同的双方就转让对价未达成合意，导致已签订的股权转让协议不具有可履行性的，应认定该转让协议不成立。|有限责任公司的股东会决议确认了有关股东之间股权转让的相关事宜，但对转让价款规定不明确，当事人不能达成补充协议的，讼争股东之间的股权转让合同是否成立？|1|
|租赁房屋消防要求不达标，能否导致合同目的不能实现，合同是否当然无效的问题。|原审认为，二被告作为承租人租赁的是一般房屋，双方对租赁物了解，标的物是符合合同要求的。租赁房屋存在与相邻建筑防火间距不足，疏散通道的宽度不够的问题。该标的物的相邻建筑防火间距和疏散通道宽度均达不到国家标准。承租人取得租赁房屋后从事宾馆经营，提升了消防要求，但阻隔合同目的实现不是必然的，不支持合同无效。 再审认为，该租赁房屋在建成后，一直作为服务性经营场所，本案提及的消防问题，程度不一的存在。但未发现以前有行政管理部门禁止其经营的记录。本次公安消防的通知是整改，并不是禁止经营。公安部2012年颁布的《建设工程消防监督管理规定》强制消防要求达标的范围，是指在50米以下的建筑物。也就是该房屋作为租赁物建立合同关系，不违反国家的强制性规定。参照最高人民法院[2003]民一他字第11号函复《关于未经消防验收合格而订立的房屋租赁合同如何认定其效力》的相关意见，认定双方签订的租赁合同成立并有效。|1|
# Examples
> 请问夫妻之间共同财产如何定义？
1. 最高人民法院关于适用《婚姻法》若干问题的解释（三）(2011-08-09): 第五条 夫妻一方个人财产在婚后产生的收益，除孳息和自然增值外，应认定为夫妻共同财产。
2. 最高人民法院关于适用《婚姻法》若干问题的解释（二）的补充规定(2017-02-28): 第十九条 由一方婚前承租、婚后用共同财产购买的房屋，房屋权属证书登记在一方名下的，应当认定为夫妻共同财产。
3. 最高人民法院关于适用《婚姻法》若干问题的解释（二）的补充规定(2017-02-28): 第二十二条 当事人结婚前，父母为双方购置房屋出资的，该出资应当认定为对自己子女的个人赠与，但父母明确表示赠与双方的除外。当事人结婚后，父母为双方购置房屋出资的，该出资应当认定为对夫妻双方的赠与，但父母明确表示赠与一方的除外。
> 请问民间借贷的利息有什么限制
1. 合同法(1999-03-15): 第二百零六条 借款人应当按照约定的期限返还借款。对借款期限没有约定或者约定不明确，依照本法第六十一条的规定仍不能确定的，借款人可以随时返还；贷款人可以催告借款人在合理期限内返还。
2. 合同法(1999-03-15): 第二百零五条 借款人应当按照约定的期限支付利息。对支付利息的期限没有约定或者约定不明确，依照本法第六十一条的规定仍不能确定，借款期间不满一年的，应当在返还借款时一并支付；借款期间一年以上的，应当在每届满一年时支付，剩余期间不满一年的，应当在返还借款时一并支付。
3. 最高人民法院关于审理民间借贷案件适用法律若干问题的规定(2020-08-19): 第二十六条 出借人请求借款人按照合同约定利率支付利息的，人民法院应予支持，但是双方约定的利率超过合同成立时一年期贷款市场报价利率四倍的除外。前款所称“一年期贷款市场报价利率”，是指中国人民银行授权全国银行间同业拆借中心自2019年8月20日起每月发布的一年期贷款市场报价利率。
# Usage
```python
from sentence_transformers import SentenceTransformer, LoggingHandler, losses, models, util
from sentence_transformers.util import cos_sim
model_path = "your_model_path"
model = SentenceTransformer(model_path).cuda()
sentence1 = "合同法(1999-03-15): 第二百零六条 借款人应当按照约定的期限返还借款。对借款期限没有约定或者约定不明确，依照本法第六十一条的规定仍不能确定的，借款人可以随时返还；贷款人可以催告借款人在合理期限内返还。"
sentence2 = "请问如果借款没还怎么办。"
encoded_sentence1 = model.encode(sentence1)
encoded_sentence2 = model.encode(sentence2)
print(cos_sim(encoded_sentence1, encoded_sentence2))
# tensor([[0.9960]])
```
欢迎引用我们:
```
@misc{cui2023chatlaw,
title={ChatLaw: Open-Source Legal Large Language Model with Integrated External Knowledge Bases},
author={Jiaxi Cui and Zongjian Li and Yang Yan and Bohua Chen and Li Yuan},
year={2023},
eprint={2306.16092},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
@misc{ChatLaw,
author={Jiaxi Cui and Zongjian Li and Yang Yan and Bohua Chen and Li Yuan},
title={ChatLaw},
year={2023},
publisher={GitHub},
journal={GitHub repository},
howpublished={\url{https://github.com/PKU-YuanGroup/ChatLaw}},
}
```
|
TheBloke/vicuna-13B-v1.5-GGUF | TheBloke | "2023-09-27T12:47:19Z" | 1,681 | 17 | transformers | [
"transformers",
"gguf",
"llama",
"arxiv:2307.09288",
"arxiv:2306.05685",
"base_model:lmsys/vicuna-13b-v1.5",
"license:llama2",
"text-generation-inference",
"region:us"
] | null | "2023-09-05T03:48:43Z" | ---
license: llama2
model_name: Vicuna 13B v1.5
base_model: lmsys/vicuna-13b-v1.5
inference: false
model_creator: lmsys
model_type: llama
prompt_template: 'A chat between a curious user and an artificial intelligence assistant.
The assistant gives helpful, detailed, and polite answers to the user''s questions.
USER: {prompt} ASSISTANT:
'
quantized_by: TheBloke
---
<!-- header start -->
<!-- 200823 -->
<div style="width: auto; margin-left: auto; margin-right: auto">
<img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
</div>
<div style="display: flex; justify-content: space-between; width: 100%;">
<div style="display: flex; flex-direction: column; align-items: flex-start;">
<p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://discord.gg/theblokeai">Chat & support: TheBloke's Discord server</a></p>
</div>
<div style="display: flex; flex-direction: column; align-items: flex-end;">
<p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p>
</div>
</div>
<div style="text-align:center; margin-top: 0em; margin-bottom: 0em"><p style="margin-top: 0.25em; margin-bottom: 0em;">TheBloke's LLM work is generously supported by a grant from <a href="https://a16z.com">andreessen horowitz (a16z)</a></p></div>
<hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
<!-- header end -->
# Vicuna 13B v1.5 - GGUF
- Model creator: [lmsys](https://huggingface.co/lmsys)
- Original model: [Vicuna 13B v1.5](https://huggingface.co/lmsys/vicuna-13b-v1.5)
<!-- description start -->
## Description
This repo contains GGUF format model files for [lmsys's Vicuna 13B v1.5](https://huggingface.co/lmsys/vicuna-13b-v1.5).
<!-- description end -->
<!-- README_GGUF.md-about-gguf start -->
### About GGUF
GGUF is a new format introduced by the llama.cpp team on August 21st 2023. It is a replacement for GGML, which is no longer supported by llama.cpp. GGUF offers numerous advantages over GGML, such as better tokenisation, and support for special tokens. It is also supports metadata, and is designed to be extensible.
Here is an incomplate list of clients and libraries that are known to support GGUF:
* [llama.cpp](https://github.com/ggerganov/llama.cpp). The source project for GGUF. Offers a CLI and a server option.
* [text-generation-webui](https://github.com/oobabooga/text-generation-webui), the most widely used web UI, with many features and powerful extensions. Supports GPU acceleration.
* [KoboldCpp](https://github.com/LostRuins/koboldcpp), a fully featured web UI, with GPU accel across all platforms and GPU architectures. Especially good for story telling.
* [LM Studio](https://lmstudio.ai/), an easy-to-use and powerful local GUI for Windows and macOS (Silicon), with GPU acceleration.
* [LoLLMS Web UI](https://github.com/ParisNeo/lollms-webui), a great web UI with many interesting and unique features, including a full model library for easy model selection.
* [Faraday.dev](https://faraday.dev/), an attractive and easy to use character-based chat GUI for Windows and macOS (both Silicon and Intel), with GPU acceleration.
* [ctransformers](https://github.com/marella/ctransformers), a Python library with GPU accel, LangChain support, and OpenAI-compatible AI server.
* [llama-cpp-python](https://github.com/abetlen/llama-cpp-python), a Python library with GPU accel, LangChain support, and OpenAI-compatible API server.
* [candle](https://github.com/huggingface/candle), a Rust ML framework with a focus on performance, including GPU support, and ease of use.
<!-- README_GGUF.md-about-gguf end -->
<!-- repositories-available start -->
## Repositories available
* [AWQ model(s) for GPU inference.](https://huggingface.co/TheBloke/vicuna-13B-v1.5-AWQ)
* [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/vicuna-13B-v1.5-GPTQ)
* [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/vicuna-13B-v1.5-GGUF)
* [lmsys's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/lmsys/vicuna-13b-v1.5)
<!-- repositories-available end -->
<!-- prompt-template start -->
## Prompt template: Vicuna
```
A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions. USER: {prompt} ASSISTANT:
```
<!-- prompt-template end -->
<!-- compatibility_gguf start -->
## Compatibility
These quantised GGUFv2 files are compatible with llama.cpp from August 27th onwards, as of commit [d0cee0d36d5be95a0d9088b674dbb27354107221](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221)
They are also compatible with many third party UIs and libraries - please see the list at the top of this README.
## Explanation of quantisation methods
<details>
<summary>Click to see details</summary>
The new methods available are:
* GGML_TYPE_Q2_K - "type-1" 2-bit quantization in super-blocks containing 16 blocks, each block having 16 weight. Block scales and mins are quantized with 4 bits. This ends up effectively using 2.5625 bits per weight (bpw)
* GGML_TYPE_Q3_K - "type-0" 3-bit quantization in super-blocks containing 16 blocks, each block having 16 weights. Scales are quantized with 6 bits. This end up using 3.4375 bpw.
* GGML_TYPE_Q4_K - "type-1" 4-bit quantization in super-blocks containing 8 blocks, each block having 32 weights. Scales and mins are quantized with 6 bits. This ends up using 4.5 bpw.
* GGML_TYPE_Q5_K - "type-1" 5-bit quantization. Same super-block structure as GGML_TYPE_Q4_K resulting in 5.5 bpw
* GGML_TYPE_Q6_K - "type-0" 6-bit quantization. Super-blocks with 16 blocks, each block having 16 weights. Scales are quantized with 8 bits. This ends up using 6.5625 bpw
Refer to the Provided Files table below to see what files use which methods, and how.
</details>
<!-- compatibility_gguf end -->
<!-- README_GGUF.md-provided-files start -->
## Provided files
| Name | Quant method | Bits | Size | Max RAM required | Use case |
| ---- | ---- | ---- | ---- | ---- | ----- |
| [vicuna-13b-v1.5.Q2_K.gguf](https://huggingface.co/TheBloke/vicuna-13B-v1.5-GGUF/blob/main/vicuna-13b-v1.5.Q2_K.gguf) | Q2_K | 2 | 5.43 GB| 7.93 GB | smallest, significant quality loss - not recommended for most purposes |
| [vicuna-13b-v1.5.Q3_K_S.gguf](https://huggingface.co/TheBloke/vicuna-13B-v1.5-GGUF/blob/main/vicuna-13b-v1.5.Q3_K_S.gguf) | Q3_K_S | 3 | 5.66 GB| 8.16 GB | very small, high quality loss |
| [vicuna-13b-v1.5.Q3_K_M.gguf](https://huggingface.co/TheBloke/vicuna-13B-v1.5-GGUF/blob/main/vicuna-13b-v1.5.Q3_K_M.gguf) | Q3_K_M | 3 | 6.34 GB| 8.84 GB | very small, high quality loss |
| [vicuna-13b-v1.5.Q3_K_L.gguf](https://huggingface.co/TheBloke/vicuna-13B-v1.5-GGUF/blob/main/vicuna-13b-v1.5.Q3_K_L.gguf) | Q3_K_L | 3 | 6.93 GB| 9.43 GB | small, substantial quality loss |
| [vicuna-13b-v1.5.Q4_0.gguf](https://huggingface.co/TheBloke/vicuna-13B-v1.5-GGUF/blob/main/vicuna-13b-v1.5.Q4_0.gguf) | Q4_0 | 4 | 7.37 GB| 9.87 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| [vicuna-13b-v1.5.Q4_K_S.gguf](https://huggingface.co/TheBloke/vicuna-13B-v1.5-GGUF/blob/main/vicuna-13b-v1.5.Q4_K_S.gguf) | Q4_K_S | 4 | 7.41 GB| 9.91 GB | small, greater quality loss |
| [vicuna-13b-v1.5.Q4_K_M.gguf](https://huggingface.co/TheBloke/vicuna-13B-v1.5-GGUF/blob/main/vicuna-13b-v1.5.Q4_K_M.gguf) | Q4_K_M | 4 | 7.87 GB| 10.37 GB | medium, balanced quality - recommended |
| [vicuna-13b-v1.5.Q5_0.gguf](https://huggingface.co/TheBloke/vicuna-13B-v1.5-GGUF/blob/main/vicuna-13b-v1.5.Q5_0.gguf) | Q5_0 | 5 | 8.97 GB| 11.47 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| [vicuna-13b-v1.5.Q5_K_S.gguf](https://huggingface.co/TheBloke/vicuna-13B-v1.5-GGUF/blob/main/vicuna-13b-v1.5.Q5_K_S.gguf) | Q5_K_S | 5 | 8.97 GB| 11.47 GB | large, low quality loss - recommended |
| [vicuna-13b-v1.5.Q5_K_M.gguf](https://huggingface.co/TheBloke/vicuna-13B-v1.5-GGUF/blob/main/vicuna-13b-v1.5.Q5_K_M.gguf) | Q5_K_M | 5 | 9.23 GB| 11.73 GB | large, very low quality loss - recommended |
| [vicuna-13b-v1.5.Q6_K.gguf](https://huggingface.co/TheBloke/vicuna-13B-v1.5-GGUF/blob/main/vicuna-13b-v1.5.Q6_K.gguf) | Q6_K | 6 | 10.68 GB| 13.18 GB | very large, extremely low quality loss |
| [vicuna-13b-v1.5.Q8_0.gguf](https://huggingface.co/TheBloke/vicuna-13B-v1.5-GGUF/blob/main/vicuna-13b-v1.5.Q8_0.gguf) | Q8_0 | 8 | 13.83 GB| 16.33 GB | very large, extremely low quality loss - not recommended |
**Note**: the above RAM figures assume no GPU offloading. If layers are offloaded to the GPU, this will reduce RAM usage and use VRAM instead.
<!-- README_GGUF.md-provided-files end -->
<!-- README_GGUF.md-how-to-download start -->
## How to download GGUF files
**Note for manual downloaders:** You almost never want to clone the entire repo! Multiple different quantisation formats are provided, and most users only want to pick and download a single file.
The following clients/libraries will automatically download models for you, providing a list of available models to choose from:
- LM Studio
- LoLLMS Web UI
- Faraday.dev
### In `text-generation-webui`
Under Download Model, you can enter the model repo: TheBloke/vicuna-13B-v1.5-GGUF and below it, a specific filename to download, such as: vicuna-13b-v1.5.q4_K_M.gguf.
Then click Download.
### On the command line, including multiple files at once
I recommend using the `huggingface-hub` Python library:
```shell
pip3 install huggingface-hub>=0.17.1
```
Then you can download any individual model file to the current directory, at high speed, with a command like this:
```shell
huggingface-cli download TheBloke/vicuna-13B-v1.5-GGUF vicuna-13b-v1.5.q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
```
<details>
<summary>More advanced huggingface-cli download usage</summary>
You can also download multiple files at once with a pattern:
```shell
huggingface-cli download TheBloke/vicuna-13B-v1.5-GGUF --local-dir . --local-dir-use-symlinks False --include='*Q4_K*gguf'
```
For more documentation on downloading with `huggingface-cli`, please see: [HF -> Hub Python Library -> Download files -> Download from the CLI](https://huggingface.co/docs/huggingface_hub/guides/download#download-from-the-cli).
To accelerate downloads on fast connections (1Gbit/s or higher), install `hf_transfer`:
```shell
pip3 install hf_transfer
```
And set environment variable `HF_HUB_ENABLE_HF_TRANSFER` to `1`:
```shell
HUGGINGFACE_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download TheBloke/vicuna-13B-v1.5-GGUF vicuna-13b-v1.5.q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
```
Windows CLI users: Use `set HUGGINGFACE_HUB_ENABLE_HF_TRANSFER=1` before running the download command.
</details>
<!-- README_GGUF.md-how-to-download end -->
<!-- README_GGUF.md-how-to-run start -->
## Example `llama.cpp` command
Make sure you are using `llama.cpp` from commit [d0cee0d36d5be95a0d9088b674dbb27354107221](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221) or later.
```shell
./main -ngl 32 -m vicuna-13b-v1.5.q4_K_M.gguf --color -c 4096 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions. USER: {prompt} ASSISTANT:"
```
Change `-ngl 32` to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.
Change `-c 4096` to the desired sequence length. For extended sequence models - eg 8K, 16K, 32K - the necessary RoPE scaling parameters are read from the GGUF file and set by llama.cpp automatically.
If you want to have a chat-style conversation, replace the `-p <PROMPT>` argument with `-i -ins`
For other parameters and how to use them, please refer to [the llama.cpp documentation](https://github.com/ggerganov/llama.cpp/blob/master/examples/main/README.md)
## How to run in `text-generation-webui`
Further instructions here: [text-generation-webui/docs/llama.cpp.md](https://github.com/oobabooga/text-generation-webui/blob/main/docs/llama.cpp.md).
## How to run from Python code
You can use GGUF models from Python using the [llama-cpp-python](https://github.com/abetlen/llama-cpp-python) or [ctransformers](https://github.com/marella/ctransformers) libraries.
### How to load this model from Python using ctransformers
#### First install the package
```bash
# Base ctransformers with no GPU acceleration
pip install ctransformers>=0.2.24
# Or with CUDA GPU acceleration
pip install ctransformers[cuda]>=0.2.24
# Or with ROCm GPU acceleration
CT_HIPBLAS=1 pip install ctransformers>=0.2.24 --no-binary ctransformers
# Or with Metal GPU acceleration for macOS systems
CT_METAL=1 pip install ctransformers>=0.2.24 --no-binary ctransformers
```
#### Simple example code to load one of these GGUF models
```python
from ctransformers import AutoModelForCausalLM
# Set gpu_layers to the number of layers to offload to GPU. Set to 0 if no GPU acceleration is available on your system.
llm = AutoModelForCausalLM.from_pretrained("TheBloke/vicuna-13B-v1.5-GGUF", model_file="vicuna-13b-v1.5.q4_K_M.gguf", model_type="llama", gpu_layers=50)
print(llm("AI is going to"))
```
## How to use with LangChain
Here's guides on using llama-cpp-python or ctransformers with LangChain:
* [LangChain + llama-cpp-python](https://python.langchain.com/docs/integrations/llms/llamacpp)
* [LangChain + ctransformers](https://python.langchain.com/docs/integrations/providers/ctransformers)
<!-- README_GGUF.md-how-to-run end -->
<!-- footer start -->
<!-- 200823 -->
## Discord
For further support, and discussions on these models and AI in general, join us at:
[TheBloke AI's Discord server](https://discord.gg/theblokeai)
## Thanks, and how to contribute
Thanks to the [chirper.ai](https://chirper.ai) team!
Thanks to Clay from [gpus.llm-utils.org](llm-utils)!
I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training.
If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects.
Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits.
* Patreon: https://patreon.com/TheBlokeAI
* Ko-Fi: https://ko-fi.com/TheBlokeAI
**Special thanks to**: Aemon Algiz.
**Patreon special mentions**: Alicia Loh, Stephen Murray, K, Ajan Kanaga, RoA, Magnesian, Deo Leter, Olakabola, Eugene Pentland, zynix, Deep Realms, Raymond Fosdick, Elijah Stavena, Iucharbius, Erik Bjäreholt, Luis Javier Navarrete Lozano, Nicholas, theTransient, John Detwiler, alfie_i, knownsqashed, Mano Prime, Willem Michiel, Enrico Ros, LangChain4j, OG, Michael Dempsey, Pierre Kircher, Pedro Madruga, James Bentley, Thomas Belote, Luke @flexchar, Leonard Tan, Johann-Peter Hartmann, Illia Dulskyi, Fen Risland, Chadd, S_X, Jeff Scroggin, Ken Nordquist, Sean Connelly, Artur Olbinski, Swaroop Kallakuri, Jack West, Ai Maven, David Ziegler, Russ Johnson, transmissions 11, John Villwock, Alps Aficionado, Clay Pascal, Viktor Bowallius, Subspace Studios, Rainer Wilmers, Trenton Dambrowitz, vamX, Michael Levine, 준교 김, Brandon Frisco, Kalila, Trailburnt, Randy H, Talal Aujan, Nathan Dryer, Vadim, 阿明, ReadyPlayerEmma, Tiffany J. Kim, George Stoitzev, Spencer Kim, Jerry Meng, Gabriel Tamborski, Cory Kujawski, Jeffrey Morgan, Spiking Neurons AB, Edmond Seymore, Alexandros Triantafyllidis, Lone Striker, Cap'n Zoog, Nikolai Manek, danny, ya boyyy, Derek Yates, usrbinkat, Mandus, TL, Nathan LeClaire, subjectnull, Imad Khwaja, webtim, Raven Klaugh, Asp the Wyvern, Gabriel Puliatti, Caitlyn Gatomon, Joseph William Delisle, Jonathan Leane, Luke Pendergrass, SuperWojo, Sebastain Graf, Will Dee, Fred von Graf, Andrey, Dan Guido, Daniel P. Andersen, Nitin Borwankar, Elle, Vitor Caleffi, biorpg, jjj, NimbleBox.ai, Pieter, Matthew Berman, terasurfer, Michael Davis, Alex, Stanislav Ovsiannikov
Thank you to all my generous patrons and donaters!
And thank you again to a16z for their generous grant.
<!-- footer end -->
<!-- original-model-card start -->
# Original model card: lmsys's Vicuna 13B v1.5
# Vicuna Model Card
## Model Details
Vicuna is a chat assistant trained by fine-tuning Llama 2 on user-shared conversations collected from ShareGPT.
- **Developed by:** [LMSYS](https://lmsys.org/)
- **Model type:** An auto-regressive language model based on the transformer architecture
- **License:** Llama 2 Community License Agreement
- **Finetuned from model:** [Llama 2](https://arxiv.org/abs/2307.09288)
### Model Sources
- **Repository:** https://github.com/lm-sys/FastChat
- **Blog:** https://lmsys.org/blog/2023-03-30-vicuna/
- **Paper:** https://arxiv.org/abs/2306.05685
- **Demo:** https://chat.lmsys.org/
## Uses
The primary use of Vicuna is research on large language models and chatbots.
The primary intended users of the model are researchers and hobbyists in natural language processing, machine learning, and artificial intelligence.
## How to Get Started with the Model
- Command line interface: https://github.com/lm-sys/FastChat#vicuna-weights
- APIs (OpenAI API, Huggingface API): https://github.com/lm-sys/FastChat/tree/main#api
## Training Details
Vicuna v1.5 is fine-tuned from Llama 2 with supervised instruction fine-tuning.
The training data is around 125K conversations collected from ShareGPT.com.
See more details in the "Training Details of Vicuna Models" section in the appendix of this [paper](https://arxiv.org/pdf/2306.05685.pdf).
## Evaluation
Vicuna is evaluated with standard benchmarks, human preference, and LLM-as-a-judge. See more details in this [paper](https://arxiv.org/pdf/2306.05685.pdf) and [leaderboard](https://huggingface.co/spaces/lmsys/chatbot-arena-leaderboard).
## Difference between different versions of Vicuna
See [vicuna_weights_version.md](https://github.com/lm-sys/FastChat/blob/main/docs/vicuna_weights_version.md)
<!-- original-model-card end -->
|
Yhyu13/oasst-rlhf-2-llama-30b-7k-steps-hf | Yhyu13 | "2023-08-04T10:09:43Z" | 1,680 | 6 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"license:other",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-05-23T04:16:45Z" | ---
license: other
---
This is the merged hf tr version of llama 30B and OA's rlhf 30B xor weights:
https://huggingface.co/OpenAssistant/oasst-rlhf-2-llama-30b-7k-steps-xor
This the md5 checksum that I get locally, which matchs the original repo suggests
```
deb33dd4ffc3d2baddcce275a00b7c1b ./tokenizer.json
ed59bfee4e87b9193fea5897d610ab24 ./tokenizer_config.json
704373f0c0d62be75e5f7d41d39a7e57 ./special_tokens_map.json
4c5941b4ee12dc0d8e6b5ca3f6819f4d ./pytorch_model-00004-of-00007.bin
13a3641423840eb89f9a86507a90b2bf ./pytorch_model.bin.index.json
d08594778f00abe70b93899628e41246 ./pytorch_model-00007-of-00007.bin
9a4d2468ecf85bf07420b200faefb4af ./config.json
2c92d306969c427275f34b4ebf66f087 ./pytorch_model-00006-of-00007.bin
148bfd184af630a7633b4de2f41bfc49 ./generation_config.json
b6e90377103e9270cbe46b13aed288ec ./pytorch_model-00005-of-00007.bin
27b0dc092f99aa2efaf467b2d8026c3f ./added_tokens.json
ed991042b2a449123824f689bb94b29e ./pytorch_model-00002-of-00007.bin
f11acc069334434d68c45a80ee899fe5 ./pytorch_model-00003-of-00007.bin
9f41bd4d5720d28567b3e7820b4a8023 ./pytorch_model-00001-of-00007.bin
eeec4125e9c7560836b4873b6f8e3025 ./tokenizer.model
``` |
TheBloke/WizardLM-30B-GPTQ | TheBloke | "2023-08-21T10:05:04Z" | 1,680 | 20 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"license:other",
"autotrain_compatible",
"text-generation-inference",
"4-bit",
"gptq",
"region:us"
] | text-generation | "2023-06-06T16:19:35Z" | ---
inference: false
license: other
---
<!-- header start -->
<!-- 200823 -->
<div style="width: auto; margin-left: auto; margin-right: auto">
<img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
</div>
<div style="display: flex; justify-content: space-between; width: 100%;">
<div style="display: flex; flex-direction: column; align-items: flex-start;">
<p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://discord.gg/theblokeai">Chat & support: TheBloke's Discord server</a></p>
</div>
<div style="display: flex; flex-direction: column; align-items: flex-end;">
<p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p>
</div>
</div>
<div style="text-align:center; margin-top: 0em; margin-bottom: 0em"><p style="margin-top: 0.25em; margin-bottom: 0em;">TheBloke's LLM work is generously supported by a grant from <a href="https://a16z.com">andreessen horowitz (a16z)</a></p></div>
<hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
<!-- header end -->
# WizardLM's WizardLM 30B v1.0 GPTQ
These files are GPTQ 4bit model files for [WizardLM's WizardLM 30B v1.0](https://huggingface.co/WizardLM/WizardLM-30B-V1.0).
It is the result of quantising to 4bit using [GPTQ-for-LLaMa](https://github.com/qwopqwop200/GPTQ-for-LLaMa).
## Other repositories available
* [4-bit GPTQ models for GPU inference](https://huggingface.co/TheBloke/WizardLM-30B-GPTQ)
* [4-bit, 5-bit and 8-bit GGML models for CPU(+GPU) inference](https://huggingface.co/TheBloke/WizardLM-30B-GGML)
* [Unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/WizardLM/WizardLM-30B-V1.0)
## Prompt template
```
A chat between a curious user and an artificial intelligence assistant.
The assistant gives helpful, detailed, and polite answers to the user's questions.
USER: prompt goes here
ASSISTANT:
```
## How to easily download and use this model in text-generation-webui
### Downloading the model
1. Click the **Model tab**.
2. Under **Download custom model or LoRA**, enter `TheBloke/WizardLM-30B-GPTQ`.
3. Click **Download**.
4. Wait until it says it's finished downloading.
5. Untick "Autoload model"
6. Click the **Refresh** icon next to **Model** in the top left.
### To use with AutoGPTQ (if installed)
1. In the **Model drop-down**: choose the model you just downloaded, `WizardLM-30B-GPTQ`.
2. Under **GPTQ**, tick **AutoGPTQ**.
3. Click **Save settings for this model** in the top right.
4. Click **Reload the Model** in the top right.
5. Once it says it's loaded, click the **Text Generation tab** and enter a prompt!
### To use with GPTQ-for-LLaMa
1. In the **Model drop-down**: choose the model you just downloaded, `WizardLM-30B-GPTQ`.
2. If you see an error in the bottom right, ignore it - it's temporary.
3. Fill out the `GPTQ parameters` on the right: `Bits = 4`, `Groupsize = -1`, `model_type = Llama`
4. Click **Save settings for this model** in the top right.
5. Click **Reload the Model** in the top right.
6. Once it says it's loaded, click the **Text Generation tab** and enter a prompt!
## Provided files
**wizardlm-30b-GPTQ-4bit--1g.act.order.safetensors**
This will work with all versions of GPTQ-for-LLaMa, and with AutoGPTQ.
It was created without group_size to lower VRAM requirements, and with --act-order (desc_act) to boost inference accuracy as much as possible.
* `wizardlm-30b-GPTQ-4bit--1g.act.order.safetensors`
* Works with all versions of GPTQ-for-LLaMa code, both Triton and CUDA branches
* Works with AutoGPTQ
* Works with text-generation-webui one-click-installers
* Parameters: Groupsize = -1. Act Order / desc_act = True.
<!-- footer start -->
<!-- 200823 -->
## Discord
For further support, and discussions on these models and AI in general, join us at:
[TheBloke AI's Discord server](https://discord.gg/theblokeai)
## Thanks, and how to contribute.
Thanks to the [chirper.ai](https://chirper.ai) team!
I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training.
If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects.
Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits.
* Patreon: https://patreon.com/TheBlokeAI
* Ko-Fi: https://ko-fi.com/TheBlokeAI
**Special thanks to**: Aemon Algiz.
**Patreon special mentions**: Sam, theTransient, Jonathan Leane, Steven Wood, webtim, Johann-Peter Hartmann, Geoffrey Montalvo, Gabriel Tamborski, Willem Michiel, John Villwock, Derek Yates, Mesiah Bishop, Eugene Pentland, Pieter, Chadd, Stephen Murray, Daniel P. Andersen, terasurfer, Brandon Frisco, Thomas Belote, Sid, Nathan LeClaire, Magnesian, Alps Aficionado, Stanislav Ovsiannikov, Alex, Joseph William Delisle, Nikolai Manek, Michael Davis, Junyu Yang, K, J, Spencer Kim, Stefan Sabev, Olusegun Samson, transmissions 11, Michael Levine, Cory Kujawski, Rainer Wilmers, zynix, Kalila, Luke @flexchar, Ajan Kanaga, Mandus, vamX, Ai Maven, Mano Prime, Matthew Berman, subjectnull, Vitor Caleffi, Clay Pascal, biorpg, alfie_i, 阿明, Jeffrey Morgan, ya boyyy, Raymond Fosdick, knownsqashed, Olakabola, Leonard Tan, ReadyPlayerEmma, Enrico Ros, Dave, Talal Aujan, Illia Dulskyi, Sean Connelly, senxiiz, Artur Olbinski, Elle, Raven Klaugh, Fen Risland, Deep Realms, Imad Khwaja, Fred von Graf, Will Dee, usrbinkat, SuperWojo, Alexandros Triantafyllidis, Swaroop Kallakuri, Dan Guido, John Detwiler, Pedro Madruga, Iucharbius, Viktor Bowallius, Asp the Wyvern, Edmond Seymore, Trenton Dambrowitz, Space Cruiser, Spiking Neurons AB, Pyrater, LangChain4j, Tony Hughes, Kacper Wikieł, Rishabh Srivastava, David Ziegler, Luke Pendergrass, Andrey, Gabriel Puliatti, Lone Striker, Sebastain Graf, Pierre Kircher, Randy H, NimbleBox.ai, Vadim, danny, Deo Leter
Thank you to all my generous patrons and donaters!
And thank you again to a16z for their generous grant.
<!-- footer end -->
# Original model card: WizardLM's WizardLM 30B v1.0
This is WizardLM-30B V1.0 delta weight.
Project Repo: https://github.com/nlpxucan/WizardLM
NOTE: The **WizardLM-30B-V1.0** & **WizardLM-13B-V1.0** use different prompt with **Wizard-7B-V1.0** at the beginning of the conversation:
1. For **WizardLM-30B-V1.0** & **WizardLM-13B-V1.0** , the Prompt should be as following:
"A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions. USER: hello, who are you? ASSISTANT:"
2. For **WizardLM-7B-V1.0** , the Prompt should be as following:
"{instruction}\n\n### Response:"
|
TaylorAI/Flash-Llama-3B | TaylorAI | "2023-08-29T23:44:33Z" | 1,680 | 2 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"custom_code",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-08-13T04:49:51Z" | ---
license: mit
---
|
Undi95/MLewd-Chat-v2-13B | Undi95 | "2023-11-17T21:08:00Z" | 1,680 | 18 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"not-for-all-audiences",
"nsfw",
"license:cc-by-nc-4.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-09-26T17:37:06Z" | ---
license: cc-by-nc-4.0
tags:
- not-for-all-audiences
- nsfw
---
THIS MODEL IS MADE FOR LEWD
SEXUAL, CRUDE AND KINKY CONTENT IN OUTPUT CAN AND WILL HAPPEN. YOU'RE WARNED
This is an attempt to make an uncensored Llama2-chat that can RP.
Added the "magic touch" of MythoMax/Huginn/You call it.
In addition, [LimaRP v3](https://huggingface.co/lemonilia/LimaRP-Llama2-13B-v3-EXPERIMENT) was used, is it recommanded to read the documentation.
This was requested.
<!-- description start -->
## Description
This repo contains fp16 files of MLewd-Chat-v2-13B, very hot and lewd model based on Llama2-chat.
<!-- description end -->
<!-- description start -->
## Models and loras used
- Undi95/MLewd-L2-13B-Part3 (checkpoint of MLewd without LORA)
- posicube/Llama2-chat-AYT-13B
- zattio770/120-Days-of-LORA-v2-13B
- royallab/Pygmalion-2-13b-SuperCOT
- Undi95/MMSoul-13b-lora
- The-Face-Of-Goonery/Huginn-13b-FP16
- lemonilia/LimaRP-Llama2-13B-v3-EXPERIMENT
<!-- description end -->
<!-- prompt-template start -->
## Prompt template: Alpaca
```
Below is an instruction that describes a task. Write a response that appropriately completes the request.
### Instruction:
{prompt}
### Response:
```
## LimaRP v3 usage and suggested settings
You can follow these instruction format settings in SillyTavern. Replace tiny with your desired response length:
Special thanks to Sushi and Shena ♥ | I love U Kubernetes.
If you want to support me, you can [here](https://ko-fi.com/undiai).
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_Undi95__MLewd-Chat-v2-13B)
| Metric | Value |
|-----------------------|---------------------------|
| Avg. | 52.72 |
| ARC (25-shot) | 61.86 |
| HellaSwag (10-shot) | 83.81 |
| MMLU (5-shot) | 57.0 |
| TruthfulQA (0-shot) | 54.51 |
| Winogrande (5-shot) | 75.77 |
| GSM8K (5-shot) | 10.46 |
| DROP (3-shot) | 25.63 |
|
moreh/MoMo-72B-LoRA-V1.4 | moreh | "2024-01-22T00:05:53Z" | 1,680 | 87 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"en",
"arxiv:2106.09685",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-01-02T09:10:30Z" | ---
license: mit
language:
- en
---
# **Introduction**
MoMo-72B is trained via Supervised Fine-Tuning (SFT) using [LoRA](https://arxiv.org/abs/2106.09685), with the QWEN-72B model as its base-model.
Note that we did not exploit any form of weight merge.
For leaderboard submission, the trained weight is realigned for compatibility with llama.
MoMo-72B is trained using **[Moreh](https://moreh.io/)**'s [MoAI platform](https://moreh.io/product), which simplifies the training of large-scale models, and AMD's MI250 GPU.
## Details
### Used Librarys
- torch
- peft
### Used Datasets
- Open-Orca/SlimOrca
- No other dataset was used
- No benchmark test set or the training set are used
- [data contamination check](https://github.com/swj0419/detect-pretrain-code-contamination) result
| Model | ARC | MMLU | TruthfulQA | GSM8K |
|------------------------------|-------|-------|-------|-------|
| **V1.4(result < 0.1, %)**| TBU |0.73 | 0.71 | TBU |
### Used Environments
- AMD MI250 & MoAI platform
- Please visit https://moreh.io/product for more information about MoAI platform
- Or, contact us directly [[email protected]](mailto:[email protected])
## How to use
```python
# pip install transformers==4.35.2
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained("moreh/MoMo-72B-LoRA-V1.4")
model = AutoModelForCausalLM.from_pretrained(
"moreh/MoMo-72B-LoRA-V1.4"
)
``` |
alnrg2arg/test_wanda_240109 | alnrg2arg | "2024-01-24T14:21:22Z" | 1,680 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"conversational",
"license:cc-by-nc-4.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-01-09T02:21:35Z" | ---
license: cc-by-nc-4.0
---
This is the pruned version of alnrg2arg/test
The sparcity of the model is 0.49
The two base models were
- https://huggingface.co/jeonsworld/CarbonVillain-en-10.7B-v2
- https://huggingface.co/kyujinpy/Sakura-SOLAR-Instruct-DPO-v2 |
bartowski/Yi-1.5-34B-Chat-16K-GGUF | bartowski | "2024-05-20T22:57:42Z" | 1,680 | 6 | null | [
"gguf",
"text-generation",
"license:apache-2.0",
"region:us"
] | text-generation | "2024-05-20T21:08:32Z" | ---
license: apache-2.0
quantized_by: bartowski
pipeline_tag: text-generation
---
## Llamacpp imatrix Quantizations of Yi-1.5-34B-Chat-16K
Using <a href="https://github.com/ggerganov/llama.cpp/">llama.cpp</a> release <a href="https://github.com/ggerganov/llama.cpp/releases/tag/b2940">b2940</a> for quantization.
Original model: https://huggingface.co/01-ai/Yi-1.5-34B-Chat-16K
All quants made using imatrix option with dataset from [here](https://gist.github.com/bartowski1182/b6ac44691e994344625687afe3263b3a)
## Prompt format
```
{system_prompt}<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant
<|im_end|>
```
## Download a file (not the whole branch) from below:
| Filename | Quant type | File Size | Description |
| -------- | ---------- | --------- | ----------- |
| [Yi-1.5-34B-Chat-16K-Q8_0.gguf](https://huggingface.co/bartowski/Yi-1.5-34B-Chat-16K-GGUF/blob/main/Yi-1.5-34B-Chat-16K-Q8_0.gguf) | Q8_0 | 36.54GB | Extremely high quality, generally unneeded but max available quant. |
| [Yi-1.5-34B-Chat-16K-Q6_K.gguf](https://huggingface.co/bartowski/Yi-1.5-34B-Chat-16K-GGUF/blob/main/Yi-1.5-34B-Chat-16K-Q6_K.gguf) | Q6_K | 28.21GB | Very high quality, near perfect, *recommended*. |
| [Yi-1.5-34B-Chat-16K-Q5_K_M.gguf](https://huggingface.co/bartowski/Yi-1.5-34B-Chat-16K-GGUF/blob/main/Yi-1.5-34B-Chat-16K-Q5_K_M.gguf) | Q5_K_M | 24.32GB | High quality, *recommended*. |
| [Yi-1.5-34B-Chat-16K-Q5_K_S.gguf](https://huggingface.co/bartowski/Yi-1.5-34B-Chat-16K-GGUF/blob/main/Yi-1.5-34B-Chat-16K-Q5_K_S.gguf) | Q5_K_S | 23.70GB | High quality, *recommended*. |
| [Yi-1.5-34B-Chat-16K-Q4_K_M.gguf](https://huggingface.co/bartowski/Yi-1.5-34B-Chat-16K-GGUF/blob/main/Yi-1.5-34B-Chat-16K-Q4_K_M.gguf) | Q4_K_M | 20.65GB | Good quality, uses about 4.83 bits per weight, *recommended*. |
| [Yi-1.5-34B-Chat-16K-Q4_K_S.gguf](https://huggingface.co/bartowski/Yi-1.5-34B-Chat-16K-GGUF/blob/main/Yi-1.5-34B-Chat-16K-Q4_K_S.gguf) | Q4_K_S | 19.59GB | Slightly lower quality with more space savings, *recommended*. |
| [Yi-1.5-34B-Chat-16K-IQ4_NL.gguf](https://huggingface.co/bartowski/Yi-1.5-34B-Chat-16K-GGUF/blob/main/Yi-1.5-34B-Chat-16K-IQ4_NL.gguf) | IQ4_NL | 19.52GB | Decent quality, slightly smaller than Q4_K_S with similar performance *recommended*. |
| [Yi-1.5-34B-Chat-16K-IQ4_XS.gguf](https://huggingface.co/bartowski/Yi-1.5-34B-Chat-16K-GGUF/blob/main/Yi-1.5-34B-Chat-16K-IQ4_XS.gguf) | IQ4_XS | 18.47GB | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. |
| [Yi-1.5-34B-Chat-16K-Q3_K_L.gguf](https://huggingface.co/bartowski/Yi-1.5-34B-Chat-16K-GGUF/blob/main/Yi-1.5-34B-Chat-16K-Q3_K_L.gguf) | Q3_K_L | 18.13GB | Lower quality but usable, good for low RAM availability. |
| [Yi-1.5-34B-Chat-16K-Q3_K_M.gguf](https://huggingface.co/bartowski/Yi-1.5-34B-Chat-16K-GGUF/blob/main/Yi-1.5-34B-Chat-16K-Q3_K_M.gguf) | Q3_K_M | 16.65GB | Even lower quality. |
| [Yi-1.5-34B-Chat-16K-IQ3_M.gguf](https://huggingface.co/bartowski/Yi-1.5-34B-Chat-16K-GGUF/blob/main/Yi-1.5-34B-Chat-16K-IQ3_M.gguf) | IQ3_M | 15.56GB | Medium-low quality, new method with decent performance comparable to Q3_K_M. |
| [Yi-1.5-34B-Chat-16K-IQ3_S.gguf](https://huggingface.co/bartowski/Yi-1.5-34B-Chat-16K-GGUF/blob/main/Yi-1.5-34B-Chat-16K-IQ3_S.gguf) | IQ3_S | 15.01GB | Lower quality, new method with decent performance, recommended over Q3_K_S quant, same size with better performance. |
| [Yi-1.5-34B-Chat-16K-Q3_K_S.gguf](https://huggingface.co/bartowski/Yi-1.5-34B-Chat-16K-GGUF/blob/main/Yi-1.5-34B-Chat-16K-Q3_K_S.gguf) | Q3_K_S | 14.96GB | Low quality, not recommended. |
| [Yi-1.5-34B-Chat-16K-IQ3_XS.gguf](https://huggingface.co/bartowski/Yi-1.5-34B-Chat-16K-GGUF/blob/main/Yi-1.5-34B-Chat-16K-IQ3_XS.gguf) | IQ3_XS | 14.23GB | Lower quality, new method with decent performance, slightly better than Q3_K_S. |
| [Yi-1.5-34B-Chat-16K-IQ3_XXS.gguf](https://huggingface.co/bartowski/Yi-1.5-34B-Chat-16K-GGUF/blob/main/Yi-1.5-34B-Chat-16K-IQ3_XXS.gguf) | IQ3_XXS | 13.33GB | Lower quality, new method with decent performance, comparable to Q3 quants. |
| [Yi-1.5-34B-Chat-16K-Q2_K.gguf](https://huggingface.co/bartowski/Yi-1.5-34B-Chat-16K-GGUF/blob/main/Yi-1.5-34B-Chat-16K-Q2_K.gguf) | Q2_K | 12.82GB | Very low quality but surprisingly usable. |
| [Yi-1.5-34B-Chat-16K-IQ2_M.gguf](https://huggingface.co/bartowski/Yi-1.5-34B-Chat-16K-GGUF/blob/main/Yi-1.5-34B-Chat-16K-IQ2_M.gguf) | IQ2_M | 11.79GB | Very low quality, uses SOTA techniques to also be surprisingly usable. |
| [Yi-1.5-34B-Chat-16K-IQ2_S.gguf](https://huggingface.co/bartowski/Yi-1.5-34B-Chat-16K-GGUF/blob/main/Yi-1.5-34B-Chat-16K-IQ2_S.gguf) | IQ2_S | 10.89GB | Very low quality, uses SOTA techniques to be usable. |
| [Yi-1.5-34B-Chat-16K-IQ2_XS.gguf](https://huggingface.co/bartowski/Yi-1.5-34B-Chat-16K-GGUF/blob/main/Yi-1.5-34B-Chat-16K-IQ2_XS.gguf) | IQ2_XS | 10.30GB | Very low quality, uses SOTA techniques to be usable. |
| [Yi-1.5-34B-Chat-16K-IQ2_XXS.gguf](https://huggingface.co/bartowski/Yi-1.5-34B-Chat-16K-GGUF/blob/main/Yi-1.5-34B-Chat-16K-IQ2_XXS.gguf) | IQ2_XXS | 9.30GB | Lower quality, uses SOTA techniques to be usable. |
| [Yi-1.5-34B-Chat-16K-IQ1_M.gguf](https://huggingface.co/bartowski/Yi-1.5-34B-Chat-16K-GGUF/blob/main/Yi-1.5-34B-Chat-16K-IQ1_M.gguf) | IQ1_M | 8.17GB | Extremely low quality, *not* recommended. |
| [Yi-1.5-34B-Chat-16K-IQ1_S.gguf](https://huggingface.co/bartowski/Yi-1.5-34B-Chat-16K-GGUF/blob/main/Yi-1.5-34B-Chat-16K-IQ1_S.gguf) | IQ1_S | 7.49GB | Extremely low quality, *not* recommended. |
## Downloading using huggingface-cli
First, make sure you have hugginface-cli installed:
```
pip install -U "huggingface_hub[cli]"
```
Then, you can target the specific file you want:
```
huggingface-cli download bartowski/Yi-1.5-34B-Chat-16K-GGUF --include "Yi-1.5-34B-Chat-16K-Q4_K_M.gguf" --local-dir ./ --local-dir-use-symlinks False
```
If the model is bigger than 50GB, it will have been split into multiple files. In order to download them all to a local folder, run:
```
huggingface-cli download bartowski/Yi-1.5-34B-Chat-16K-GGUF --include "Yi-1.5-34B-Chat-16K-Q8_0.gguf/*" --local-dir Yi-1.5-34B-Chat-16K-Q8_0 --local-dir-use-symlinks False
```
You can either specify a new local-dir (Yi-1.5-34B-Chat-16K-Q8_0) or download them all in place (./)
## Which file should I choose?
A great write up with charts showing various performances is provided by Artefact2 [here](https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9)
The first thing to figure out is how big a model you can run. To do this, you'll need to figure out how much RAM and/or VRAM you have.
If you want your model running as FAST as possible, you'll want to fit the whole thing on your GPU's VRAM. Aim for a quant with a file size 1-2GB smaller than your GPU's total VRAM.
If you want the absolute maximum quality, add both your system RAM and your GPU's VRAM together, then similarly grab a quant with a file size 1-2GB Smaller than that total.
Next, you'll need to decide if you want to use an 'I-quant' or a 'K-quant'.
If you don't want to think too much, grab one of the K-quants. These are in format 'QX_K_X', like Q5_K_M.
If you want to get more into the weeds, you can check out this extremely useful feature chart:
[llama.cpp feature matrix](https://github.com/ggerganov/llama.cpp/wiki/Feature-matrix)
But basically, if you're aiming for below Q4, and you're running cuBLAS (Nvidia) or rocBLAS (AMD), you should look towards the I-quants. These are in format IQX_X, like IQ3_M. These are newer and offer better performance for their size.
These I-quants can also be used on CPU and Apple Metal, but will be slower than their K-quant equivalent, so speed vs performance is a tradeoff you'll have to decide.
The I-quants are *not* compatible with Vulcan, which is also AMD, so if you have an AMD card double check if you're using the rocBLAS build or the Vulcan build. At the time of writing this, LM Studio has a preview with ROCm support, and other inference engines have specific builds for ROCm.
Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski
|
MayaPH/GodziLLa-30B | MayaPH | "2023-08-02T17:29:41Z" | 1,679 | 10 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"merge",
"mix",
"cot",
"arxiv:2009.03300",
"arxiv:1803.05457",
"arxiv:1905.07830",
"arxiv:2109.07958",
"license:cc-by-nc-4.0",
"autotrain_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-07-08T20:11:22Z" | ---
pipeline_tag: text-generation
license: cc-by-nc-4.0
inference: false
tags:
- merge
- mix
- cot
---
<img src="https://drive.google.com/uc?export=view&id=16DzZwhqybQvT1wQVp-6qXHI9HhKft6CR" width="50%" alt="GodziLLa-30B">
Released July 9, 2023
## Model Description
GodziLLa-30B is an experimental combination of various proprietary Maya LoRAs with CalderaAI's [Lazarus-30B](https://huggingface.co/CalderaAI/30B-Lazarus). This composite model is not meant for any other use outside of research on competing LoRA adapter behavior. More specifically, since this is inherently a LlaMA model, **commercial use is prohibited**. This model's primary purpose is to stress test the limitations of composite LLMs and observe its performance with respect to other LLMs available on the [Open LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard).
## Open LLM Leaderboard Metrics
| Metric | Value |
|-----------------------|-------|
| MMLU (5-shot) | 54.2 |
| ARC (25-shot) | 61.5 |
| HellaSwag (10-shot) | 82.1 |
| TruthfulQA (0-shot) | 55.9 |
| Average | 63.4 |
According to the leaderboard description, here are the benchmarks used for the evaluation:
- [MMLU](https://arxiv.org/abs/2009.03300) (5-shot) - a test to measure a text model’s multitask accuracy. The test covers 57 tasks including elementary mathematics, US history, computer science, law, and more.
- [AI2 Reasoning Challenge](https://arxiv.org/abs/1803.05457) -ARC- (25-shot) - a set of grade-school science questions.
- [HellaSwag](https://arxiv.org/abs/1905.07830) (10-shot) - a test of commonsense inference, which is easy for humans (~95%) but challenging for SOTA models.
- [TruthfulQA](https://arxiv.org/abs/2109.07958) (0-shot) - a test to measure a model’s propensity to reproduce falsehoods commonly found online.
## Leaderboard Highlights (as of July 22, 2023)
- GodziLLa-30B is on par with [Falcon-40B-instruct](https://huggingface.co/tiiuae/falcon-40b-instruct) (June 2023's Rank #1).
- GodziLLa-30B outperforms Meta AI's LLaMA [30B](https://ai.meta.com/blog/large-language-model-llama-meta-ai/) model.
- GodziLLa-30B ranks 4th worldwide, for open-source LLMs, on the [TruthfulQA](https://arxiv.org/abs/2109.07958) benchmark.
- GodziLLa-30B beats [GPT-3.5 175B](https://platform.openai.com/docs/models/gpt-3-5) (text-davinci-003) on the [TruthfulQA](https://arxiv.org/abs/2109.07958) benchmark and performs closely (< 4%) on the [HellaSwag](https://arxiv.org/abs/1905.07830) benchmark.*
*Based on a [leaderboard clone](https://huggingface.co/spaces/gsaivinay/open_llm_leaderboard) with GPT-3.5 and GPT-4 included.
## Recommended Prompt Format
Alpaca's instruction is the recommended prompt format, but Vicuna's instruction format may also work.
## Usage
To use GodziLLa-30B, you are required to provide attribution in accordance with the Creative Commons Attribution-NonCommercial 4.0 International (CC BY-NC 4.0) license. Please include the following attribution notice when utilizing GodziLLa-30B in your work:
```python
# This code uses GodziLLa-30B, a language model developed by Maya Philippines.
# The model is licensed under the Creative Commons Attribution-NonCommercial 4.0 International (CC BY-NC 4.0) license.
# For more information, visit: https://creativecommons.org/licenses/by-nc/4.0/
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("MayaPH/GodziLLa-30B")
model = AutoModelForCausalLM.from_pretrained("MayaPH/GodziLLa-30B")
```
Please ensure that you include the relevant attribution notice in your code or any other form of usage and restrict your usage to non-commercial use to comply with the license terms.
## Ethical Considerations
When using GodziLLa-30B, it is important to consider the following ethical considerations:
1. **Privacy and Security:** Avoid sharing sensitive personal information while interacting with the model. The model does not have privacy safeguards, so exercise caution when discussing personal or confidential matters.
2. **Fairness and Bias:** The model's responses may reflect biases present in the training data. Be aware of potential biases and make an effort to evaluate responses critically and fairly.
3. **Transparency:** The model operates as a predictive text generator based on patterns learned from the training data. The model's inner workings and the specific training data used are proprietary and not publicly available.
4. **User Responsibility:** Users should take responsibility for their own decisions and not solely rely on the information provided by the model. Consult with the appropriate professionals or reliable sources for specific advice or recommendations.
5. **NSFW Content:** The model is a merge of multiple model checkpoints and LoRA adapters. It is highly likely that the resulting model contains uncensored content that may include, but is not limited to, violence, gore, explicit language, and sexual content. If you plan to further refine this model for safe/aligned usage, you are highly encouraged to implement guardrails along with it.
## Further Information
For additional information or inquiries about GodziLLa-30B, please contact the Maya Philippines iOps Team via [email protected].
## Disclaimer
GodziLLa-30B is an AI language model from Maya Philippines. It is provided "as is" without warranty of any kind, express or implied. The model developers and Maya Philippines shall not be liable for any direct or indirect damages arising from the use of this model.
## Acknowledgments
The development of GodziLLa-30B was made possible by Maya Philippines and the curation of the various proprietary datasets and creation of the different proprietary LoRA adapters. |
ahxt/llama2_xs_460M_experimental | ahxt | "2023-11-17T21:26:46Z" | 1,679 | 12 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"llama2",
"llama-2",
"llama2 architecture",
"en",
"dataset:Redpajama",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-07-26T01:50:25Z" | ---
language:
- en
tags:
- llama2
- llama-2
- llama
- llama2 architecture
datasets:
- Redpajama
metrics:
- MMLU
---
# LLaMa Lite: Reduced-Scale, Experimental Versions of LLaMA and LLaMa 2
In this series of repos, we present an open-source reproduction of Meta AI's [LLaMA](https://ai.meta.com/blog/large-language-model-llama-meta-ai/) and [LLaMa 2](https://ai.meta.com/llama/) large language models. However, with significantly reduced model sizes, the experimental version of [llama1_s](https://huggingface.co/ahxt/llama1_s_1.8B_experimental) has 1.8B parameters, and the experimental version of [llama2_xs](https://huggingface.co/ahxt/llama2_xs_460M_experimental) has 460M parameters. ('s' stands for small, while 'xs' denotes extra small).
## Dataset and Tokenization
We train our models on part of [RedPajama](https://www.together.xyz/blog/redpajama) dataset. We use the [GPT2Tokenizer](https://huggingface.co/docs/transformers/v4.31.0/en/model_doc/gpt2#transformers.GPT2Tokenizer) to tokenize the text.
### Using with HuggingFace Transformers
The experimental checkpoints can be directly loaded by [Transformers](https://huggingface.co/transformers/) library. The following code snippet shows how to load the our experimental model and generate text with it.
```python
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
# model_path = 'ahxt/llama2_xs_460M_experimental'
model_path = 'ahxt/llama1_s_1.8B_experimental'
model = AutoModelForCausalLM.from_pretrained(model_path)
tokenizer = AutoTokenizer.from_pretrained(model_path)
model.eval()
prompt = 'Q: What is the largest bird?\nA:'
input_ids = tokenizer(prompt, return_tensors="pt").input_ids
tokens = model.generate(input_ids, max_length=20)
print( tokenizer.decode(tokens[0].tolist(), skip_special_tokens=True) )
# Q: What is the largest bird?\nA: The largest bird is the bald eagle.
```
## Evaluation
We evaluate our models on the MMLU task
markdown table
| Models | #parameters |zero-shot | 5-shot |
| --- | --- | --- | --- |
| llama | 7B | 28.46 | 35.05 |
| openllama | 3B | 24.90 | 26.71 |
|TinyLlama-1.1B-step-50K-105b | 1.1B | 19.00 | 26.53 |
| llama2_xs_460M | 0.46B | 21.13 | 26.39 |
## Contact
This experimental version is developed by:
[Xiaotian Han](https://ahxt.github.io/) from Texas A&M University. And these experimental verisons are for research only.
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_ahxt__llama2_xs_460M_experimental)
| Metric | Value |
|-----------------------|---------------------------|
| Avg. | 26.65 |
| ARC (25-shot) | 24.91 |
| HellaSwag (10-shot) | 38.47 |
| MMLU (5-shot) | 26.17 |
| TruthfulQA (0-shot) | 41.59 |
| Winogrande (5-shot) | 49.88 |
| GSM8K (5-shot) | 0.0 |
| DROP (3-shot) | 5.51 |
|
Devio/test-3b | Devio | "2023-09-02T15:55:18Z" | 1,679 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-09-02T15:46:08Z" | Entry not found |
TheBloke/Mixtral-8x7B-MoE-RP-Story-GGUF | TheBloke | "2023-12-15T17:33:45Z" | 1,679 | 41 | transformers | [
"transformers",
"gguf",
"mixtral",
"not-for-all-audiences",
"nsfw",
"base_model:Undi95/Mixtral-8x7B-MoE-RP-Story",
"license:cc-by-nc-4.0",
"text-generation-inference",
"region:us"
] | null | "2023-12-14T21:47:12Z" | ---
base_model: Undi95/Mixtral-8x7B-MoE-RP-Story
inference: false
license: cc-by-nc-4.0
model_creator: Undi
model_name: Mixtral 8X7B MoE RP Story
model_type: mixtral
prompt_template: '{prompt}
'
quantized_by: TheBloke
tags:
- not-for-all-audiences
- nsfw
---
<!-- markdownlint-disable MD041 -->
<!-- header start -->
<!-- 200823 -->
<div style="width: auto; margin-left: auto; margin-right: auto">
<img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
</div>
<div style="display: flex; justify-content: space-between; width: 100%;">
<div style="display: flex; flex-direction: column; align-items: flex-start;">
<p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://discord.gg/theblokeai">Chat & support: TheBloke's Discord server</a></p>
</div>
<div style="display: flex; flex-direction: column; align-items: flex-end;">
<p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p>
</div>
</div>
<div style="text-align:center; margin-top: 0em; margin-bottom: 0em"><p style="margin-top: 0.25em; margin-bottom: 0em;">TheBloke's LLM work is generously supported by a grant from <a href="https://a16z.com">andreessen horowitz (a16z)</a></p></div>
<hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
<!-- header end -->
# Mixtral 8X7B MoE RP Story - GGUF
- Model creator: [Undi](https://huggingface.co/Undi95)
- Original model: [Mixtral 8X7B MoE RP Story](https://huggingface.co/Undi95/Mixtral-8x7B-MoE-RP-Story)
<!-- description start -->
## Description
This repo contains GGUF format model files for [Undi's Mixtral 8X7B MoE RP Story](https://huggingface.co/Undi95/Mixtral-8x7B-MoE-RP-Story).
<!-- description end -->
<!-- README_GGUF.md-about-gguf start -->
### About GGUF
GGUF is a new format introduced by the llama.cpp team on August 21st 2023. It is a replacement for GGML, which is no longer supported by llama.cpp.
### Mixtral GGUF
Support for Mixtral was merged into Llama.cpp on December 13th.
These Mixtral GGUFs are known to work in:
* llama.cpp as of December 13th
* KoboldCpp 1.52 as later
* LM Studio 0.2.9 and later
* llama-cpp-python 0.2.23 and later
Other clients/libraries, not listed above, may not yet work.
<!-- README_GGUF.md-about-gguf end -->
<!-- repositories-available start -->
## Repositories available
* [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/Mixtral-8x7B-MoE-RP-Story-GPTQ)
* [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/Mixtral-8x7B-MoE-RP-Story-GGUF)
* [Undi's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/Undi95/Mixtral-8x7B-MoE-RP-Story)
<!-- repositories-available end -->
<!-- prompt-template start -->
## Prompt template: Unknown
```
{prompt}
```
<!-- prompt-template end -->
<!-- compatibility_gguf start -->
## Compatibility
These Mixtral GGUFs are compatible with llama.cpp from December 13th onwards. Other clients/libraries may not work yet.
## Explanation of quantisation methods
<details>
<summary>Click to see details</summary>
The new methods available are:
* GGML_TYPE_Q2_K - "type-1" 2-bit quantization in super-blocks containing 16 blocks, each block having 16 weight. Block scales and mins are quantized with 4 bits. This ends up effectively using 2.5625 bits per weight (bpw)
* GGML_TYPE_Q3_K - "type-0" 3-bit quantization in super-blocks containing 16 blocks, each block having 16 weights. Scales are quantized with 6 bits. This end up using 3.4375 bpw.
* GGML_TYPE_Q4_K - "type-1" 4-bit quantization in super-blocks containing 8 blocks, each block having 32 weights. Scales and mins are quantized with 6 bits. This ends up using 4.5 bpw.
* GGML_TYPE_Q5_K - "type-1" 5-bit quantization. Same super-block structure as GGML_TYPE_Q4_K resulting in 5.5 bpw
* GGML_TYPE_Q6_K - "type-0" 6-bit quantization. Super-blocks with 16 blocks, each block having 16 weights. Scales are quantized with 8 bits. This ends up using 6.5625 bpw
Refer to the Provided Files table below to see what files use which methods, and how.
</details>
<!-- compatibility_gguf end -->
<!-- README_GGUF.md-provided-files start -->
## Provided files
| Name | Quant method | Bits | Size | Max RAM required | Use case |
| ---- | ---- | ---- | ---- | ---- | ----- |
| [mixtral-8x7b-moe-rp-story.Q2_K.gguf](https://huggingface.co/TheBloke/Mixtral-8x7B-MoE-RP-Story-GGUF/blob/main/mixtral-8x7b-moe-rp-story.Q2_K.gguf) | Q2_K | 2 | 15.64 GB| 18.14 GB | smallest, significant quality loss - not recommended for most purposes |
| [mixtral-8x7b-moe-rp-story.Q3_K_M.gguf](https://huggingface.co/TheBloke/Mixtral-8x7B-MoE-RP-Story-GGUF/blob/main/mixtral-8x7b-moe-rp-story.Q3_K_M.gguf) | Q3_K_M | 3 | 20.36 GB| 22.86 GB | very small, high quality loss |
| [mixtral-8x7b-moe-rp-story.Q4_0.gguf](https://huggingface.co/TheBloke/Mixtral-8x7B-MoE-RP-Story-GGUF/blob/main/mixtral-8x7b-moe-rp-story.Q4_0.gguf) | Q4_0 | 4 | 26.44 GB| 28.94 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| [mixtral-8x7b-moe-rp-story.Q4_K_M.gguf](https://huggingface.co/TheBloke/Mixtral-8x7B-MoE-RP-Story-GGUF/blob/main/mixtral-8x7b-moe-rp-story.Q4_K_M.gguf) | Q4_K_M | 4 | 26.44 GB| 28.94 GB | medium, balanced quality - recommended |
| [mixtral-8x7b-moe-rp-story.Q5_0.gguf](https://huggingface.co/TheBloke/Mixtral-8x7B-MoE-RP-Story-GGUF/blob/main/mixtral-8x7b-moe-rp-story.Q5_0.gguf) | Q5_0 | 5 | 32.23 GB| 34.73 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| [mixtral-8x7b-moe-rp-story.Q5_K_M.gguf](https://huggingface.co/TheBloke/Mixtral-8x7B-MoE-RP-Story-GGUF/blob/main/mixtral-8x7b-moe-rp-story.Q5_K_M.gguf) | Q5_K_M | 5 | 32.23 GB| 34.73 GB | large, very low quality loss - recommended |
| [mixtral-8x7b-moe-rp-story.Q6_K.gguf](https://huggingface.co/TheBloke/Mixtral-8x7B-MoE-RP-Story-GGUF/blob/main/mixtral-8x7b-moe-rp-story.Q6_K.gguf) | Q6_K | 6 | 38.38 GB| 40.88 GB | very large, extremely low quality loss |
| [mixtral-8x7b-moe-rp-story.Q8_0.gguf](https://huggingface.co/TheBloke/Mixtral-8x7B-MoE-RP-Story-GGUF/blob/main/mixtral-8x7b-moe-rp-story.Q8_0.gguf) | Q8_0 | 8 | 49.62 GB| 52.12 GB | very large, extremely low quality loss - not recommended |
**Note**: the above RAM figures assume no GPU offloading. If layers are offloaded to the GPU, this will reduce RAM usage and use VRAM instead.
<!-- README_GGUF.md-provided-files end -->
<!-- README_GGUF.md-how-to-download start -->
## How to download GGUF files
**Note for manual downloaders:** You almost never want to clone the entire repo! Multiple different quantisation formats are provided, and most users only want to pick and download a single file.
The following clients/libraries will automatically download models for you, providing a list of available models to choose from:
* LM Studio
* LoLLMS Web UI
* Faraday.dev
### In `text-generation-webui`
Under Download Model, you can enter the model repo: TheBloke/Mixtral-8x7B-MoE-RP-Story-GGUF and below it, a specific filename to download, such as: mixtral-8x7b-moe-rp-story.Q4_K_M.gguf.
Then click Download.
### On the command line, including multiple files at once
I recommend using the `huggingface-hub` Python library:
```shell
pip3 install huggingface-hub
```
Then you can download any individual model file to the current directory, at high speed, with a command like this:
```shell
huggingface-cli download TheBloke/Mixtral-8x7B-MoE-RP-Story-GGUF mixtral-8x7b-moe-rp-story.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
```
<details>
<summary>More advanced huggingface-cli download usage (click to read)</summary>
You can also download multiple files at once with a pattern:
```shell
huggingface-cli download TheBloke/Mixtral-8x7B-MoE-RP-Story-GGUF --local-dir . --local-dir-use-symlinks False --include='*Q4_K*gguf'
```
For more documentation on downloading with `huggingface-cli`, please see: [HF -> Hub Python Library -> Download files -> Download from the CLI](https://huggingface.co/docs/huggingface_hub/guides/download#download-from-the-cli).
To accelerate downloads on fast connections (1Gbit/s or higher), install `hf_transfer`:
```shell
pip3 install hf_transfer
```
And set environment variable `HF_HUB_ENABLE_HF_TRANSFER` to `1`:
```shell
HF_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download TheBloke/Mixtral-8x7B-MoE-RP-Story-GGUF mixtral-8x7b-moe-rp-story.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
```
Windows Command Line users: You can set the environment variable by running `set HF_HUB_ENABLE_HF_TRANSFER=1` before the download command.
</details>
<!-- README_GGUF.md-how-to-download end -->
<!-- README_GGUF.md-how-to-run start -->
## Example `llama.cpp` command
Make sure you are using `llama.cpp` from commit [d0cee0d](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221) or later.
```shell
./main -ngl 35 -m mixtral-8x7b-moe-rp-story.Q4_K_M.gguf --color -c 32768 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "{prompt}"
```
Change `-ngl 32` to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.
Change `-c 32768` to the desired sequence length. For extended sequence models - eg 8K, 16K, 32K - the necessary RoPE scaling parameters are read from the GGUF file and set by llama.cpp automatically. Note that longer sequence lengths require much more resources, so you may need to reduce this value.
If you want to have a chat-style conversation, replace the `-p <PROMPT>` argument with `-i -ins`
For other parameters and how to use them, please refer to [the llama.cpp documentation](https://github.com/ggerganov/llama.cpp/blob/master/examples/main/README.md)
## How to run in `text-generation-webui`
Note that text-generation-webui may not yet be compatible with Mixtral GGUFs. Please check compatibility first.
Further instructions can be found in the text-generation-webui documentation, here: [text-generation-webui/docs/04 ‐ Model Tab.md](https://github.com/oobabooga/text-generation-webui/blob/main/docs/04%20%E2%80%90%20Model%20Tab.md#llamacpp).
## How to run from Python code
You can use GGUF models from Python using the [llama-cpp-python](https://github.com/abetlen/llama-cpp-python) version 0.2.23 and later.
### How to load this model in Python code, using llama-cpp-python
For full documentation, please see: [llama-cpp-python docs](https://abetlen.github.io/llama-cpp-python/).
#### First install the package
Run one of the following commands, according to your system:
```shell
# Base ctransformers with no GPU acceleration
pip install llama-cpp-python
# With NVidia CUDA acceleration
CMAKE_ARGS="-DLLAMA_CUBLAS=on" pip install llama-cpp-python
# Or with OpenBLAS acceleration
CMAKE_ARGS="-DLLAMA_BLAS=ON -DLLAMA_BLAS_VENDOR=OpenBLAS" pip install llama-cpp-python
# Or with CLBLast acceleration
CMAKE_ARGS="-DLLAMA_CLBLAST=on" pip install llama-cpp-python
# Or with AMD ROCm GPU acceleration (Linux only)
CMAKE_ARGS="-DLLAMA_HIPBLAS=on" pip install llama-cpp-python
# Or with Metal GPU acceleration for macOS systems only
CMAKE_ARGS="-DLLAMA_METAL=on" pip install llama-cpp-python
# In windows, to set the variables CMAKE_ARGS in PowerShell, follow this format; eg for NVidia CUDA:
$env:CMAKE_ARGS = "-DLLAMA_OPENBLAS=on"
pip install llama-cpp-python
```
#### Simple llama-cpp-python example code
```python
from llama_cpp import Llama
# Set gpu_layers to the number of layers to offload to GPU. Set to 0 if no GPU acceleration is available on your system.
llm = Llama(
model_path="./mixtral-8x7b-moe-rp-story.Q4_K_M.gguf", # Download the model file first
n_ctx=32768, # The max sequence length to use - note that longer sequence lengths require much more resources
n_threads=8, # The number of CPU threads to use, tailor to your system and the resulting performance
n_gpu_layers=35 # The number of layers to offload to GPU, if you have GPU acceleration available
)
# Simple inference example
output = llm(
"{prompt}", # Prompt
max_tokens=512, # Generate up to 512 tokens
stop=["</s>"], # Example stop token - not necessarily correct for this specific model! Please check before using.
echo=True # Whether to echo the prompt
)
# Chat Completion API
llm = Llama(model_path="./mixtral-8x7b-moe-rp-story.Q4_K_M.gguf", chat_format="llama-2") # Set chat_format according to the model you are using
llm.create_chat_completion(
messages = [
{"role": "system", "content": "You are a story writing assistant."},
{
"role": "user",
"content": "Write a story about llamas."
}
]
)
```
## How to use with LangChain
Here are guides on using llama-cpp-python and ctransformers with LangChain:
* [LangChain + llama-cpp-python](https://python.langchain.com/docs/integrations/llms/llamacpp)
<!-- README_GGUF.md-how-to-run end -->
<!-- footer start -->
<!-- 200823 -->
## Discord
For further support, and discussions on these models and AI in general, join us at:
[TheBloke AI's Discord server](https://discord.gg/theblokeai)
## Thanks, and how to contribute
Thanks to the [chirper.ai](https://chirper.ai) team!
Thanks to Clay from [gpus.llm-utils.org](llm-utils)!
I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training.
If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects.
Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits.
* Patreon: https://patreon.com/TheBlokeAI
* Ko-Fi: https://ko-fi.com/TheBlokeAI
**Special thanks to**: Aemon Algiz.
**Patreon special mentions**: Michael Levine, 阿明, Trailburnt, Nikolai Manek, John Detwiler, Randy H, Will Dee, Sebastain Graf, NimbleBox.ai, Eugene Pentland, Emad Mostaque, Ai Maven, Jim Angel, Jeff Scroggin, Michael Davis, Manuel Alberto Morcote, Stephen Murray, Robert, Justin Joy, Luke @flexchar, Brandon Frisco, Elijah Stavena, S_X, Dan Guido, Undi ., Komninos Chatzipapas, Shadi, theTransient, Lone Striker, Raven Klaugh, jjj, Cap'n Zoog, Michel-Marie MAUDET (LINAGORA), Matthew Berman, David, Fen Risland, Omer Bin Jawed, Luke Pendergrass, Kalila, OG, Erik Bjäreholt, Rooh Singh, Joseph William Delisle, Dan Lewis, TL, John Villwock, AzureBlack, Brad, Pedro Madruga, Caitlyn Gatomon, K, jinyuan sun, Mano Prime, Alex, Jeffrey Morgan, Alicia Loh, Illia Dulskyi, Chadd, transmissions 11, fincy, Rainer Wilmers, ReadyPlayerEmma, knownsqashed, Mandus, biorpg, Deo Leter, Brandon Phillips, SuperWojo, Sean Connelly, Iucharbius, Jack West, Harry Royden McLaughlin, Nicholas, terasurfer, Vitor Caleffi, Duane Dunston, Johann-Peter Hartmann, David Ziegler, Olakabola, Ken Nordquist, Trenton Dambrowitz, Tom X Nguyen, Vadim, Ajan Kanaga, Leonard Tan, Clay Pascal, Alexandros Triantafyllidis, JM33133, Xule, vamX, ya boyyy, subjectnull, Talal Aujan, Alps Aficionado, wassieverse, Ari Malik, James Bentley, Woland, Spencer Kim, Michael Dempsey, Fred von Graf, Elle, zynix, William Richards, Stanislav Ovsiannikov, Edmond Seymore, Jonathan Leane, Martin Kemka, usrbinkat, Enrico Ros
Thank you to all my generous patrons and donaters!
And thank you again to a16z for their generous grant.
<!-- footer end -->
<!-- original-model-card start -->
# Original model card: Undi's Mixtral 8X7B MoE RP Story
Mixtral-8x7B-MoE-RP-Story is a model made primarely for chatting, RP (Roleplay) and storywriting.
2 RP model, 2 chat model, 1 occult model, 1 storywritting model, 1 mathematic model and 1 DPO model was used for a MoE. Bagel was the base.
The DPO chat model is here to help get more human reply.
This is my first try at doing this, so don't hesitate to give feedback!
WARNING: ALL THE "K" GGUF QUANT OF MIXTRAL MODELS SEEMS TO BE [BROKEN](https://cdn-uploads.huggingface.co/production/uploads/63ab1241ad514ca8d1430003/TvjEP14ps7ZUgJ-0-mhIX.png), PREFER Q4_0, Q5_0 or Q8_0!
<!-- description start -->
## Description
This repo contains fp16 files of Mixtral-8x7B-MoE-RP-Story.
<!-- description end -->
<!-- description start -->
## Models used
The list of model used and their activator/theme can be found [here](https://huggingface.co/Undi95/Mixtral-8x7B-MoE-RP-Story/blob/main/config.yaml)
<!-- description end -->
<!-- prompt-template start -->
## Prompt template: Custom
Using Bagel as a base let us a lot of different prompting system theorically, you can see all the prompting available [here](https://huggingface.co/jondurbin/bagel-7b-v0.1#prompt-formatting).
If you want to support me, you can [here](https://ko-fi.com/undiai).
<!-- original-model-card end -->
|
vilm/Quyen-Pro-v0.1 | vilm | "2024-02-08T15:02:39Z" | 1,679 | 10 | transformers | [
"transformers",
"safetensors",
"qwen2",
"text-generation",
"conversational",
"en",
"dataset:teknium/OpenHermes-2.5",
"dataset:LDJnr/Capybara",
"dataset:Intel/orca_dpo_pairs",
"dataset:argilla/distilabel-capybara-dpo-7k-binarized",
"license:other",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-02-05T16:50:31Z" | ---
library_name: transformers
license: other
datasets:
- teknium/OpenHermes-2.5
- LDJnr/Capybara
- Intel/orca_dpo_pairs
- argilla/distilabel-capybara-dpo-7k-binarized
language:
- en
pipeline_tag: text-generation
---
# Quyen
<img src="quyen.webp" width="512" height="512" alt="Quyen">
# Model Description
Quyen is our first flagship LLM series based on the Qwen1.5 family. We introduced 6 different versions:
- **Quyen-SE (0.5B)**
- **Quyen-Mini (1.8B)**
- **Quyen (4B)**
- **Quyen-Plus (7B)**
- **Quyen-Pro (14B)**
- **Quyen-Pro-Max (72B)**
All models were trained with SFT and DPO using the following dataset:
- *OpenHermes-2.5* by **Teknium**
- *Capyabara* by **LDJ**
- *argilla/distilabel-capybara-dpo-7k-binarized* by **argilla**
- *orca_dpo_pairs* by **Intel**
- and Private Data by **Ontocord** & **BEE-spoke-data**
# Prompt Template
- All Quyen models use ChatML as the default template:
```
<|im_start|>system
You are a sentient, superintelligent artificial general intelligence, here to teach and assist me.<|im_end|>
<|im_start|>user
Hello world.<|im_end|>
<|im_start|>assistant
```
- You can also use `apply_chat_template`:
```python
messages = [
{"role": "system", "content": "You are a sentient, superintelligent artificial general intelligence, here to teach and assist me."},
{"role": "user", "content": "Hello world."}
]
gen_input = tokenizer.apply_chat_template(message, return_tensors="pt")
model.generate(**gen_input)
```
# Benchmarks:
- Coming Soon! We will update the benchmarks later
# Acknowledgement
- We're incredibly grateful to **Tensoic** and **Ontocord** for their generous support with compute and data preparation.
- Special thanks to the Qwen team for letting us access the models early for these amazing finetunes. |
megagonlabs/t5-base-japanese-web | megagonlabs | "2021-09-06T10:32:21Z" | 1,678 | 18 | transformers | [
"transformers",
"pytorch",
"t5",
"text2text-generation",
"seq2seq",
"ja",
"dataset:mc4",
"dataset:wiki40b",
"arxiv:1910.10683",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text2text-generation | "2022-03-02T23:29:05Z" | ---
language: ja
tags:
- t5
- text2text-generation
- seq2seq
license: apache-2.0
datasets:
- mc4
- wiki40b
---
# t5-base-japanese-web (with Byte-fallback, 32K)
## Description
[megagonlabs/t5-base-japanese-web](https://huggingface.co/megagonlabs/t5-base-japanese-web) is a T5 (Text-to-Text Transfer Transformer) model pre-trained on Japanese web texts.
Training codes are [available on GitHub](https://github.com/megagonlabs/t5-japanese).
The vocabulary size of this model is 32K.
[8K version is also available](https://huggingface.co/megagonlabs/t5-base-japanese-web-8k).
### Corpora
We used following corpora for pre-training.
- Japanese in [mC4/3.0.1](https://huggingface.co/datasets/mc4) (We used [Tensorflow native format](https://github.com/allenai/allennlp/discussions/5056))
- 87,425,304 pages
- 782 GB in TFRecord format
- [Japanese](https://www.tensorflow.org/datasets/catalog/wiki40b#wiki40bja) in [wiki40b/1.3.0](https://www.tensorflow.org/datasets/catalog/wiki40b)
- 828,236 articles (2,073,584 examples)
- 2 GB in TFRecord format
### Tokenizer
We used Japanese Wikipedia to train [SentencePiece](https://github.com/google/sentencepiece).
- Vocabulary size: 32,000
- [Byte-fallback](https://github.com/google/sentencepiece/releases/tag/v0.1.9): Enabled
### Parameters
- T5 model: [models/t5.1.1.base.gin](https://github.com/google-research/text-to-text-transfer-transformer/blob/main/t5/models/gin/models/t5.1.1.base.gin)
- Training steps: 1,000,000
It took about 126 hours with TPU v3-8
## Related models
- [日本語T5事前学習済みモデル (sonoisa/t5-base-japanese)](https://huggingface.co/sonoisa/t5-base-japanese)
- [日本語T5事前学習済みモデル (sonoisa/t5-base-japanese-mC4-Wikipedia)](https://huggingface.co/sonoisa/t5-base-japanese-mC4-Wikipedia)
## License
Apache License 2.0
## Citations
- mC4
Contains information from `mC4` which is made available under the [ODC Attribution License](https://opendatacommons.org/licenses/by/1-0/).
```bibtex
@article{2019t5,
author = {Colin Raffel and Noam Shazeer and Adam Roberts and Katherine Lee and Sharan Narang and Michael Matena and Yanqi Zhou and Wei Li and Peter J. Liu},
title = {Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer},
journal = {arXiv e-prints},
year = {2019},
archivePrefix = {arXiv},
eprint = {1910.10683},
}
```
- wiki40b
```bibtex
@inproceedings{49029,
title = {Wiki-40B: Multilingual Language Model Dataset},
author = {Mandy Guo and Zihang Dai and Denny Vrandecic and Rami Al-Rfou},
year = {2020},
booktitle = {LREC 2020}
}
```
|
vitouphy/wav2vec2-xls-r-300m-timit-phoneme | vitouphy | "2023-05-13T17:04:31Z" | 1,678 | 22 | transformers | [
"transformers",
"pytorch",
"safetensors",
"wav2vec2",
"automatic-speech-recognition",
"en",
"generated_from_trainer",
"doi:10.57967/hf/0125",
"license:apache-2.0",
"model-index",
"endpoints_compatible",
"region:us"
] | automatic-speech-recognition | "2022-05-08T06:41:55Z" | ---
language:
- en
license: apache-2.0
tags:
- automatic-speech-recognition
- pytorch
- transformers
- en
- generated_from_trainer
model-index:
- name: wav2vec2-xls-r-300m-phoneme
results:
- task:
name: Speech Recognition
type: automatic-speech-recognition
dataset:
name: DARPA TIMIT
type: timit
args: en
metrics:
- name: Test CER
type: cer
value: 7.996
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
## Model
This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the Timit dataset. Check [this notebook](https://www.kaggle.com/code/vitouphy/phoneme-recognition-with-wav2vec2) for training detail.
## Usage
**Approach 1:** Using HuggingFace's pipeline, this will cover everything end-to-end from raw audio input to text output.
```python
from transformers import pipeline
# Load the model
pipe = pipeline(model="vitouphy/wav2vec2-xls-r-300m-timit-phoneme")
# Process raw audio
output = pipe("audio_file.wav", chunk_length_s=10, stride_length_s=(4, 2))
```
**Approach 2:** More custom way to predict phonemes.
```python
from transformers import Wav2Vec2Processor, Wav2Vec2ForCTC
from datasets import load_dataset
import torch
import soundfile as sf
# load model and processor
processor = Wav2Vec2Processor.from_pretrained("vitouphy/wav2vec2-xls-r-300m-timit-phoneme")
model = Wav2Vec2ForCTC.from_pretrained("vitouphy/wav2vec2-xls-r-300m-timit-phoneme")
# Read and process the input
audio_input, sample_rate = sf.read("audio_file.wav")
inputs = processor(audio_input, sampling_rate=16_000, return_tensors="pt", padding=True)
with torch.no_grad():
logits = model(inputs.input_values, attention_mask=inputs.attention_mask).logits
# Decode id into string
predicted_ids = torch.argmax(logits, axis=-1)
predicted_sentences = processor.batch_decode(predicted_ids)
print(predicted_sentences)
```
## Training and evaluation data
We use [DARPA TIMIT dataset](https://www.kaggle.com/datasets/mfekadu/darpa-timit-acousticphonetic-continuous-speech) for this model.
- We split into **80/10/10** for training, validation, and testing respectively.
- That roughly corresponds to about **137/17/17** minutes.
- The model obtained **7.996%** on this test set.
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 3e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 2000
- training_steps: 10000
- mixed_precision_training: Native AMP
### Framework versions
- Transformers 4.17.0.dev0
- Pytorch 1.10.2+cu102
- Datasets 1.18.2.dev0
- Tokenizers 0.11.0
### Citation
```
@misc { phy22-phoneme,
author = {Phy, Vitou},
title = {{Automatic Phoneme Recognition on TIMIT Dataset with Wav2Vec 2.0}},
year = 2022,
note = {{If you use this model, please cite it using these metadata.}},
publisher = {Hugging Face},
version = {1.0},
doi = {10.57967/hf/0125},
url = {https://huggingface.co/vitouphy/wav2vec2-xls-r-300m-timit-phoneme}
}
``` |
TheBloke/LongChat-13B-GPTQ | TheBloke | "2023-08-21T02:19:16Z" | 1,678 | 27 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"custom_code",
"license:other",
"autotrain_compatible",
"text-generation-inference",
"4-bit",
"gptq",
"region:us"
] | text-generation | "2023-06-30T09:14:43Z" | ---
inference: false
license: other
---
<!-- header start -->
<!-- 200823 -->
<div style="width: auto; margin-left: auto; margin-right: auto">
<img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
</div>
<div style="display: flex; justify-content: space-between; width: 100%;">
<div style="display: flex; flex-direction: column; align-items: flex-start;">
<p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://discord.gg/theblokeai">Chat & support: TheBloke's Discord server</a></p>
</div>
<div style="display: flex; flex-direction: column; align-items: flex-end;">
<p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p>
</div>
</div>
<div style="text-align:center; margin-top: 0em; margin-bottom: 0em"><p style="margin-top: 0.25em; margin-bottom: 0em;">TheBloke's LLM work is generously supported by a grant from <a href="https://a16z.com">andreessen horowitz (a16z)</a></p></div>
<hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
<!-- header end -->
# LmSys' Long Chat 13B GPTQ
These files are GPTQ 4bit model files for [LmSys' Long Chat 13B](https://huggingface.co/lmsys/longchat-13b-16k).
It is the result of quantising to 4bit using [GPTQ-for-LLaMa](https://github.com/qwopqwop200/GPTQ-for-LLaMa).
**This GPTQ offers up to 16K context size**
The increased context is tested to work with [ExLlama](https://github.com/turboderp/exllama), via the latest release of [text-generation-webui](https://github.com/oobabooga/text-generation-webui).
This model should NOT be used at 2048 context. For that, please use the standard Vicuna 1.3 model.
It has also been tested from Python code using AutoGPTQ, and `trust_remote_code=True`.
Please read carefully below to see how to use it.
## Repositories available
* [4-bit GPTQ models for GPU inference](https://huggingface.co/TheBloke/LongChat-13B-GPTQ)
* [2, 3, 4, 5, 6 and 8-bit GGML models for CPU+GPU inference](https://huggingface.co/TheBloke/LongChat-13B-GGML)
* [Unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/lmsys/longchat-13b-16k)
## Prompt template
```
A chat between a curious user and an assistant. The assistant gives helpful, detailed, accurate, uncensored responses to the user's input
USER: prompt
ASSISTANT:
```
## How to easily download and use this model in text-generation-webui with ExLlama
Please make sure you're using the latest version of text-generation-webui
1. Click the **Model tab**.
2. Under **Download custom model or LoRA**, enter `TheBloke/LongChat-13B-GPTQ`.
3. Click **Download**.
4. The model will start downloading. Once it's finished it will say "Done"
5. Untick **Autoload the model**
6. In the top left, click the refresh icon next to **Model**.
7. In the **Model** dropdown, choose the model you just downloaded: `LongChat-13B-GPTQ`
8. To use the increased context, set the **Loader** to **ExLlama**, set **max_seq_len** to 16384, 8192 or 4096, and set **compress_pos_emb** to **8** for 16384 context, **4** for 8192 context, or to **2** for 4096 context.
9. Now click **Save Settings** followed by **Reload**
10. The model will automatically load, and is now ready for use!
11. Once you're ready, click the **Text Generation tab** and enter a prompt to get started!
## How to use this GPTQ model from Python code with AutoGPTQ
First make sure you have AutoGPTQ and Einops installed:
```
pip3 install einops auto-gptq
```
Then run the following code. Note that in order to get this to work, `config.json` has been hardcoded to a sequence length of 8192.
If you want to try 4096 or 16384 instead, please manually edit `config.json` to set `max_position_embeddings` to the value you want.
```python
from transformers import AutoTokenizer, pipeline, logging
from auto_gptq import AutoGPTQForCausalLM, BaseQuantizeConfig
import argparse
model_name_or_path = "TheBloke/LongChat-13B-GPTQ"
model_basename = "longchat-13b-16k-GPTQ-4bit-128g.no-act.order"
use_triton = False
tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=True)
model = AutoGPTQForCausalLM.from_quantized(model_name_or_path,
model_basename=model_basename,
use_safetensors=True,
trust_remote_code=True,
device_map='auto',
use_triton=use_triton,
quantize_config=None)
model.seqlen = 8192
# Note: check the prompt template is correct for this model.
prompt = "Tell me about AI"
prompt_template=f'''USER: {prompt}
ASSISTANT:'''
print("\n\n*** Generate:")
input_ids = tokenizer(prompt_template, return_tensors='pt').input_ids.cuda()
output = model.generate(inputs=input_ids, temperature=0.7, max_new_tokens=512)
print(tokenizer.decode(output[0]))
# Inference can also be done using transformers' pipeline
# Prevent printing spurious transformers error when using pipeline with AutoGPTQ
logging.set_verbosity(logging.CRITICAL)
print("*** Pipeline:")
pipe = pipeline(
"text-generation",
model=model,
tokenizer=tokenizer,
max_new_tokens=512,
temperature=0.7,
top_p=0.95,
repetition_penalty=1.15
)
print(pipe(prompt_template)[0]['generated_text'])
```
## Provided files
**longchat-13b-16k-GPTQ-4bit-128g.no-act.order.safetensors**
This will work with AutoGPTQ, ExLlama, and CUDA versions of GPTQ-for-LLaMa. There are reports of issues with Triton mode of recent GPTQ-for-LLaMa. If you have issues, please use AutoGPTQ instead.
It was created with group_size 128 to increase inference accuracy, but without --act-order (desc_act) to increase compatibility and improve inference speed.
* `longchat-13b-16k-GPTQ-4bit-128g.no-act.order.safetensors`
* Works for use with ExLlama with increased context (4096, 8192, 16384, or other values in-between)
* Works with AutoGPTQ in Python code, including with increased context, if `trust_remote_code=True` is set.
* Should work with GPTQ-for-LLaMa in CUDA mode, but unknown if increased context works - TBC. May have issues with GPTQ-for-LLaMa Triton mode.
* Works with text-generation-webui, including one-click-installers.
* Parameters: Groupsize = 128. Act Order / desc_act = False.
<!-- footer start -->
<!-- 200823 -->
## Discord
For further support, and discussions on these models and AI in general, join us at:
[TheBloke AI's Discord server](https://discord.gg/theblokeai)
## Thanks, and how to contribute.
Thanks to the [chirper.ai](https://chirper.ai) team!
I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training.
If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects.
Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits.
* Patreon: https://patreon.com/TheBlokeAI
* Ko-Fi: https://ko-fi.com/TheBlokeAI
**Special thanks to**: Aemon Algiz.
**Patreon special mentions**: Sam, theTransient, Jonathan Leane, Steven Wood, webtim, Johann-Peter Hartmann, Geoffrey Montalvo, Gabriel Tamborski, Willem Michiel, John Villwock, Derek Yates, Mesiah Bishop, Eugene Pentland, Pieter, Chadd, Stephen Murray, Daniel P. Andersen, terasurfer, Brandon Frisco, Thomas Belote, Sid, Nathan LeClaire, Magnesian, Alps Aficionado, Stanislav Ovsiannikov, Alex, Joseph William Delisle, Nikolai Manek, Michael Davis, Junyu Yang, K, J, Spencer Kim, Stefan Sabev, Olusegun Samson, transmissions 11, Michael Levine, Cory Kujawski, Rainer Wilmers, zynix, Kalila, Luke @flexchar, Ajan Kanaga, Mandus, vamX, Ai Maven, Mano Prime, Matthew Berman, subjectnull, Vitor Caleffi, Clay Pascal, biorpg, alfie_i, 阿明, Jeffrey Morgan, ya boyyy, Raymond Fosdick, knownsqashed, Olakabola, Leonard Tan, ReadyPlayerEmma, Enrico Ros, Dave, Talal Aujan, Illia Dulskyi, Sean Connelly, senxiiz, Artur Olbinski, Elle, Raven Klaugh, Fen Risland, Deep Realms, Imad Khwaja, Fred von Graf, Will Dee, usrbinkat, SuperWojo, Alexandros Triantafyllidis, Swaroop Kallakuri, Dan Guido, John Detwiler, Pedro Madruga, Iucharbius, Viktor Bowallius, Asp the Wyvern, Edmond Seymore, Trenton Dambrowitz, Space Cruiser, Spiking Neurons AB, Pyrater, LangChain4j, Tony Hughes, Kacper Wikieł, Rishabh Srivastava, David Ziegler, Luke Pendergrass, Andrey, Gabriel Puliatti, Lone Striker, Sebastain Graf, Pierre Kircher, Randy H, NimbleBox.ai, Vadim, danny, Deo Leter
Thank you to all my generous patrons and donaters!
And thank you again to a16z for their generous grant.
<!-- footer end -->
# Original model card: LmSys' Long Chat 13B
# longchat-13b-16k Model Card
## Model details
**Model type:**
longchat-13b-16k is an open-source chatbot trained by fine-tuning llama-13b on user-shared conversations collected from ShareGPT, using the condensing rotary embedding technique reported in the [blog](https://lmsys.org/blog/2023-06-29-longchat).
**Model date:**
longchat-13b-16k was trained on June 2023.
**Organizations developing the model:**
The LongChat developers: Dacheng Li*, Rulin Shao*, Anze Xie, Ying Sheng, Lianmin Zheng, Ion Stoica, Xuezhe Ma, and Hao Zhang
**Paper or resources for more information:**
https://github.com/DachengLi1/LongChat
**Where to send questions or comments about the model:**
https://github.com/DachengLi1/LongChat
## Intended use
**Primary intended uses:**
The primary use of longchat-13b-16k is for research purposes.
**Primary intended users:**
The primary intended users of the model are researchers in natural language processing, machine learning, and artificial intelligence.
## Training dataset
18K conversations collected from ShareGPT.com.
## Evaluation dataset
A preliminary evaluation of the model quality is conducted by our released [LongEval](https://github.com/DachengLi1/LongChat).
|
adept/persimmon-8b-chat | adept | "2023-10-11T15:07:27Z" | 1,678 | 42 | transformers | [
"transformers",
"pytorch",
"persimmon",
"text-generation",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-generation | "2023-09-07T19:39:24Z" | ---
license: apache-2.0
---
At Adept, we’re working towards an AI agent that can help people do anything they need to do on a computer. We’re not in the business of shipping isolated language models (LMs)—this was an early output of the model scaling program that will support our products.
We trained it from scratch using a context size of 16K. Many LM use cases are context-bound; our model has 4 times the context size of LLaMA2 and 8 times that of GPT-3, MPT, etc.
This is a chat finetuned version of the base model. The best prompt to use is:
human: [some query]
adept:
See https://www.adept.ai/blog/persimmon-8b for more info |
LeoLM/leo-hessianai-7b-chat-bilingual | LeoLM | "2023-09-29T13:16:38Z" | 1,678 | 7 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"custom_code",
"en",
"de",
"dataset:LeoLM/OpenSchnabeltier",
"dataset:OpenAssistant/OASST-DE",
"dataset:FreedomIntelligence/alpaca-gpt4-deutsch",
"dataset:FreedomIntelligence/evol-instruct-deutsch",
"dataset:LeoLM/German_Poems",
"dataset:LeoLM/German_Songs",
"dataset:garage-bAInd/Open-Platypus",
"dataset:WizardLM/WizardLM_evol_instruct_70k",
"dataset:bjoernp/oasst25-08-23-filtered",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-09-10T19:00:52Z" | ---
datasets:
- LeoLM/OpenSchnabeltier
- OpenAssistant/OASST-DE
- FreedomIntelligence/alpaca-gpt4-deutsch
- FreedomIntelligence/evol-instruct-deutsch
- LeoLM/German_Poems
- LeoLM/German_Songs
- garage-bAInd/Open-Platypus
- WizardLM/WizardLM_evol_instruct_70k
- bjoernp/oasst25-08-23-filtered
language:
- en
- de
library_name: transformers
pipeline_tag: text-generation
---
# LAION LeoLM: **L**inguistically **E**nhanced **O**pen **L**anguage **M**odel
Meet LeoLM, the first open and commercially available German Foundation Language Model built on Llama-2.
Our models extend Llama-2's capabilities into German through continued pretraining on a large corpus of German-language and mostly locality specific text.
Thanks to a compute grant at HessianAI's new supercomputer **42**, we release two foundation models trained with 8k context length,
[`LeoLM/leo-hessianai-7b`](https://huggingface.co/LeoLM/leo-hessianai-7b) and [`LeoLM/leo-hessianai-13b`](https://huggingface.co/LeoLM/leo-hessianai-13b) under the [Llama-2 community license](https://huggingface.co/meta-llama/Llama-2-70b/raw/main/LICENSE.txt) (70b also coming soon! 👀).
With this release, we hope to bring a new wave of opportunities to German open-source and commercial LLM research and accelerate adoption.
Read our [blog post]() or our paper (preprint coming soon) for more details!
*A project by Björn Plüster and Christoph Schuhmann in collaboration with LAION and HessianAI.*
## LeoLM Chat
`LeoLM/leo-hessianai-7b-chat-bilingual` is a bilingual English-German chat model built on our foundation model `LeoLM/leo-hessianai-7b` and finetuned on a selection of German translateed instruction datasets and their English counterparts.
The model performs exceptionally well on writing, explanation and discussion tasks but struggles somewhat with math and advanced reasoning. See our MT-Bench scores:
```
{
"first_turn": 5.64375,
"second_turn": 4.075,
"categories": {
"writing": 5.925,
"roleplay": 5.25,
"reasoning": 3.1,
"math": 1.8,
"coding": 3.4,
"extraction": 5,
"stem": 6.5,
"humanities": 7.9
},
"average": 4.859375
}
```
## Model Details
- **Finetuned from:** [LeoLM/leo-hessianai-7b](https://huggingface.co/LeoLM/leo-hessianai-7b)
- **Model type:** Causal decoder-only transformer language model
- **Language:** English and German
- **Demo:** [Web Demo]()
- **License:** [LLAMA 2 COMMUNITY LICENSE AGREEMENT](https://huggingface.co/meta-llama/Llama-2-70b/raw/main/LICENSE.txt)
- **Contact:** [LAION Discord](https://discord.com/invite/eq3cAMZtCC) or [Björn Plüster](mailto:[email protected])
## Use in 🤗Transformers
First install direct dependencies:
```
pip install transformers torch sentencepiece
```
If you want faster inference using flash-attention2, you need to install these dependencies:
```bash
pip install packaging ninja
pip install flash-attn==v2.1.1 --no-build-isolation
pip install git+https://github.com/HazyResearch/[email protected]#subdirectory=csrc/rotary
```
Then load the model in transformers:
```python
from transformers import pipeline
import torch
system_prompt = """<|im_start|>system
Dies ist eine Unterhaltung zwischen einem intelligenten, hilfsbereitem KI-Assistenten und einem Nutzer.
Der Assistent gibt ausführliche, hilfreiche und ehrliche Antworten.<|im_end|>
"""
prompt_format = "<|im_start|>user\n{prompt}<|im_end|>\n<|im_start|>assistant\n"
prompt = "Erkläre mir wie die Fahrradwegesituation in Hamburg ist."
generator = pipeline(model="LeoLM/leo-hessianai-7b-chat-bilingual", device="cuda", torch_dtype=torch.float16, trust_remote_code=True) # True for flash-attn2 else False
print(generator(prompt_format.format(prompt=prompt), do_sample=True, top_p=0.95, max_length=8192))
```
"*Als KI kann ich keine persönlichen Beobachtungen teilen, aber ich kann einige allgemeine Informationen zur Fahrradwegesituation in Hamburg liefern. Im Vergleich zu vielen anderen großen Städten hat Hamburg eine hohe Anzahl von Fahrradfahrern und nimmt seine Verantwortung für nachhaltige Verkehrsmittel sehr ernst. Es gibt viele Fahrradwege und separate Fahrspuren, die Radfahrern ermöglichen, zusammen mit dem Autoverkehr zu fahren. Diese Fahrradspuren sind oft mit Markierungen gekennzeichnet und durch physische Trennungen von anderen Fahrspuren abgegrenzt. Darüber hinaus gibt es viele Fahrradstraßen, auf denen Radfahrer Vorfahrt haben und Autos langsamer fahren müssen.*
*In einigen städtischen Gebieten können Fahrradwege jedoch eng oder überfüllt sein, besonders während der Stoßzeiten. Es gibt auch viele Kreuzungen, an denen Radfahrer anhalten und auf Grün warten müssen, ähnlich wie Autofahrer. Insgesamt ist die Fahrradinfrastruktur in Hamburg ziemlich gut, aber wie überall gibt es immer Raum für Verbesserungen.*"
## Prompting / Prompt Template
Prompt dialogue template (ChatML format):
```
"""
<|im_start|>system
{system_message}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant
"""
```
The model input can contain multiple conversation turns between user and assistant, e.g.
```
<|im_start|>user
{prompt 1}<|im_end|>
<|im_start|>assistant
{reply 1}<|im_end|>
<|im_start|>user
{prompt 2}<|im_end|>
<|im_start|>assistant
(...)
```
## Ethical Considerations and Limitations
LeoLM has been tested in English and German, and has not covered, nor could it cover all scenarios.
For these reasons, as with all LLMs, the potential outputs of `LeoLM/leo-hessianai-7b-chat` cannot be predicted
in advance, and the model may in some instances produce inaccurate, biased or other objectionable responses
to user prompts. Therefore, before deploying any applications of `LeoLM/leo-hessianai-7b-chat`, developers should
perform safety testing and tuning tailored to their specific applications of the model.
Please see Meta's [Responsible Use Guide](https://ai.meta.com/llama/responsible-use-guide/).
## Finetuning Details
| Hyperparameter | Value |
|---|---|
| Num epochs | 3 |
| Examples per epoch | 233275 |
| Global batch size | 256 |
| Learning rate | 3e-5 |
| Warmup steps | 100 |
| LR scheduler | Cosine |
| Adam betas | (0.9, 0.95) |
| Weight decay | 0.001 |
## Dataset Details
```
## Stats for 'Subset of LeoLM/OpenSchnabeltier' (21314 samples (100.0%))
-----------------
Accepted: 21314/21314 (100.0%)
Accepted tokens: 8134690
Skipped: 0 (0.0%)
Min tokens per sample: 25
Max tokens per sample: 1202
Avg tokens per sample: 381.65947264708643
-----------------
## Stats for 'Subset of garage-bAInd/Open-Platypus' (24427 samples (100.0%))
-----------------
Accepted: 24427/24427 (100.0%)
Accepted tokens: 9549043
Skipped: 0 (0.0%)
Min tokens per sample: 23
Max tokens per sample: 5054
Avg tokens per sample: 390.9216440823679
-----------------
## Stats for 'Subset of WizardLM/WizardLM_evol_instruct_70k' (68600 samples (100.0%))
-----------------
Accepted: 68600/68600 (100.0%)
Accepted tokens: 33045040
Skipped: 0 (0.0%)
Min tokens per sample: 18
Max tokens per sample: 11810
Avg tokens per sample: 481.7061224489796
-----------------
## Stats for 'Subset of FreedomIntelligence/evol-instruct-deutsch' (57841 samples (100.0%))
-----------------
Accepted: 57841/57841 (100.0%)
Accepted tokens: 42958192
Skipped: 0 (0.0%)
Min tokens per sample: 33
Max tokens per sample: 5507
Avg tokens per sample: 742.6944900675991
-----------------
## Stats for 'Subset of FreedomIntelligence/alpaca-gpt4-deutsch' (48969 samples (100.0%))
-----------------
Accepted: 48969/48969 (100.0%)
Accepted tokens: 13372005
Skipped: 0 (0.0%)
Min tokens per sample: 19
Max tokens per sample: 1359
Avg tokens per sample: 273.07082031489307
-----------------
## Stats for 'Subset of LeoLM/German_Songs' (490 samples (100.0%))
-----------------
Accepted: 490/490 (100.0%)
Accepted tokens: 618642
Skipped: 0 (0.0%)
Min tokens per sample: 747
Max tokens per sample: 1678
Avg tokens per sample: 1262.534693877551
-----------------
## Stats for 'Subset of LeoLM/German_Poems' (392 samples (100.0%))
-----------------
Accepted: 392/392 (100.0%)
Accepted tokens: 187897
Skipped: 0 (0.0%)
Min tokens per sample: 231
Max tokens per sample: 826
Avg tokens per sample: 479.3290816326531
-----------------
## Stats for 'Subset of OpenAssistant/OASST_DE' (3646 samples (100.0%))
-----------------
Accepted: 3646/3646 (100.0%)
Accepted tokens: 2338738
Skipped: 0 (0.0%)
Min tokens per sample: 29
Max tokens per sample: 2484
Avg tokens per sample: 641.4530992868897
-----------------
## Stats for 'Subset of bjoernp/oasst25-08-23-filtered' (8922 samples (100.0%))
-----------------
Accepted: 8922/8922 (100.0%)
Accepted tokens: 4526427
Skipped: 0 (0.0%)
Min tokens per sample: 23
Max tokens per sample: 5407
Avg tokens per sample: 507.3332212508406
-----------------
## Stats for 'total' (235632 samples (100.0%))
-----------------
Accepted: 235632/235632 (100.0%)
Accepted tokens: 115862397
Skipped: 0 (0.0%)
Min tokens per sample: 18
Max tokens per sample: 11810
Avg tokens per sample: 491.70909299246284
-----------------
``` |
Weyaxi/HelpSteer-filtered-7B | Weyaxi | "2023-11-24T19:35:20Z" | 1,678 | 0 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"instruct",
"en",
"dataset:Weyaxi/HelpSteer-filtered",
"license:cc-by-4.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-11-24T19:07:00Z" | ---
license: cc-by-4.0
datasets:
- Weyaxi/HelpSteer-filtered
language:
- en
tags:
- mistral
- instruct
---
# HelpSteer-filtered-7B
Original weights of [HelpSteer-filtered-7B](https://huggingface.co/Weyaxi/HelpSteer-filtered-7B). Finetuned from [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1).
## Lora Weights
You can access lora weights from here:
[Weyaxi/HelpSteer-filtered-7B-Lora](https://huggingface.co/Weyaxi/HelpSteer-filtered-7B-Lora) |
Sao10K/Frostwind-10.7B-v1 | Sao10K | "2023-12-19T09:46:58Z" | 1,678 | 8 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"en",
"license:cc-by-nc-4.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-12-19T04:43:06Z" | ---
license: cc-by-nc-4.0
language:
- en
---
Frostwind-v1
A finetune of [upstage/SOLAR-10.7B-v1.0](https://huggingface.co/upstage/SOLAR-10.7B-v1.0)
<br>Took Roughly 3 Hours with 4x 4090s, over 2 Epochs, with around 52K varied samples.
Dataset Composition:
<br>20% - Coding
<br>30% - Instruct
<br>30% - Generalised Data
<br>10% - Roleplay
<br>10% - Dealignment
***
Testing Notes:
Fairly smart, as I expected. Obviously not at the level of the bigger models, but I did not expect that level from this.
Could be sampler issues, but generally I needed 1/2 swipes to get the correct answer when doing Zero context tests. If context is filled, no issues on my end.
For Roleplays: adding things like avoid writing as {{user}} suprisingly helps. Plus a proper prompt of course. I liked the writing style. Handles group characters in 1 card well, during my tests.
Fairly uncensored *during roleplay.* Yeah the as an AI stuff can happen at Zero context, but I have no issues once a character card is introduced. I had no issues making outputs that would give me 2500 Life Sentences if posted here.
***
Trained with Alpaca Format:
```
### Instruction:
<Prompt>
### Response:
```
OR
```
### Instruction:
<Prompt>
### Input:
<Insert Context Here>
### Response:
```
***
<br>wandb:
<br>wandb: Run history:
<br>wandb: eval/loss █▃▂▂▂▂▂▁▁▁▁▂▂▂▂▂▂▁▁▁
<br>wandb: eval/runtime ▃▂▃▂▃▂▂▃▁▃█▂▃▃▃▂▃▃▂▂
<br>wandb: eval/samples_per_second ▆▇▆▇▆▇▇▆█▆▁▇▆▆▆▇▆▆▇▇
<br>wandb: eval/steps_per_second ▆▇▆▇▆▇▇▆█▆▁▇▆▆▆▇▆▆▇▇
<br>wandb: train/epoch ▁▁▁▂▂▂▂▂▂▃▃▃▃▃▄▄▄▄▄▄▅▅▅▅▅▅▆▆▆▆▆▇▇▇▇▇▇███
<br>wandb: train/global_step ▁▁▁▂▂▂▂▂▂▃▃▃▃▃▄▄▄▄▄▄▅▅▅▅▅▅▆▆▆▆▆▇▇▇▇▇▇███
<br>wandb: train/learning_rate ▄███████▇▇▇▇▇▆▆▆▆▅▅▅▅▄▄▄▃▃▃▃▂▂▂▂▂▁▁▁▁▁▁▁
<br>wandb: train/loss █▅▅▆▅▅▄▄▄▆▆▅▆▆▆▅▄▆▅▅▅▆▄▄▃▄▃▃▂▃▄▂▂▃▃▂▁▂▂▂
<br>wandb:
<br>wandb: Run summary:
<br>wandb: eval/loss 0.74622
<br>wandb: eval/runtime 72.5049
<br>wandb: eval/samples_per_second 37.239
<br>wandb: eval/steps_per_second 2.331
<br>wandb: train/epoch 1.98
<br>wandb: train/global_step 410
<br>wandb: train/learning_rate 0.0
<br>wandb: train/loss 0.6457
<br>wandb: train/total_flos 3.4382652340646707e+18
<br>wandb: train/train_loss 0.70204
<br>wandb: train/train_runtime 10880.917
<br>wandb: train/train_samples_per_second 9.417
<br>wandb: train/train_steps_per_second 0.038
<br>wandb: |
ToyotaGoodPrice/gemma-2b-it-mnlp-m2 | ToyotaGoodPrice | "2024-06-03T20:15:27Z" | 1,678 | 0 | peft | [
"peft",
"safetensors",
"arxiv:1910.09700",
"base_model:google/gemma-1.1-2b-it",
"region:us"
] | null | "2024-06-03T20:07:17Z" | ---
library_name: peft
base_model: google/gemma-1.1-2b-it
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
### Framework versions
- PEFT 0.11.1 |
MaziyarPanahi/mergekit-slerp-rnzykzl-GGUF | MaziyarPanahi | "2024-06-16T14:35:57Z" | 1,678 | 0 | transformers | [
"transformers",
"gguf",
"mistral",
"quantized",
"2-bit",
"3-bit",
"4-bit",
"5-bit",
"6-bit",
"8-bit",
"GGUF",
"safetensors",
"text-generation",
"mergekit",
"merge",
"conversational",
"base_model:WizardLM/WizardMath-7B-V1.1",
"base_model:NousResearch/Hermes-2-Pro-Mistral-7B",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us",
"base_model:mergekit-community/mergekit-slerp-rnzykzl"
] | text-generation | "2024-06-16T14:13:34Z" | ---
tags:
- quantized
- 2-bit
- 3-bit
- 4-bit
- 5-bit
- 6-bit
- 8-bit
- GGUF
- transformers
- safetensors
- mistral
- text-generation
- mergekit
- merge
- conversational
- base_model:WizardLM/WizardMath-7B-V1.1
- base_model:NousResearch/Hermes-2-Pro-Mistral-7B
- autotrain_compatible
- endpoints_compatible
- text-generation-inference
- region:us
- text-generation
model_name: mergekit-slerp-rnzykzl-GGUF
base_model: mergekit-community/mergekit-slerp-rnzykzl
inference: false
model_creator: mergekit-community
pipeline_tag: text-generation
quantized_by: MaziyarPanahi
---
# [MaziyarPanahi/mergekit-slerp-rnzykzl-GGUF](https://huggingface.co/MaziyarPanahi/mergekit-slerp-rnzykzl-GGUF)
- Model creator: [mergekit-community](https://huggingface.co/mergekit-community)
- Original model: [mergekit-community/mergekit-slerp-rnzykzl](https://huggingface.co/mergekit-community/mergekit-slerp-rnzykzl)
## Description
[MaziyarPanahi/mergekit-slerp-rnzykzl-GGUF](https://huggingface.co/MaziyarPanahi/mergekit-slerp-rnzykzl-GGUF) contains GGUF format model files for [mergekit-community/mergekit-slerp-rnzykzl](https://huggingface.co/mergekit-community/mergekit-slerp-rnzykzl).
### About GGUF
GGUF is a new format introduced by the llama.cpp team on August 21st 2023. It is a replacement for GGML, which is no longer supported by llama.cpp.
Here is an incomplete list of clients and libraries that are known to support GGUF:
* [llama.cpp](https://github.com/ggerganov/llama.cpp). The source project for GGUF. Offers a CLI and a server option.
* [llama-cpp-python](https://github.com/abetlen/llama-cpp-python), a Python library with GPU accel, LangChain support, and OpenAI-compatible API server.
* [LM Studio](https://lmstudio.ai/), an easy-to-use and powerful local GUI for Windows and macOS (Silicon), with GPU acceleration. Linux available, in beta as of 27/11/2023.
* [text-generation-webui](https://github.com/oobabooga/text-generation-webui), the most widely used web UI, with many features and powerful extensions. Supports GPU acceleration.
* [KoboldCpp](https://github.com/LostRuins/koboldcpp), a fully featured web UI, with GPU accel across all platforms and GPU architectures. Especially good for story telling.
* [GPT4All](https://gpt4all.io/index.html), a free and open source local running GUI, supporting Windows, Linux and macOS with full GPU accel.
* [LoLLMS Web UI](https://github.com/ParisNeo/lollms-webui), a great web UI with many interesting and unique features, including a full model library for easy model selection.
* [Faraday.dev](https://faraday.dev/), an attractive and easy to use character-based chat GUI for Windows and macOS (both Silicon and Intel), with GPU acceleration.
* [candle](https://github.com/huggingface/candle), a Rust ML framework with a focus on performance, including GPU support, and ease of use.
* [ctransformers](https://github.com/marella/ctransformers), a Python library with GPU accel, LangChain support, and OpenAI-compatible AI server. Note, as of time of writing (November 27th 2023), ctransformers has not been updated in a long time and does not support many recent models.
## Special thanks
🙏 Special thanks to [Georgi Gerganov](https://github.com/ggerganov) and the whole team working on [llama.cpp](https://github.com/ggerganov/llama.cpp/) for making all of this possible. |
John6666/ras-real-anime-screencap-v1-sdxl | John6666 | "2024-06-26T01:07:17Z" | 1,678 | 0 | diffusers | [
"diffusers",
"safetensors",
"text-to-image",
"stable-diffusion",
"stable-diffusion-xl",
"anime",
"pony",
"license:other",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionXLPipeline",
"region:us"
] | text-to-image | "2024-06-26T01:02:44Z" | ---
license: other
license_name: faipl-1.0-sd
license_link: https://freedevproject.org/faipl-1.0-sd/
tags:
- text-to-image
- stable-diffusion
- stable-diffusion-xl
- anime
- pony
---
Original model is [here](https://civitai.com/models/538280/ras-real-anime-screencap-ponysdxl?modelVersionId=598405).
|
RichardErkhov/attention-avengers_-_Qwen1.5-0.5B-Chat-SFT-MCQA-gguf | RichardErkhov | "2024-06-30T04:29:10Z" | 1,678 | 0 | null | [
"gguf",
"region:us"
] | null | "2024-06-30T04:20:39Z" | Quantization made by Richard Erkhov.
[Github](https://github.com/RichardErkhov)
[Discord](https://discord.gg/pvy7H8DZMG)
[Request more models](https://github.com/RichardErkhov/quant_request)
Qwen1.5-0.5B-Chat-SFT-MCQA - GGUF
- Model creator: https://huggingface.co/attention-avengers/
- Original model: https://huggingface.co/attention-avengers/Qwen1.5-0.5B-Chat-SFT-MCQA/
| Name | Quant method | Size |
| ---- | ---- | ---- |
| [Qwen1.5-0.5B-Chat-SFT-MCQA.Q2_K.gguf](https://huggingface.co/RichardErkhov/attention-avengers_-_Qwen1.5-0.5B-Chat-SFT-MCQA-gguf/blob/main/Qwen1.5-0.5B-Chat-SFT-MCQA.Q2_K.gguf) | Q2_K | 0.23GB |
| [Qwen1.5-0.5B-Chat-SFT-MCQA.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/attention-avengers_-_Qwen1.5-0.5B-Chat-SFT-MCQA-gguf/blob/main/Qwen1.5-0.5B-Chat-SFT-MCQA.IQ3_XS.gguf) | IQ3_XS | 0.24GB |
| [Qwen1.5-0.5B-Chat-SFT-MCQA.IQ3_S.gguf](https://huggingface.co/RichardErkhov/attention-avengers_-_Qwen1.5-0.5B-Chat-SFT-MCQA-gguf/blob/main/Qwen1.5-0.5B-Chat-SFT-MCQA.IQ3_S.gguf) | IQ3_S | 0.25GB |
| [Qwen1.5-0.5B-Chat-SFT-MCQA.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/attention-avengers_-_Qwen1.5-0.5B-Chat-SFT-MCQA-gguf/blob/main/Qwen1.5-0.5B-Chat-SFT-MCQA.Q3_K_S.gguf) | Q3_K_S | 0.25GB |
| [Qwen1.5-0.5B-Chat-SFT-MCQA.IQ3_M.gguf](https://huggingface.co/RichardErkhov/attention-avengers_-_Qwen1.5-0.5B-Chat-SFT-MCQA-gguf/blob/main/Qwen1.5-0.5B-Chat-SFT-MCQA.IQ3_M.gguf) | IQ3_M | 0.26GB |
| [Qwen1.5-0.5B-Chat-SFT-MCQA.Q3_K.gguf](https://huggingface.co/RichardErkhov/attention-avengers_-_Qwen1.5-0.5B-Chat-SFT-MCQA-gguf/blob/main/Qwen1.5-0.5B-Chat-SFT-MCQA.Q3_K.gguf) | Q3_K | 0.26GB |
| [Qwen1.5-0.5B-Chat-SFT-MCQA.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/attention-avengers_-_Qwen1.5-0.5B-Chat-SFT-MCQA-gguf/blob/main/Qwen1.5-0.5B-Chat-SFT-MCQA.Q3_K_M.gguf) | Q3_K_M | 0.26GB |
| [Qwen1.5-0.5B-Chat-SFT-MCQA.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/attention-avengers_-_Qwen1.5-0.5B-Chat-SFT-MCQA-gguf/blob/main/Qwen1.5-0.5B-Chat-SFT-MCQA.Q3_K_L.gguf) | Q3_K_L | 0.28GB |
| [Qwen1.5-0.5B-Chat-SFT-MCQA.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/attention-avengers_-_Qwen1.5-0.5B-Chat-SFT-MCQA-gguf/blob/main/Qwen1.5-0.5B-Chat-SFT-MCQA.IQ4_XS.gguf) | IQ4_XS | 0.28GB |
| [Qwen1.5-0.5B-Chat-SFT-MCQA.Q4_0.gguf](https://huggingface.co/RichardErkhov/attention-avengers_-_Qwen1.5-0.5B-Chat-SFT-MCQA-gguf/blob/main/Qwen1.5-0.5B-Chat-SFT-MCQA.Q4_0.gguf) | Q4_0 | 0.29GB |
| [Qwen1.5-0.5B-Chat-SFT-MCQA.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/attention-avengers_-_Qwen1.5-0.5B-Chat-SFT-MCQA-gguf/blob/main/Qwen1.5-0.5B-Chat-SFT-MCQA.IQ4_NL.gguf) | IQ4_NL | 0.29GB |
| [Qwen1.5-0.5B-Chat-SFT-MCQA.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/attention-avengers_-_Qwen1.5-0.5B-Chat-SFT-MCQA-gguf/blob/main/Qwen1.5-0.5B-Chat-SFT-MCQA.Q4_K_S.gguf) | Q4_K_S | 0.29GB |
| [Qwen1.5-0.5B-Chat-SFT-MCQA.Q4_K.gguf](https://huggingface.co/RichardErkhov/attention-avengers_-_Qwen1.5-0.5B-Chat-SFT-MCQA-gguf/blob/main/Qwen1.5-0.5B-Chat-SFT-MCQA.Q4_K.gguf) | Q4_K | 0.3GB |
| [Qwen1.5-0.5B-Chat-SFT-MCQA.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/attention-avengers_-_Qwen1.5-0.5B-Chat-SFT-MCQA-gguf/blob/main/Qwen1.5-0.5B-Chat-SFT-MCQA.Q4_K_M.gguf) | Q4_K_M | 0.3GB |
| [Qwen1.5-0.5B-Chat-SFT-MCQA.Q4_1.gguf](https://huggingface.co/RichardErkhov/attention-avengers_-_Qwen1.5-0.5B-Chat-SFT-MCQA-gguf/blob/main/Qwen1.5-0.5B-Chat-SFT-MCQA.Q4_1.gguf) | Q4_1 | 0.3GB |
| [Qwen1.5-0.5B-Chat-SFT-MCQA.Q5_0.gguf](https://huggingface.co/RichardErkhov/attention-avengers_-_Qwen1.5-0.5B-Chat-SFT-MCQA-gguf/blob/main/Qwen1.5-0.5B-Chat-SFT-MCQA.Q5_0.gguf) | Q5_0 | 0.32GB |
| [Qwen1.5-0.5B-Chat-SFT-MCQA.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/attention-avengers_-_Qwen1.5-0.5B-Chat-SFT-MCQA-gguf/blob/main/Qwen1.5-0.5B-Chat-SFT-MCQA.Q5_K_S.gguf) | Q5_K_S | 0.32GB |
| [Qwen1.5-0.5B-Chat-SFT-MCQA.Q5_K.gguf](https://huggingface.co/RichardErkhov/attention-avengers_-_Qwen1.5-0.5B-Chat-SFT-MCQA-gguf/blob/main/Qwen1.5-0.5B-Chat-SFT-MCQA.Q5_K.gguf) | Q5_K | 0.33GB |
| [Qwen1.5-0.5B-Chat-SFT-MCQA.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/attention-avengers_-_Qwen1.5-0.5B-Chat-SFT-MCQA-gguf/blob/main/Qwen1.5-0.5B-Chat-SFT-MCQA.Q5_K_M.gguf) | Q5_K_M | 0.33GB |
| [Qwen1.5-0.5B-Chat-SFT-MCQA.Q5_1.gguf](https://huggingface.co/RichardErkhov/attention-avengers_-_Qwen1.5-0.5B-Chat-SFT-MCQA-gguf/blob/main/Qwen1.5-0.5B-Chat-SFT-MCQA.Q5_1.gguf) | Q5_1 | 0.34GB |
| [Qwen1.5-0.5B-Chat-SFT-MCQA.Q6_K.gguf](https://huggingface.co/RichardErkhov/attention-avengers_-_Qwen1.5-0.5B-Chat-SFT-MCQA-gguf/blob/main/Qwen1.5-0.5B-Chat-SFT-MCQA.Q6_K.gguf) | Q6_K | 0.36GB |
| [Qwen1.5-0.5B-Chat-SFT-MCQA.Q8_0.gguf](https://huggingface.co/RichardErkhov/attention-avengers_-_Qwen1.5-0.5B-Chat-SFT-MCQA-gguf/blob/main/Qwen1.5-0.5B-Chat-SFT-MCQA.Q8_0.gguf) | Q8_0 | 0.47GB |
Original model description:
Entry not found
|
Helsinki-NLP/opus-mt-zh-de | Helsinki-NLP | "2023-08-16T12:09:09Z" | 1,677 | 0 | transformers | [
"transformers",
"pytorch",
"tf",
"marian",
"text2text-generation",
"translation",
"zh",
"de",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | translation | "2022-03-02T23:29:04Z" | ---
language:
- zh
- de
tags:
- translation
license: apache-2.0
---
### zho-deu
* source group: Chinese
* target group: German
* OPUS readme: [zho-deu](https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/zho-deu/README.md)
* model: transformer-align
* source language(s): cmn cmn_Bopo cmn_Hang cmn_Hani cmn_Hira cmn_Kana cmn_Latn lzh_Hani wuu_Hani yue_Hani
* target language(s): deu
* model: transformer-align
* pre-processing: normalization + SentencePiece (spm32k,spm32k)
* download original weights: [opus-2020-06-17.zip](https://object.pouta.csc.fi/Tatoeba-MT-models/zho-deu/opus-2020-06-17.zip)
* test set translations: [opus-2020-06-17.test.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/zho-deu/opus-2020-06-17.test.txt)
* test set scores: [opus-2020-06-17.eval.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/zho-deu/opus-2020-06-17.eval.txt)
## Benchmarks
| testset | BLEU | chr-F |
|-----------------------|-------|-------|
| Tatoeba-test.zho.deu | 32.1 | 0.522 |
### System Info:
- hf_name: zho-deu
- source_languages: zho
- target_languages: deu
- opus_readme_url: https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/zho-deu/README.md
- original_repo: Tatoeba-Challenge
- tags: ['translation']
- languages: ['zh', 'de']
- src_constituents: {'cmn_Hans', 'nan', 'nan_Hani', 'gan', 'yue', 'cmn_Kana', 'yue_Hani', 'wuu_Bopo', 'cmn_Latn', 'yue_Hira', 'cmn_Hani', 'cjy_Hans', 'cmn', 'lzh_Hang', 'lzh_Hira', 'cmn_Hant', 'lzh_Bopo', 'zho', 'zho_Hans', 'zho_Hant', 'lzh_Hani', 'yue_Hang', 'wuu', 'yue_Kana', 'wuu_Latn', 'yue_Bopo', 'cjy_Hant', 'yue_Hans', 'lzh', 'cmn_Hira', 'lzh_Yiii', 'lzh_Hans', 'cmn_Bopo', 'cmn_Hang', 'hak_Hani', 'cmn_Yiii', 'yue_Hant', 'lzh_Kana', 'wuu_Hani'}
- tgt_constituents: {'deu'}
- src_multilingual: False
- tgt_multilingual: False
- prepro: normalization + SentencePiece (spm32k,spm32k)
- url_model: https://object.pouta.csc.fi/Tatoeba-MT-models/zho-deu/opus-2020-06-17.zip
- url_test_set: https://object.pouta.csc.fi/Tatoeba-MT-models/zho-deu/opus-2020-06-17.test.txt
- src_alpha3: zho
- tgt_alpha3: deu
- short_pair: zh-de
- chrF2_score: 0.522
- bleu: 32.1
- brevity_penalty: 0.9540000000000001
- ref_len: 19102.0
- src_name: Chinese
- tgt_name: German
- train_date: 2020-06-17
- src_alpha2: zh
- tgt_alpha2: de
- prefer_old: False
- long_pair: zho-deu
- helsinki_git_sha: 480fcbe0ee1bf4774bcbe6226ad9f58e63f6c535
- transformers_git_sha: 2207e5d8cb224e954a7cba69fa4ac2309e9ff30b
- port_machine: brutasse
- port_time: 2020-08-21-14:41 |
marcopost-it/biobert-it | marcopost-it | "2022-02-16T14:15:27Z" | 1,677 | 0 | transformers | [
"transformers",
"pytorch",
"bert",
"fill-mask",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | fill-mask | "2022-03-02T23:29:05Z" | Hi!
This model has been trained on Italian biomedical data.
For further information, do not hesitate to send me a message! ;)
[email protected] (Marco Postiglione) |
nvidia/stt_it_conformer_ctc_large | nvidia | "2022-10-29T00:16:48Z" | 1,677 | 1 | nemo | [
"nemo",
"automatic-speech-recognition",
"speech",
"audio",
"CTC",
"Conformer",
"Transformer",
"pytorch",
"NeMo",
"hf-asr-leaderboard",
"Riva",
"it",
"dataset:facebook/voxpopuli",
"dataset:facebook/multilingual_librispeech",
"dataset:mozilla-foundation/common_voice_11_0",
"arxiv:2005.08100",
"license:cc-by-4.0",
"model-index",
"region:us"
] | automatic-speech-recognition | "2022-10-24T21:09:43Z" | ---
language:
- it
library_name: nemo
datasets:
- facebook/voxpopuli
- facebook/multilingual_librispeech
- mozilla-foundation/common_voice_11_0
thumbnail: null
tags:
- automatic-speech-recognition
- speech
- audio
- CTC
- Conformer
- Transformer
- pytorch
- NeMo
- hf-asr-leaderboard
- Riva
license: cc-by-4.0
model-index:
- name: stt_it_conformer_ctc_large
results:
- task:
type: Automatic Speech Recognition
name: speech-recognition
dataset:
name: common-voice-11-0
type: mozilla-foundation/common_voice_11_0
config: it
split: dev
args:
language: it
metrics:
- name: Dev WER
type: wer
value: 5.38
- task:
type: Automatic Speech Recognition
name: speech-recognition
dataset:
name: common-voice-11-0
type: mozilla-foundation/common_voice_11_0
config: it
split: test
args:
language: it
metrics:
- name: Test WER
type: wer
value: 5.92
- task:
type: Automatic Speech Recognition
name: automatic-speech-recognition
dataset:
name: Multilingual LibriSpeech
type: facebook/multilingual_librispeech
config: italian
split: dev
args:
language: it
metrics:
- name: Dev WER
type: wer
value: 13.16
- task:
type: Automatic Speech Recognition
name: automatic-speech-recognition
dataset:
name: Multilingual LibriSpeech
type: facebook/multilingual_librispeech
config: italian
split: test
args:
language: it
metrics:
- name: Test WER
type: wer
value: 10.62
- task:
type: Automatic Speech Recognition
name: speech-recognition
dataset:
name: VoxPopuli
type: facebook/voxpopuli
config: it
split: dev
args:
language: it
metrics:
- name: Dev WER
type: wer
value: 13.43
- task:
type: Automatic Speech Recognition
name: speech-recognition
dataset:
name: VoxPopuli
type: facebook/voxpopuli
config: it
split: test
args:
language: it
metrics:
- name: Test WER
type: wer
value: 16.75
---
# NVIDIA Conformer-CTC Large (it)
<style>
img {
display: inline;
}
</style>
| [](#model-architecture)
| [](#model-architecture)
| [](#datasets)
| [](#deployment-with-nvidia-riva) |
This model transcribes speech in lowercase Italian alphabet including spaces, and was trained on a composite dataset comprising of 487 hours of Italian speech. It is a non-autoregressive "large" variant of Conformer, with around 120 million parameters.
See the [model architecture](#model-architecture) section and [NeMo documentation](https://docs.nvidia.com/deeplearning/nemo/user-guide/docs/en/main/asr/models.html#conformer-ctc) for complete architecture details.
It is also compatible with NVIDIA Riva for [production-grade server deployments](#deployment-with-nvidia-riva).
## Usage
The model is available for use in the NeMo toolkit [3], and can be used as a pre-trained checkpoint for inference or for fine-tuning on another dataset.
To train, fine-tune or play with the model you will need to install [NVIDIA NeMo](https://github.com/NVIDIA/NeMo). We recommend you install it after you've installed latest PyTorch version.
```
pip install nemo_toolkit['all']
```
### Automatically instantiate the model
```python
import nemo.collections.asr as nemo_asr
asr_model = nemo_asr.models.EncDecCTCModelBPE.from_pretrained("nvidia/stt_it_conformer_ctc_large")
```
### Transcribing using Python
Simply do:
```
asr_model.transcribe(['sample.wav'])
```
### Transcribing many audio files
```shell
python [NEMO_GIT_FOLDER]/examples/asr/transcribe_speech.py
pretrained_name="nvidia/stt_it_conformer_ctc_large"
audio_dir="<DIRECTORY CONTAINING AUDIO FILES>"
```
### Input
This model accepts 16000 kHz Mono-channel Audio (wav files) as input.
### Output
This model provides transcribed speech as a string for a given audio sample.
## Model Architecture
Conformer-CTC model is a non-autoregressive variant of Conformer model [1] for Automatic Speech Recognition which uses CTC loss/decoding instead of Transducer. You may find more info on the detail of this model here: [Conformer-CTC Model](https://docs.nvidia.com/deeplearning/nemo/user-guide/docs/en/main/asr/models.html#conformer-ctc).
## Training
The NeMo toolkit [3] was used for training these models for over several hundred epochs. These models are trained with this [example script](https://github.com/NVIDIA/NeMo/blob/main/examples/asr/asr_ctc/speech_to_text_ctc_bpe.py) and this [base config](https://github.com/NVIDIA/NeMo/blob/main/examples/asr/conf/conformer/conformer_ctc_bpe.yaml).
The tokenizers for these models were built using the text transcripts of the train set with this [script](https://github.com/NVIDIA/NeMo/blob/main/scripts/tokenizers/process_asr_text_tokenizer.py).
The checkpoint of the language model used as the neural rescorer can be found [here](https://catalog.ngc.nvidia.com/orgs/nvidia/teams/nemo/models/stt_it_conformer_ctc_large/files). To train n-gram language model only the transcriptions from the training dataset was used. You may find more info on how to train and use language models for ASR models here: [ASR Language Modeling](https://docs.nvidia.com/deeplearning/nemo/user-guide/docs/en/main/asr/asr_language_modeling.html)
### Datasets
All the models in this collection are trained on a composite dataset (NeMo ASRSET) comprising of 487 hours of Italian speech:
- Mozilla Common Voice 11.0 (Italian) - 220 hours after data cleaning
- Multilingual LibriSpeech (Italian) - 214 hours after data cleaning
- VoxPopuli transcribed subset (Italian) - 53 hours after data cleaning
## Performance
The list of the available models in this collection is shown in the following table. Performances of the ASR models are reported in terms of Word Error Rate (WER%) with greedy decoding.
| Version | Tokenizer | Vocabulary Size | MCV 11.0 Dev | MCV 11.0 Test | MLS Dev | MLS Test | VoxPopuli Dev | VoxPopuli Test | Train Dataset |
|---------|-----------------------|-----------------|--------------|---------------|---------|----------|---------------|----------------|--------------------|
| 1.13.0 | SentencePiece Unigram | 128 | 6.65 | 7.20 | 14.77 | 11.76 | 14.77 | 18.06 | NeMo ASRSET It 2.0 |
While deploying with [NVIDIA Riva](https://developer.nvidia.com/riva), you can combine this model with external language models to further improve WER. The WER(%) of the latest model with different language modeling techniques are reported in the following table.
| Language Modeling | MCV 11.0 Dev | MCV 11.0 Test | MLS Dev | MLS Test | VoxPopuli Dev | VoxPopuli Test | Comment |
|-------------------|--------------|---------------|---------|----------|---------------|----------------|--------------------------------------------------------|
| N-gram LM | 5.38 | 5.92 | 13.16 | 10.62 | 13.43 | 16.75 | N=5, beam_width=128, n_gram_alpha=2.0, n_gram_beta=2.0 |
## Limitations
Since this model was trained on publicly available speech datasets, the performance of this model might degrade for speech which includes technical terms, or vernacular that the model has not been trained on. The model might also perform worse for accented speech.
## Deployment with NVIDIA Riva
For the best real-time accuracy, latency, and throughput, deploy the model with [NVIDIA Riva](https://developer.nvidia.com/riva), an accelerated speech AI SDK deployable on-prem, in all clouds, multi-cloud, hybrid, at the edge, and embedded.
Additionally, Riva provides:
* World-class out-of-the-box accuracy for the most common languages with model checkpoints trained on proprietary data with hundreds of thousands of GPU-compute hours
* Best in class accuracy with run-time word boosting (e.g., brand and product names) and customization of acoustic model, language model, and inverse text normalization
* Streaming speech recognition, Kubernetes compatible scaling, and Enterprise-grade support
Check out [Riva live demo](https://developer.nvidia.com/riva#demos).
## References
- [1] [Conformer: Convolution-augmented Transformer for Speech Recognition](https://arxiv.org/abs/2005.08100)
- [2] [Google Sentencepiece Tokenizer](https://github.com/google/sentencepiece)
- [3] [NVIDIA NeMo Toolkit](https://github.com/NVIDIA/NeMo)
## Licence
License to use this model is covered by the [CC-BY-4 License](https://creativecommons.org/licenses/by/4.0/legalcode) unless another License/Terms Of Use/EULA is clearly specified. By downloading the public and release version of the model, you accept the terms and conditions of the [CC-BY-4 License](https://creativecommons.org/licenses/by/4.0/legalcode). |
NEU-HAI/mental-alpaca | NEU-HAI | "2023-09-26T06:19:07Z" | 1,677 | 5 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"mental",
"mental health",
"large language model",
"alpaca",
"en",
"arxiv:2307.14385",
"license:cc-by-nc-4.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-08-21T17:32:03Z" | ---
license: cc-by-nc-4.0
language:
- en
tags:
- mental
- mental health
- large language model
- alpaca
---
# Model Card for mental-alpaca
<!-- Provide a quick summary of what the model is/does. -->
This is a fine-tuned large language model for mental health prediction via online text data.
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
We fine-tune an Alpaca model with 4 high-quality text (6 tasks in total) datasets for the mental health prediction scenario: Dreaddit, DepSeverity, SDCNL, and CCRS-Suicide.
We have a separate model, fine-tuned on FLAN-T5-XXL, namely Mental-FLAN-T5, shared [here](https://huggingface.co/NEU-HAI/mental-flan-t5-xxl)
- **Developed by:** Northeastern University Human-Centered AI Lab
- **Model type:** Sequence-to-sequence Text-generation
- **Language(s) (NLP):** English
- **License:** cc-by-nc-4.0
- **Finetuned from model:** https://github.com/tatsu-lab/stanford_alpaca
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** https://github.com/neuhai/Mental-LLM
- **Paper:** https://arxiv.org/abs/2307.14385
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
The model is intended to be used for research purposes only in English.
The model has been fine-tuned for mental health prediction via online text data. Detailed information about the fine-tuning process and prompts can be found in our [paper](https://arxiv.org/abs/2307.14385).
The use of this model should also comply with the restrictions from [stanford_alpaca project](https://github.com/tatsu-lab/stanford_alpaca) and [Llama-2-7b](https://huggingface.co/meta-llama/Llama-2-7b).
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
The out-of-scope use of this model should comply with [stanford_alpaca project](https://github.com/tatsu-lab/stanford_alpaca) and [Llama-2-7b](https://huggingface.co/meta-llama/Llama-2-7b).
## Bias, Risks, and Limitations
The Bias, Risks, and Limitations of this model should also comply with [stanford_alpaca project](https://github.com/tatsu-lab/stanford_alpaca) and [Llama-2-7b](https://huggingface.co/meta-llama/Llama-2-7b).
## How to Get Started with the Model
Use the code below to get started with the model.
```
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("NEU-HAI/Llama-2-7b-alpaca-cleaned")
model = AutoModelForCausalLM.from_pretrained("NEU-HAI/Llama-2-7b-alpaca-cleaned")
```
## Training Details and Evaluation
Detailed information about our work can be found in our [paper](https://arxiv.org/abs/2307.14385).
## Citation
```
@article{xu2023leveraging,
title={Mental-LLM: Leveraging large language models for mental health prediction via online text data},
author={Xu, Xuhai and Yao, Bingshen and Dong, Yuanzhe and Gabriel, Saadia and Yu, Hong and Ghassemi, Marzyeh and Hendler, James and Dey, Anind K and Wang, Dakuo},
journal={arXiv preprint arXiv:2307.14385},
year={2023}
}
```
|
Riiid/sheep-duck-llama-2 | Riiid | "2023-10-13T00:59:55Z" | 1,677 | 35 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"Riiid",
"llama-2",
"en",
"arxiv:2306.02707",
"license:llama2",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-09-06T01:16:43Z" | ---
thumbnail: >-
https://cdn-uploads.huggingface.co/production/uploads/62fb1ef7e8c9c532aa7d19e4/NswB5XPkkOljeRh1xbMmR.png
pipeline_tag: text-generation
license: llama2
language:
- en
library_name: transformers
tags:
- Riiid
- llama-2
---
# sheep-duck-llama-2
<img src = "https://cdn-uploads.huggingface.co/production/uploads/62fb1ef7e8c9c532aa7d19e4/NswB5XPkkOljeRh1xbMmR.png" width="30%" height="30%">
This is a finetuned model from llama-2-70b.
## Model Details
* **Developed by**: [Riiid](https://riiid.com/)
* **Backbone Model**: [LLaMA-2](https://github.com/facebookresearch/llama/tree/main)
* **Library**: [HuggingFace Transformers](https://github.com/huggingface/transformers)
## Dataset Details
### Used Datasets
- Orca-style dataset
- Alpaca-style dataset
### Prompt Template
```
### System:
{System}
### User:
{User}
### Assistant:
{Assistant}
```
## Evaluation
| Metric | Value |
|-----------------------|-------|
| ARC (25-shot) | 72.44 |
| HellaSwag (10-shot) | 87.79 |
| MMLU (5-shot) | 70.74 |
| TruthfulQA (0-shot) | 63.71 |
| Avg. | 73.67 |
## Limitations & Biases:
Llama2 and fine-tuned variants are a new technology that carries risks with use. Testing conducted to date has been in English, and has not covered, nor could it cover all scenarios. For these reasons, as with all LLMs, Llama 2 and any fine-tuned varient's potential outputs cannot be predicted in advance, and the model may in some instances produce inaccurate, biased or other objectionable responses to user prompts. Therefore, before deploying any applications of Llama 2 variants, developers should perform safety testing and tuning tailored to their specific applications of the model.
Please see the Responsible Use Guide available at https://ai.meta.com/llama/responsible-use-guide/
## License Disclaimer:
This model is bound by the license & usage restrictions of the original Llama-2 model. And comes with no warranty or gurantees of any kind.
## Contact Us
- [Riiid](https://riiid.com/)
## Citation:
Please kindly cite using the following BibTeX:
```bibtex
@article{platypus2023,
title={Platypus: Quick, Cheap, and Powerful Refinement of LLMs},
author={Ariel N. Lee and Cole J. Hunter and Nataniel Ruiz},
booktitle={arXiv preprint arxiv:2308.07317},
year={2023}
}
```
```
@misc{mukherjee2023orca,
title={Orca: Progressive Learning from Complex Explanation Traces of GPT-4},
author={Subhabrata Mukherjee and Arindam Mitra and Ganesh Jawahar and Sahaj Agarwal and Hamid Palangi and Ahmed Awadallah},
year={2023},
eprint={2306.02707},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
```
```
@misc{Orca-best,
title = {Orca-best: A filtered version of orca gpt4 dataset.},
author = {Shahul Es},
year = {2023},
publisher = {HuggingFace},
journal = {HuggingFace repository},
howpublished = {\url{https://huggingface.co/datasets/shahules786/orca-best/},
}
```
```
@software{touvron2023llama2,
title={Llama 2: Open Foundation and Fine-Tuned Chat Models},
author={Hugo Touvron, Louis Martin, Kevin Stone, Peter Albert, Amjad Almahairi, Yasmine Babaei, Nikolay Bashlykov, Soumya Batra, Prajjwal Bhargava,
Shruti Bhosale, Dan Bikel, Lukas Blecher, Cristian Canton Ferrer, Moya Chen, Guillem Cucurull, David Esiobu, Jude Fernandes, Jeremy Fu, Wenyin Fu, Brian Fuller,
Cynthia Gao, Vedanuj Goswami, Naman Goyal, Anthony Hartshorn, Saghar Hosseini, Rui Hou, Hakan Inan, Marcin Kardas, Viktor Kerkez Madian Khabsa, Isabel Kloumann,
Artem Korenev, Punit Singh Koura, Marie-Anne Lachaux, Thibaut Lavril, Jenya Lee, Diana Liskovich, Yinghai Lu, Yuning Mao, Xavier Martinet, Todor Mihaylov,
Pushkar Mishra, Igor Molybog, Yixin Nie, Andrew Poulton, Jeremy Reizenstein, Rashi Rungta, Kalyan Saladi, Alan Schelten, Ruan Silva, Eric Michael Smith,
Ranjan Subramanian, Xiaoqing Ellen Tan, Binh Tang, Ross Taylor, Adina Williams, Jian Xiang Kuan, Puxin Xu , Zheng Yan, Iliyan Zarov, Yuchen Zhang, Angela Fan,
Melanie Kambadur, Sharan Narang, Aurelien Rodriguez, Robert Stojnic, Sergey Edunov, Thomas Scialom},
year={2023}
}
``` |
Yukang/Llama-2-13b-longlora-32k-ft | Yukang | "2023-09-25T12:36:06Z" | 1,677 | 8 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"arxiv:2309.12307",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-09-12T10:59:44Z" | # LongLoRA: Efficient Fine-tuning of Long-Context Large Language Models
<font size=6><div align='center' > <a href=http://arxiv.org/abs/2309.12307>**Paper**</a> | <a href="https://huggingface.co/Yukang">**Models**</a> | <a href="https://github.com/dvlab-research/LongLoRA">**Code**</a> </div></font>
**LongLoRA: Efficient Fine-tuning of Long-Context Large Language Models [[Paper](http://arxiv.org/abs/2309.12307)]** <br />
[Yukang Chen](https://scholar.google.com/citations?user=6p0ygKUAAAAJ&hl=en),
[Shengju Qian](https://scholar.google.com/citations?user=QNnWmasAAAAJ),
[Haotian Tang](https://scholar.google.com/citations?user=WxL13BAAAAAJ&hl),
[Xin Lai](https://scholar.google.com/citations?user=tqNDPA4AAAAJ&hl=zh-CN),
[Zhijian Liu](https://scholar.google.com/citations?user=3coYSTUAAAAJ&hl=en),
[Song Han](https://scholar.google.com/citations?user=E0iCaa4AAAAJ&hl=zh-CN),
[Jiaya Jia](https://scholar.google.com/citations?user=XPAkzTEAAAAJ&hl=en)<br />
## Abstract
We present LongLoRA, an efficient fine-tuning approach that extends the context sizes of pre-trained large language models (LLMs), with limited computation cost.
Typically, training LLMs with long context sizes is computationally expensive, requiring extensive training hours and GPU resources.
In this paper, we speed up the context extension of LLMs in two aspects. On the one hand, although dense global attention is needed during inference, fine-tuning the model can be effectively and efficiently done by sparse local attention. The proposed shift short attention effectively enables context extension, leading to non-trivial computation saving with similar performance to fine-tuning with vanilla attention. On the other hand, we find that LoRA for context extension works well under the premise of trainable embedding and normalization. LongLoRA demonstrates strong empirical results on various tasks on LLaMA2 models from 7B/13B to 70B. LongLoRA adopts LLaMA2 7B from 4k context to 100k, or LLaMA2 70B to 32k on a single 8x A100 machine. LongLoRA extends models' context while retaining their original architectures, and is compatible with most existing techniques, like FlashAttention-2. In addition, to make LongLoRA practical, we collect a dataset, LongQA, for supervised fine-tuning. It contains more than 3k long context question-answer pairs. For more details, please refer to the [paper](http://arxiv.org/abs/2309.12307).
## Highlights
**LongLoRA** speed up the context extension of pre-trained large language models in both attention-level and weight-level.
1. The proposed shifted short attention is easy to implement, compatible with Flash-Attention, and not required during inference.
2. We release all our models, including models from 7B to 70B, context length from 8k to 100k, including [LLaMA2-LongLoRA-7B-100k](https://huggingface.co/Yukang/Llama-2-7b-longlora-100k-ft), [LLaMA2-LongLoRA-13B-64k](https://huggingface.co/Yukang/Llama-2-13b-longlora-64k), and [LLaMA2-LongLoRA-70B-32k](https://huggingface.co/Yukang/Llama-2-70b-longlora-32k).
3. We build up a long-context QA dataset, LongQA, for supervised fine-tuning (SFT). We release 13B and 70B 32k models with SFT, [Llama-2-13b-chat-longlora-32k-sft](https://huggingface.co/Yukang/Llama-2-13b-chat-longlora-32k-sft) and [Llama-2-70b-chat-longlora-32k-sft](https://huggingface.co/Yukang/Llama-2-70b-chat-longlora-32k-sft). We will further release the dataset next week.
## Released models
### Models with supervised fine-tuning
| Model | Size | Context | Train | Link |
|:----------------------------------|------|---------|---------|-------------------------------------------------------------------------|
| Llama-2-13b-chat-longlora-32k-sft | 13B | 32768 | LoRA+ | [link](https://huggingface.co/Yukang/Llama-2-13b-chat-longlora-32k-sft) |
| Llama-2-70b-chat-longlora-32k-sft | 70B | 32768 | LoRA+ | [link](https://huggingface.co/Yukang/Llama-2-70b-chat-longlora-32k-sft) |
### Models with context extension via fully fine-tuning
| Model | Size | Context | Train | Link |
|:----------------------------|------|---------|-------|-------------------------------------------------------------------|
| Llama-2-7b-longlora-8k-ft | 7B | 8192 | Full FT | [link](https://huggingface.co/Yukang/Llama-2-7b-longlora-8k-ft) |
| Llama-2-7b-longlora-16k-ft | 7B | 16384 | Full FT | [link](https://huggingface.co/Yukang/Llama-2-7b-longlora-16k-ft) |
| Llama-2-7b-longlora-32k-ft | 7B | 32768 | Full FT | [link](https://huggingface.co/Yukang/Llama-2-7b-longlora-32k-ft) |
| Llama-2-7b-longlora-100k-ft | 7B | 100000 | Full FT | [link](https://huggingface.co/Yukang/Llama-2-7b-longlora-100k-ft) |
| Llama-2-13b-longlora-8k-ft | 13B | 8192 | Full FT | [link](https://huggingface.co/Yukang/Llama-2-13b-longlora-8k-ft) |
| Llama-2-13b-longlora-16k-ft | 13B | 16384 | Full FT | [link](https://huggingface.co/Yukang/Llama-2-13b-longlora-16k-ft) |
| Llama-2-13b-longlora-32k-ft | 13B | 32768 | Full FT | [link](https://huggingface.co/Yukang/Llama-2-13b-longlora-32k-ft) |
### Models with context extension via improved LoRA fine-tuning
| Model | Size | Context | Train | Link |
|:----------------------------|------|---------|-------|-------------------------------------------------------------------|
| Llama-2-7b-longlora-8k | 7B | 8192 | LoRA+ | [link](https://huggingface.co/Yukang/Llama-2-7b-longlora-8k) |
| Llama-2-7b-longlora-16k | 7B | 16384 | LoRA+ | [link](https://huggingface.co/Yukang/Llama-2-7b-longlora-16k) |
| Llama-2-7b-longlora-32k | 7B | 32768 | LoRA+ | [link](https://huggingface.co/Yukang/Llama-2-7b-longlora-32k) |
| Llama-2-13b-longlora-8k | 13B | 8192 | LoRA+ | [link](https://huggingface.co/Yukang/Llama-2-13b-longlora-8k) |
| Llama-2-13b-longlora-16k | 13B | 16384 | LoRA+ | [link](https://huggingface.co/Yukang/Llama-2-13b-longlora-16k) |
| Llama-2-13b-longlora-32k | 13B | 32768 | LoRA+ | [link](https://huggingface.co/Yukang/Llama-2-13b-longlora-32k) |
| Llama-2-13b-longlora-64k | 13B | 65536 | LoRA+ | [link](https://huggingface.co/Yukang/Llama-2-13b-longlora-64k) |
| Llama-2-70b-longlora-32k | 70B | 32768 | LoRA+ | [link](https://huggingface.co/Yukang/Llama-2-70b-longlora-32k) |
| Llama-2-70b-chat-longlora-32k | 70B | 32768 | LoRA+ | [link](https://huggingface.co/Yukang/Llama-2-70b-chat-longlora-32k) |
## Citation
If you find this project useful in your research, please consider citing:
```
@article{longlora,
title={LongLoRA: Efficient Fine-tuning of Long-Context Large Language Models},
author={Yukang Chen and Shengju Qian and Haotian Tang and Xin Lai and Zhijian Liu and Song Han and Jiaya Jia},
journal={arXiv:2309.12307},
year={2023}
}
```
## Acknowledgement
- This work is built upon the [LLaMA2](https://ai.meta.com/llama) as the pre-trained models.
- This work is based on [DeepSpeed](https://github.com/microsoft/DeepSpeed), [peft](https://github.com/huggingface/peft), and [Flash-Attention2](https://github.com/Dao-AILab/flash-attention) for acceleration.
- The perplexity evaluation code is modified upon [Landmark Attention](https://github.com/epfml/landmark-attention).
- We use [LongChat](https://github.com/DachengLi1/LongChat) for the retrieval evaluation.
|
ai4bharat/indictrans2-indic-indic-1B | ai4bharat | "2024-05-17T12:37:41Z" | 1,677 | 2 | transformers | [
"transformers",
"pytorch",
"IndicTrans",
"text2text-generation",
"indictrans2",
"translation",
"ai4bharat",
"multilingual",
"custom_code",
"as",
"bn",
"brx",
"doi",
"gom",
"gu",
"hi",
"kn",
"ks",
"mai",
"ml",
"mr",
"mni",
"ne",
"or",
"pa",
"sa",
"sat",
"snd",
"ta",
"te",
"ur",
"dataset:flores-200",
"dataset:IN22-Gen",
"dataset:IN22-Conv",
"license:mit",
"autotrain_compatible",
"region:us"
] | translation | "2023-11-28T17:45:12Z" | ---
language:
- as
- bn
- brx
- doi
- gom
- gu
- hi
- kn
- ks
- mai
- ml
- mr
- mni
- ne
- or
- pa
- sa
- sat
- snd
- ta
- te
- ur
language_details: >-
asm_Beng, ben_Beng, brx_Deva, doi_Deva, gom_Deva, guj_Gujr,
hin_Deva, kan_Knda, kas_Arab, mai_Deva, mal_Mlym, mar_Deva,
mni_Mtei, npi_Deva, ory_Orya, pan_Guru, san_Deva, sat_Olck,
snd_Deva, tam_Taml, tel_Telu, urd_Arab
tags:
- indictrans2
- translation
- ai4bharat
- multilingual
license: mit
datasets:
- flores-200
- IN22-Gen
- IN22-Conv
metrics:
- bleu
- chrf
- chrf++
- comet
inference: false
---
# IndicTrans2
This is the model card of IndicTrans2 Indic-Indic 1B variant adapted after stitching Indic-En 1B and En-Indic 1B variants.
Please refer to the [blog](https://ai4bharat.iitm.ac.in/blog/indictrans2-m2m/) for further details on model training, data and metrics.
### Usage Instructions
Please refer to the [github repository](https://github.com/AI4Bharat/IndicTrans2/tree/main/huggingface_interface) for a detail description on how to use HF compatible IndicTrans2 models for inference.
```python
import torch
from transformers import (
AutoModelForSeq2SeqLM,
AutoTokenizer,
)
from IndicTransTokenizer import IndicProcessor
model_name = "ai4bharat/indictrans2-indic-indic-1B"
tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
model = AutoModelForSeq2SeqLM.from_pretrained(model_name, trust_remote_code=True)
ip = IndicProcessor(inference=True)
input_sentences = [
"जब मैं छोटा था, मैं हर रोज़ पार्क जाता था।",
"हमने पिछले सप्ताह एक नई फिल्म देखी जो कि बहुत प्रेरणादायक थी।",
"अगर तुम मुझे उस समय पास मिलते, तो हम बाहर खाना खाने चलते।",
"मेरे मित्र ने मुझे उसके जन्मदिन की पार्टी में बुलाया है, और मैं उसे एक तोहफा दूंगा।",
]
src_lang, tgt_lang = "hin_Deva", "tam_Taml"
batch = ip.preprocess_batch(
input_sentences,
src_lang=src_lang,
tgt_lang=tgt_lang,
)
DEVICE = "cuda" if torch.cuda.is_available() else "cpu"
# Tokenize the sentences and generate input encodings
inputs = tokenizer(
batch,
truncation=True,
padding="longest",
return_tensors="pt",
return_attention_mask=True,
).to(DEVICE)
# Generate translations using the model
with torch.no_grad():
generated_tokens = model.generate(
**inputs,
use_cache=True,
min_length=0,
max_length=256,
num_beams=5,
num_return_sequences=1,
)
# Decode the generated tokens into text
with tokenizer.as_target_tokenizer():
generated_tokens = tokenizer.batch_decode(
generated_tokens.detach().cpu().tolist(),
skip_special_tokens=True,
clean_up_tokenization_spaces=True,
)
# Postprocess the translations, including entity replacement
translations = ip.postprocess_batch(generated_tokens, lang=tgt_lang)
for input_sentence, translation in zip(input_sentences, translations):
print(f"{src_lang}: {input_sentence}")
print(f"{tgt_lang}: {translation}")
```
**Note: IndicTrans2 is now compatible with AutoTokenizer, however you need to use IndicProcessor from [IndicTransTokenizer](https://github.com/VarunGumma/IndicTransTokenizer) for preprocessing before tokenization.**
### Citation
If you consider using our work then please cite using:
```
@article{gala2023indictrans,
title={IndicTrans2: Towards High-Quality and Accessible Machine Translation Models for all 22 Scheduled Indian Languages},
author={Jay Gala and Pranjal A Chitale and A K Raghavan and Varun Gumma and Sumanth Doddapaneni and Aswanth Kumar M and Janki Atul Nawale and Anupama Sujatha and Ratish Puduppully and Vivek Raghavan and Pratyush Kumar and Mitesh M Khapra and Raj Dabre and Anoop Kunchukuttan},
journal={Transactions on Machine Learning Research},
issn={2835-8856},
year={2023},
url={https://openreview.net/forum?id=vfT4YuzAYA},
note={}
}
``` |
Dampish/StellarX-4B-V0 | Dampish | "2023-12-03T19:52:22Z" | 1,676 | 1 | transformers | [
"transformers",
"pytorch",
"gpt_neox",
"text-generation",
"arxiv:2204.06745",
"license:cc-by-nc-sa-4.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-05-27T19:04:49Z" | ---
license: cc-by-nc-sa-4.0
---
# StellarX: A Base Model by Dampish and Arkane
StellarX is a powerful autoregressive language model designed for various natural language processing tasks. It has been trained on a massive dataset containing 810 billion tokens, trained on "redpajama," and is built upon the popular GPT-NeoX architecture. With approximately 4 billion parameters, StellarX offers exceptional performance and versatility.
## Model Details
- **Training Data:** StellarX is trained on a large-scale dataset provided by "redpajama" maintained by the group "togethercumputer." This dataset has been instrumental in shaping StellarX's language capabilities and general-purpose understanding.
- **Model Architecture:** StellarX is built upon the GPT-NeoX architecture, which may, be, inspired by GPT-3 and shares similarities with GPT-J-6B. The architecture incorporates key advancements in transformer-based language models, ensuring high-quality predictions and contextual understanding.
- **Model Size:** StellarX consists of approximately 4 billion parameters, making it a highly capable language model for a wide range of natural language processing tasks.
- **Carbon-Friendly and Resource-Efficient:** StellarX has been optimized for carbon efficiency and can be comfortably run on local devices. When loaded in 8 bits, the model requires only about 5GB of storage, making it more accessible and convenient for various applications.
- **V0** Meaning what version it is on, currently version 0, Assume version 0 has only been trained on 300B tokens and the goal is 810B tokens. The next version aims to have a way higher accuracy.
## How to Use
To load StellarX using the Hugging Face Transformers library, you can use the following code snippet:
```python
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("Dampish/StellarX-4B-V0")
model = AutoModelForCausalLM.from_pretrained("Dampish/StellarX-4B-V0")
```
This model is particularly beneficial for those seeking a language model that is powerful, compact, and can be run on local devices without a hefty carbon footprint. Remember, when considering Darius1, it's not just about the impressive numbers—it's about what these numbers represent: powerful performance, optimized resources, and responsible computing.
**For any queries related to this model, feel free to reach out to "Dampish#3607" on discord.**
## Licensing and Usage
StellarX, developed by the Dampish, is made available under the Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License (CC-BY-NC-SA-4.0). This license ensures that you can utilize the model for research purposes and personal use without any restrictions, while also promoting the sharing and adaptation of the model under certain conditions.
# Research and Personal Use
StellarX can be freely used for research purposes, allowing you to explore its capabilities, conduct experiments, and develop novel applications. Whether you're a student, researcher, or hobbyist, the model's availability under the CC-BY-NC-SA-4.0 license empowers you to unlock the potential of StellarX for your own non-commercial projects.
# Commercial Usage
For commercial usage of StellarX, an additional licensing arrangement must be established. If you intend to leverage the model for any commercial purpose, such as integrating it into a product or service, you are required to reach an agreement with the Dampish. This agreement will specify the terms, including the agreed-upon percentage or licensing fee to be paid for the commercial use of StellarX.
To initiate discussions regarding commercial usage, please contact Dampish through the designated channels mentioned earlier. They will be able to provide you with further information and guide you through the process of establishing a licensing arrangement tailored to your specific requirements.
# Importance of Licensing Compliance
It is crucial to respect the licensing terms to ensure the fair usage and continued development of StellarX. The revenue generated from commercial licensing supports the efforts of the Dampish in advancing the model and making it more widely accessible.
# Note on CC-BY-NC-SA-4.0
Under the CC-BY-NC-SA-4.0 license, you are allowed to modify and adapt StellarX, incorporating it into your own projects. However, any derivative work or modifications should also be shared under the same license terms, ensuring the continued openness and collaborative spirit of the project.
Please review the complete text of the CC-BY-NC-SA-4.0 license to familiarize yourself with its provisions and requirements. It is essential to comply with the terms of the license to respect the intellectual property rights and contributions of the Dampish and the wider community involved in developing StellarX.
## GPT-NeoX and Model Selection
GPT-NeoX-20B, a sibling model to StellarX, is a 20 billion parameter autoregressive language model trained on the Pile using the GPT-NeoX library. StellarX draws inspiration from the architectural advancements and performance of GPT-NeoX models. While the specifics of StellarX's architecture and parameters may differ, it benefits from the proven capabilities of GPT-NeoX and its suitability for diverse natural language processing tasks.
## Training and Evaluation
StellarX's training dataset comprises a comprehensive collection of English-language texts, covering various domains, thanks to the efforts of "redpajama" dataset by the group "togethercumputer" group.
Evaluation of GPT-NeoX 20B performance has demonstrated its competence across different natural language tasks. Although since this description provides a brief summary, we refer to the GPT-NeoX Paper https://arxiv.org/abs/2204.06745, comparing GPT-NeoX 20B to other models on tasks such as OpenAI's LAMBADA, SciQ, PIQA, TriviaQA, and ARC Challenge.
## Limitations and Considerations
StellarX, like its sibling models, is intended primarily for research purposes. It provides a powerful foundation for extracting useful features and insights from the English language. While StellarX can be further fine-tuned and adapted for deployment, users should conduct their own risk and bias assessments before using it as a basis for downstream tasks.
It's important to note that StellarX is not intended for direct deployment without supervision. It is not designed for human-facing interactions, unlike models like ChatGPT, which have been fine-tuned using reinforcement learning from human feedback to better understand human instructions and dialogue.
Furthermore, StellarX is not limited to the English language if trained properly and can sometimes be used for translation aswell as text generation in other languages.
Lastly, users should be aware of potential biases and limitations inherent in
Special thanks to the group that created the training dataset. The Redpajama dataset, used to train StellarX, thank you togethercumputer.
## Community and Support
To inquire about StellarX and receive support, you can join the Dampish's
server and engage in discussions in the #questions channel. It is recommended to explore the existing documentation and resources available for GPT-NeoX-20B to familiarize yourself with the model before seeking assistance on. For better information about GPT-NeoX, you can reach out to eleutherAI.
## Summary
StellarX, a base language model developed by the Dampish, offers impressive language capabilities and flexibility. Trained on an extensive dataset and built upon the GPT-NeoX architecture, StellarX excels in various natural language processing tasks. Its carbon-friendly and resource-efficient design makes it accessible for local device deployment. Researchers and enthusiasts can freely explore StellarX for research purposes and personal use, while commercial users should adhere to the licensing terms.
**Again i am really grateful for the data made by togethercumputers and their willingness to opensource, they inspired this project and sparked the idea in Stellar-models, i am truly really really grateful to them.
-dampish**
Discord: https://discord.gg/vasyNnUa
OR Reach out to me personally on Discord via the username: Dampish#3607
Thank you for your time.
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_Dampish__StellarX-4B-V0)
| Metric | Value |
|-----------------------|---------------------------|
| Avg. | 33.54 |
| ARC (25-shot) | 36.95 |
| HellaSwag (10-shot) | 61.9 |
| MMLU (5-shot) | 26.85 |
| TruthfulQA (0-shot) | 34.3 |
| Winogrande (5-shot) | 63.85 |
| GSM8K (5-shot) | 0.0 |
| DROP (3-shot) | 10.95 |
|
OptimalScale/robin-65b-v2-delta | OptimalScale | "2023-07-16T02:48:33Z" | 1,676 | 12 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"arxiv:2302.13971",
"arxiv:2306.12420",
"autotrain_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-06-11T06:48:38Z" | ---
inference: false
---
# Robin Model Card
## Model Details
Robin is a series of models finetuned from LLaMA on several high-quality data.
- **Developed by:** [LMFlow](https://github.com/OptimalScale/LMFlow/)
- **Model type:** An auto-regressive language model based on the transformer architecture.
- **License:** Non-commercial license
- **Finetuned from model:** [LLaMA](https://arxiv.org/abs/2302.13971).
### Model Sources
- **Repository:** https://github.com/OptimalScale/LMFlow/
- **Blog:** https://medium.com/@hkust.ml/robin-v2-launches-achieves-unparalleled-performance-on-openllm-4f6886e822c1
- **Paper:** https://arxiv.org/abs/2306.12420
- **Demo:** https://lmflow.com/
## Uses
Robin is primarily utilized for conducting research on extensive language models and chatbots, catering to users specializing in natural language processing, machine learning, and artificial intelligence research.
## How to Get Started with the Model
We provide four kinds of demos including:
- Online Service: If you don't want to run any code and just want to try our models, we deploy our instruction-tuned LLaMA you to have a try.
- Colab Chatbot (shell): An interactive shell-based chatbot for you to easily deploy a chatbot on colab.
- Colab Chatbot (web): An interactive web-based chatbot for you to easily deploy your own chatbot on colab.
- Local Deploy: We also provide a way for you to deploy your model/chatbot locally, which means you can deploy much larger model than previous three methods if you have enough resource.
Please refer to https://github.com/OptimalScale/LMFlow#demos
## Training Details
Expanding upon the initial idea of self-instruct techniques, we incorporated several different data sources and build a new dataset called [LMFlow Dataset](http://lmflow.org:5000/lmflow_data.tar.gz).
The new training split is created by merging the following datasets:
- ShareGPT: randomly sample 50K English data and 10K Chinese data from ShareGPT.
- GPT-4-LLM: 52K English data from GPT-4-LLM.
- BELLE: randomly sample 80K Chinese data from BELLE.
See more details in the "Instruction Tuning" section in our [paper](https://arxiv.org/pdf/2306.12420.pdf).
## Evaluation
Robin is evaluated with [LMFlow Benchmark](https://blog.gopenai.com/lmflow-benchmark-an-automatic-evaluation-framework-for-open-source-llms-ef5c6f142418).
See more details in this [paper](https://arxiv.org/pdf/2306.12420.pdf).
## Citation
If you find this repository useful, please consider giving ⭐ and citing our [paper](https://arxiv.org/abs/2306.12420):
```
@misc{lmflow,
author = {Shizhe Diao and Rui Pan and Hanze Dong and KaShun Shum and Jipeng Zhang and Wei Xiong and Tong Zhang},
title = {LMFlow: An Extensible Toolkit for Finetuning and Inference of Large Foundation Models},
year = {2023},
publisher = {GitHub},
journal = {GitHub repository},
howpublished = {\url{https://optimalscale.github.io/LMFlow/}},
}
``` |
rwitz/dec10 | rwitz | "2024-03-04T13:10:09Z" | 1,676 | 0 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"merge",
"en",
"dataset:Intel/orca_dpo_pairs",
"dataset:athirdpath/DPO_Pairs-Roleplay-Alpaca-NSFW",
"license:cc-by-nc-4.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-12-11T00:16:13Z" | ---
language:
- en
license: cc-by-nc-4.0
tags:
- merge
datasets:
- Intel/orca_dpo_pairs
- athirdpath/DPO_Pairs-Roleplay-Alpaca-NSFW
pipeline_tag: text-generation
model-index:
- name: dec10
results:
- task:
type: text-generation
name: Text Generation
dataset:
name: AI2 Reasoning Challenge (25-Shot)
type: ai2_arc
config: ARC-Challenge
split: test
args:
num_few_shot: 25
metrics:
- type: acc_norm
value: 69.11
name: normalized accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=rwitz/dec10
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: HellaSwag (10-Shot)
type: hellaswag
split: validation
args:
num_few_shot: 10
metrics:
- type: acc_norm
value: 86.46
name: normalized accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=rwitz/dec10
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: MMLU (5-Shot)
type: cais/mmlu
config: all
split: test
args:
num_few_shot: 5
metrics:
- type: acc
value: 64.98
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=rwitz/dec10
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: TruthfulQA (0-shot)
type: truthful_qa
config: multiple_choice
split: validation
args:
num_few_shot: 0
metrics:
- type: mc2
value: 60.42
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=rwitz/dec10
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: Winogrande (5-shot)
type: winogrande
config: winogrande_xl
split: validation
args:
num_few_shot: 5
metrics:
- type: acc
value: 80.74
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=rwitz/dec10
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: GSM8k (5-shot)
type: gsm8k
config: main
split: test
args:
num_few_shot: 5
metrics:
- type: acc
value: 70.58
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=rwitz/dec10
name: Open LLM Leaderboard
---
Slerp Merge of rwitz/go-bruins-v2 and Weyaxi/OpenHermes-2.5-neural-chat-v3-3-Slerp
# Go Bruins V2 - A Fine-tuned Language Model
## Updates
## Overview
**Go Bruins-V2** is a language model fine-tuned on the rwitz/go-bruins architecture. It's designed to push the boundaries of NLP applications, offering unparalleled performance in generating human-like text.
## Model Details
- **Developer:** Ryan Witzman
- **Base Model:** [rwitz/go-bruins](https://huggingface.co/rwitz/go-bruins)
- **Fine-tuning Method:** Direct Preference Optimization (DPO)
- **Training Steps:** 642
- **Language:** English
- **License:** MIT
## Capabilities
Go Bruins excels in a variety of NLP tasks, including but not limited to:
- Text generation
- Language understanding
- Sentiment analysis
## Usage
**Warning:** This model may output NSFW or illegal content. Use with caution and at your own risk.
### For Direct Use:
```python
from transformers import pipeline
model_name = "rwitz/go-bruins-v2"
inference_pipeline = pipeline('text-generation', model=model_name)
input_text = "Your input text goes here"
output = inference_pipeline(input_text)
print(output)
```
### Not Recommended For:
- Illegal activities
- Harassment
- Professional advice or crisis situations
## Training and Evaluation
Trained on a dataset from [athirdpath/DPO_Pairs-Roleplay-Alpaca-NSFW](https://huggingface.co/datasets/athirdpath/DPO_Pairs-Roleplay-Alpaca-NSFW), Go Bruins V2 has shown promising improvements over its predecessor, Go Bruins.
# Evaluations
| Metric | Average | Arc Challenge | Hella Swag | MMLU | Truthful Q&A | Winogrande | GSM8k |
|---------------|---------|---------------|------------|------|--------------|------------|-------|
| **Score** | ?? | ??.8 | ??.05| ??.75 | ??.7 | ??.45 | ??.67 |
Note: The original MMLU evaluation has been corrected to include 5-shot data rather than 1-shot data.
## Contact
For any inquiries or feedback, reach out to Ryan Witzman on Discord: `rwitz_`.
---
## Citations
```
@misc{unacybertron7b,
title={Cybertron: Uniform Neural Alignment},
author={Xavier Murias},
year={2023},
publisher = {HuggingFace},
journal = {HuggingFace repository},
howpublished = {\url{https://huggingface.co/fblgit/una-cybertron-7b-v2-bf16}},
}
```
*This model card was created with care by Ryan Witzman.*
rewrite this model card for new version called go-bruins-v2 that is finetuned on dpo on the original go-bruins model on athirdpath/DPO_Pairs-Roleplay-Alpaca-NSFW
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_rwitz__dec10)
| Metric |Value|
|---------------------------------|----:|
|Avg. |72.05|
|AI2 Reasoning Challenge (25-Shot)|69.11|
|HellaSwag (10-Shot) |86.46|
|MMLU (5-Shot) |64.98|
|TruthfulQA (0-shot) |60.42|
|Winogrande (5-shot) |80.74|
|GSM8k (5-shot) |70.58|
|
Lewdiculous/Kunoichi-DPO-v2-7B-GGUF-Imatrix | Lewdiculous | "2024-05-04T14:47:05Z" | 1,676 | 31 | transformers | [
"transformers",
"gguf",
"mistral",
"quantized",
"text-generation-inference",
"text-generation",
"base_model:SanjiWatsuki/Kunoichi-DPO-v2-7B",
"license:cc-by-nc-4.0",
"region:us"
] | text-generation | "2024-02-27T10:16:40Z" | ---
base_model:
- SanjiWatsuki/Kunoichi-DPO-v2-7B
library_name: transformers
tags:
- mistral
- quantized
- text-generation-inference
pipeline_tag: text-generation
inference: false
license: cc-by-nc-4.0
---
> [!TIP]
> **Support:** <br>
> My upload speeds have been cooked and unstable lately. <br>
> Realistically I'd need to move to get a better provider. <br>
> If you **want** and you are able to... <br>
> [**You can support my various endeavors here (Ko-fi).**](https://ko-fi.com/Lewdiculous) <br>
> I apologize for disrupting your experience.
# **GGUF-Imatrix quantizations for [SanjiWatsuki/Kunoichi-DPO-v2-7B](https://huggingface.co/SanjiWatsuki/Kunoichi-DPO-v2-7B/).**
# What does "Imatrix" mean?
It stands for **Importance Matrix**, a technique used to improve the quality of quantized models.
The **Imatrix** is calculated based on calibration data, and it helps determine the importance of different model activations during the quantization process. The idea is to preserve the most important information during quantization, which can help reduce the loss of model performance.
One of the benefits of using an Imatrix is that it can lead to better model performance, especially when the calibration data is diverse.
More information: [[1]](https://github.com/ggerganov/llama.cpp/discussions/5006) [[2]](https://github.com/ggerganov/llama.cpp/discussions/5263#discussioncomment-8395384)
*If you want any specific quantization to be added, feel free to ask.*
All credits belong to the [creator](https://huggingface.co/SanjiWatsuki/).
`Base⇢ GGUF(F16)⇢ Imatrix-Data(F16)⇢ GGUF(Imatrix-Quants)`
<!-- The new **IQ3_S** quant-option has shown to be better than the old Q3_K_S, so I added that instead of the later. Only supported in `koboldcpp-1.59.1` or higher. -->
Using [llama.cpp](https://github.com/ggerganov/llama.cpp/)-[b2277](https://github.com/ggerganov/llama.cpp/releases/tag/b2277).
For --imatrix data, `imatrix-Kunoichi-DPO-v2-7B-F16.dat` was used.
# Waifu card:
# Original model information:
| Model | MT Bench | EQ Bench | MMLU | Logic Test |
|----------------------|----------|----------|---------|-------------|
| GPT-4-Turbo | 9.32 | - | - | - |
| GPT-4 | 8.99 | 62.52 | 86.4 | 0.86 |
| **Kunoichi-DPO-v2-7B** | **8.51** | **42.18** | **64.94**| **0.58** |
| Mixtral-8x7B-Instruct| 8.30 | 44.81 | 70.6 | 0.75 |
| **Kunoichi-DPO-7B** | **8.29** | **41.60** | **64.83** | **0.59** |
| **Kunoichi-7B** | **8.14** | **44.32** | **64.9** | **0.58** |
| Starling-7B | 8.09 | - | 63.9 | 0.51 |
| Claude-2 | 8.06 | 52.14 | 78.5 | - |
| Silicon-Maid-7B | 7.96 | 40.44 | 64.7 | 0.54 |
| Loyal-Macaroni-Maid-7B | 7.95 | 38.66 | 64.9 | 0.57 |
| GPT-3.5-Turbo | 7.94 | 50.28 | 70 | 0.57 |
| Claude-1 | 7.9 | - | 77 | - |
| Openchat-3.5 | 7.81 | 37.08 | 64.3 | 0.39 |
| Dolphin-2.6-DPO | 7.74 | 42.88 | 61.9 | 0.53 |
| Zephyr-7B-beta | 7.34 | 38.71 | 61.4 | 0.30 |
| Llama-2-70b-chat-hf | 6.86 | 51.56 | 63 | - |
| Neural-chat-7b-v3-1 | 6.84 | 43.61 | 62.4 | 0.30 |
| Model | Average | AGIEval | GPT4All | TruthfulQA | Bigbench |
|---|---:|---:|---:|---:|---:|
| **Kunoichi-DPO-7B**|**58.4**| 45.08 | 74| 66.99| 47.52|
| **Kunoichi-DPO-v2-7B**|**58.31**| 44.85| 75.05| 65.69| 47.65|
| [Kunoichi-7B](https://huggingface.co/SanjiWatsuki/Kunoichi-7B)|57.54| 44.99| 74.86| 63.72| 46.58|
| [OpenPipe/mistral-ft-optimized-1218](https://huggingface.co/OpenPipe/mistral-ft-optimized-1218)| 56.85 | 44.74 | 75.6 | 59.89 | 47.17 |
| [Silicon-Maid-7B](https://huggingface.co/SanjiWatsuki/Silicon-Maid-7B) | 56.45| 44.74| 74.26| 61.5| 45.32|
| [mlabonne/NeuralHermes-2.5-Mistral-7B](https://huggingface.co/mlabonne/NeuralHermes-2.5-Mistral-7B) | 53.51 | 43.67 | 73.24 | 55.37 | 41.76 |
| [teknium/OpenHermes-2.5-Mistral-7B](https://huggingface.co/teknium/OpenHermes-2.5-Mistral-7B) | 52.42 | 42.75 | 72.99 | 52.99 | 40.94 |
| [openchat/openchat_3.5](https://huggingface.co/openchat/openchat_3.5) | 51.34 | 42.67 | 72.92 | 47.27 | 42.51 |
| [berkeley-nest/Starling-LM-7B-alpha](https://huggingface.co/berkeley-nest/Starling-LM-7B-alpha) | 51.16 | 42.06 | 72.72 | 47.33 | 42.53 |
| [HuggingFaceH4/zephyr-7b-beta](https://huggingface.co/HuggingFaceH4/zephyr-7b-beta) | 50.99 | 37.33 | 71.83 | 55.1 | 39.7 |
| Model | AlpacaEval2 | Length |
| --------------------------- | ----------- | ------ |
| GPT-4 | 23.58% | 1365 |
| GPT-4 0314 | 22.07% | 1371 |
| Mistral Medium | 21.86% | 1500 |
| Mixtral 8x7B v0.1 | 18.26% | 1465 |
| **Kunoichi-DPO-v2** | **17.19%** | 1785 |
| Claude 2 | 17.19% | 1069 |
| Claude | 16.99% | 1082 |
| Gemini Pro | 16.85% | 1315 |
| GPT-4 0613 | 15.76% | 1140 |
| Claude 2.1 | 15.73% | 1096 |
| Mistral 7B v0.2 | 14.72% | 1676 |
| GPT 3.5 Turbo 0613 | 14.13% | 1328 |
| LLaMA2 Chat 70B | 13.87% | 1790 |
| LMCocktail-10.7B-v1 | 13.15% | 1203 |
| WizardLM 13B V1.1 | 11.23% | 1525 |
| Zephyr 7B Beta | 10.99% | 1444 |
| OpenHermes-2.5-Mistral (7B) | 10.34% | 1107 |
| GPT 3.5 Turbo 0301 | 9.62% | 827 |
| **Kunoichi-7B** | **9.38%** | 1492 |
| GPT 3.5 Turbo 1106 | 9.18% | 796 |
| GPT-3.5 | 8.56% | 1018 |
| Phi-2 DPO | 7.76% | 1687 |
| LLaMA2 Chat 13B | 7.70% | 1513 | |
MaziyarPanahi/mergekit-slerp-tzunwnr-GGUF | MaziyarPanahi | "2024-06-16T21:07:40Z" | 1,676 | 0 | transformers | [
"transformers",
"gguf",
"mistral",
"quantized",
"2-bit",
"3-bit",
"4-bit",
"5-bit",
"6-bit",
"8-bit",
"GGUF",
"safetensors",
"text-generation",
"mergekit",
"merge",
"conversational",
"base_model:meta-llama/Meta-Llama-3-8B",
"base_model:NousResearch/Hermes-2-Pro-Mistral-7B",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us",
"base_model:mergekit-community/mergekit-slerp-tzunwnr"
] | text-generation | "2024-06-16T20:41:43Z" | ---
tags:
- quantized
- 2-bit
- 3-bit
- 4-bit
- 5-bit
- 6-bit
- 8-bit
- GGUF
- transformers
- safetensors
- mistral
- text-generation
- mergekit
- merge
- conversational
- base_model:meta-llama/Meta-Llama-3-8B
- base_model:NousResearch/Hermes-2-Pro-Mistral-7B
- autotrain_compatible
- endpoints_compatible
- text-generation-inference
- region:us
- text-generation
model_name: mergekit-slerp-tzunwnr-GGUF
base_model: mergekit-community/mergekit-slerp-tzunwnr
inference: false
model_creator: mergekit-community
pipeline_tag: text-generation
quantized_by: MaziyarPanahi
---
# [MaziyarPanahi/mergekit-slerp-tzunwnr-GGUF](https://huggingface.co/MaziyarPanahi/mergekit-slerp-tzunwnr-GGUF)
- Model creator: [mergekit-community](https://huggingface.co/mergekit-community)
- Original model: [mergekit-community/mergekit-slerp-tzunwnr](https://huggingface.co/mergekit-community/mergekit-slerp-tzunwnr)
## Description
[MaziyarPanahi/mergekit-slerp-tzunwnr-GGUF](https://huggingface.co/MaziyarPanahi/mergekit-slerp-tzunwnr-GGUF) contains GGUF format model files for [mergekit-community/mergekit-slerp-tzunwnr](https://huggingface.co/mergekit-community/mergekit-slerp-tzunwnr).
### About GGUF
GGUF is a new format introduced by the llama.cpp team on August 21st 2023. It is a replacement for GGML, which is no longer supported by llama.cpp.
Here is an incomplete list of clients and libraries that are known to support GGUF:
* [llama.cpp](https://github.com/ggerganov/llama.cpp). The source project for GGUF. Offers a CLI and a server option.
* [llama-cpp-python](https://github.com/abetlen/llama-cpp-python), a Python library with GPU accel, LangChain support, and OpenAI-compatible API server.
* [LM Studio](https://lmstudio.ai/), an easy-to-use and powerful local GUI for Windows and macOS (Silicon), with GPU acceleration. Linux available, in beta as of 27/11/2023.
* [text-generation-webui](https://github.com/oobabooga/text-generation-webui), the most widely used web UI, with many features and powerful extensions. Supports GPU acceleration.
* [KoboldCpp](https://github.com/LostRuins/koboldcpp), a fully featured web UI, with GPU accel across all platforms and GPU architectures. Especially good for story telling.
* [GPT4All](https://gpt4all.io/index.html), a free and open source local running GUI, supporting Windows, Linux and macOS with full GPU accel.
* [LoLLMS Web UI](https://github.com/ParisNeo/lollms-webui), a great web UI with many interesting and unique features, including a full model library for easy model selection.
* [Faraday.dev](https://faraday.dev/), an attractive and easy to use character-based chat GUI for Windows and macOS (both Silicon and Intel), with GPU acceleration.
* [candle](https://github.com/huggingface/candle), a Rust ML framework with a focus on performance, including GPU support, and ease of use.
* [ctransformers](https://github.com/marella/ctransformers), a Python library with GPU accel, LangChain support, and OpenAI-compatible AI server. Note, as of time of writing (November 27th 2023), ctransformers has not been updated in a long time and does not support many recent models.
## Special thanks
🙏 Special thanks to [Georgi Gerganov](https://github.com/ggerganov) and the whole team working on [llama.cpp](https://github.com/ggerganov/llama.cpp/) for making all of this possible. |
dbmdz/bert-medium-historic-multilingual-cased | dbmdz | "2023-09-06T22:19:02Z" | 1,675 | 0 | transformers | [
"transformers",
"pytorch",
"tf",
"tensorboard",
"safetensors",
"bert",
"fill-mask",
"multilingual",
"arxiv:1908.08962",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | fill-mask | "2022-03-02T23:29:05Z" | ---
language: multilingual
license: mit
widget:
- text: "and I cannot conceive the reafon why [MASK] hath"
- text: "Täkäläinen sanomalehdistö [MASK] erit - täin"
- text: "Det vore [MASK] häller nödvändigt att be"
- text: "Comme, à cette époque [MASK] était celle de la"
- text: "In [MASK] an atmosphärischen Nahrungsmitteln"
---
# Historic Language Models (HLMs)
## Languages
Our Historic Language Models Zoo contains support for the following languages - incl. their training data source:
| Language | Training data | Size
| -------- | ------------- | ----
| German | [Europeana](http://www.europeana-newspapers.eu/) | 13-28GB (filtered)
| French | [Europeana](http://www.europeana-newspapers.eu/) | 11-31GB (filtered)
| English | [British Library](https://data.bl.uk/digbks/db14.html) | 24GB (year filtered)
| Finnish | [Europeana](http://www.europeana-newspapers.eu/) | 1.2GB
| Swedish | [Europeana](http://www.europeana-newspapers.eu/) | 1.1GB
## Models
At the moment, the following models are available on the model hub:
| Model identifier | Model Hub link
| --------------------------------------------- | --------------------------------------------------------------------------
| `dbmdz/bert-base-historic-multilingual-cased` | [here](https://huggingface.co/dbmdz/bert-base-historic-multilingual-cased)
| `dbmdz/bert-base-historic-english-cased` | [here](https://huggingface.co/dbmdz/bert-base-historic-english-cased)
| `dbmdz/bert-base-finnish-europeana-cased` | [here](https://huggingface.co/dbmdz/bert-base-finnish-europeana-cased)
| `dbmdz/bert-base-swedish-europeana-cased` | [here](https://huggingface.co/dbmdz/bert-base-swedish-europeana-cased)
We also released smaller models for the multilingual model:
| Model identifier | Model Hub link
| ----------------------------------------------- | ---------------------------------------------------------------------------
| `dbmdz/bert-tiny-historic-multilingual-cased` | [here](https://huggingface.co/dbmdz/bert-tiny-historic-multilingual-cased)
| `dbmdz/bert-mini-historic-multilingual-cased` | [here](https://huggingface.co/dbmdz/bert-mini-historic-multilingual-cased)
| `dbmdz/bert-small-historic-multilingual-cased` | [here](https://huggingface.co/dbmdz/bert-small-historic-multilingual-cased)
| `dbmdz/bert-medium-historic-multilingual-cased` | [here](https://huggingface.co/dbmdz/bert-base-historic-multilingual-cased)
**Notice**: We have released language models for Historic German and French trained on more noisier data earlier - see
[this repo](https://github.com/stefan-it/europeana-bert) for more information:
| Model identifier | Model Hub link
| --------------------------------------------- | --------------------------------------------------------------------------
| `dbmdz/bert-base-german-europeana-cased` | [here](https://huggingface.co/dbmdz/bert-base-german-europeana-cased)
| `dbmdz/bert-base-french-europeana-cased` | [here](https://huggingface.co/dbmdz/bert-base-french-europeana-cased)
# Corpora Stats
## German Europeana Corpus
We provide some statistics using different thresholds of ocr confidences, in order to shrink down the corpus size
and use less-noisier data:
| OCR confidence | Size
| -------------- | ----
| **0.60** | 28GB
| 0.65 | 18GB
| 0.70 | 13GB
For the final corpus we use a OCR confidence of 0.6 (28GB). The following plot shows a tokens per year distribution:
## French Europeana Corpus
Like German, we use different ocr confidence thresholds:
| OCR confidence | Size
| -------------- | ----
| 0.60 | 31GB
| 0.65 | 27GB
| **0.70** | 27GB
| 0.75 | 23GB
| 0.80 | 11GB
For the final corpus we use a OCR confidence of 0.7 (27GB). The following plot shows a tokens per year distribution:
## British Library Corpus
Metadata is taken from [here](https://data.bl.uk/digbks/DB21.html). Stats incl. year filtering:
| Years | Size
| ----------------- | ----
| ALL | 24GB
| >= 1800 && < 1900 | 24GB
We use the year filtered variant. The following plot shows a tokens per year distribution:
## Finnish Europeana Corpus
| OCR confidence | Size
| -------------- | ----
| 0.60 | 1.2GB
The following plot shows a tokens per year distribution:
## Swedish Europeana Corpus
| OCR confidence | Size
| -------------- | ----
| 0.60 | 1.1GB
The following plot shows a tokens per year distribution:
## All Corpora
The following plot shows a tokens per year distribution of the complete training corpus:
# Multilingual Vocab generation
For the first attempt, we use the first 10GB of each pretraining corpus. We upsample both Finnish and Swedish to ~10GB.
The following tables shows the exact size that is used for generating a 32k and 64k subword vocabs:
| Language | Size
| -------- | ----
| German | 10GB
| French | 10GB
| English | 10GB
| Finnish | 9.5GB
| Swedish | 9.7GB
We then calculate the subword fertility rate and portion of `[UNK]`s over the following NER corpora:
| Language | NER corpora
| -------- | ------------------
| German | CLEF-HIPE, NewsEye
| French | CLEF-HIPE, NewsEye
| English | CLEF-HIPE
| Finnish | NewsEye
| Swedish | NewsEye
Breakdown of subword fertility rate and unknown portion per language for the 32k vocab:
| Language | Subword fertility | Unknown portion
| -------- | ------------------ | ---------------
| German | 1.43 | 0.0004
| French | 1.25 | 0.0001
| English | 1.25 | 0.0
| Finnish | 1.69 | 0.0007
| Swedish | 1.43 | 0.0
Breakdown of subword fertility rate and unknown portion per language for the 64k vocab:
| Language | Subword fertility | Unknown portion
| -------- | ------------------ | ---------------
| German | 1.31 | 0.0004
| French | 1.16 | 0.0001
| English | 1.17 | 0.0
| Finnish | 1.54 | 0.0007
| Swedish | 1.32 | 0.0
# Final pretraining corpora
We upsample Swedish and Finnish to ~27GB. The final stats for all pretraining corpora can be seen here:
| Language | Size
| -------- | ----
| German | 28GB
| French | 27GB
| English | 24GB
| Finnish | 27GB
| Swedish | 27GB
Total size is 130GB.
# Smaller multilingual models
Inspired by the ["Well-Read Students Learn Better: On the Importance of Pre-training Compact Models"](https://arxiv.org/abs/1908.08962)
paper, we train smaller models (different layers and hidden sizes), and report number of parameters and pre-training costs:
| Model (Layer / Hidden size) | Parameters | Pre-Training time
| --------------------------- | ----------: | ----------------------:
| hmBERT Tiny ( 2/128) | 4.58M | 4.3 sec / 1,000 steps
| hmBERT Mini ( 4/256) | 11.55M | 10.5 sec / 1,000 steps
| hmBERT Small ( 4/512) | 29.52M | 20.7 sec / 1,000 steps
| hmBERT Medium ( 8/512) | 42.13M | 35.0 sec / 1,000 steps
| hmBERT Base (12/768) | 110.62M | 80.0 sec / 1,000 steps
We then perform downstream evaluations on the multilingual [NewsEye](https://zenodo.org/record/4573313#.Ya3oVr-ZNzU) dataset:
# Pretraining
## Multilingual model - hmBERT Base
We train a multilingual BERT model using the 32k vocab with the official BERT implementation
on a v3-32 TPU using the following parameters:
```bash
python3 run_pretraining.py --input_file gs://histolectra/historic-multilingual-tfrecords/*.tfrecord \
--output_dir gs://histolectra/bert-base-historic-multilingual-cased \
--bert_config_file ./config.json \
--max_seq_length=512 \
--max_predictions_per_seq=75 \
--do_train=True \
--train_batch_size=128 \
--num_train_steps=3000000 \
--learning_rate=1e-4 \
--save_checkpoints_steps=100000 \
--keep_checkpoint_max=20 \
--use_tpu=True \
--tpu_name=electra-2 \
--num_tpu_cores=32
```
The following plot shows the pretraining loss curve:
## Smaller multilingual models
We use the same parameters as used for training the base model.
### hmBERT Tiny
The following plot shows the pretraining loss curve for the tiny model:
### hmBERT Mini
The following plot shows the pretraining loss curve for the mini model:
### hmBERT Small
The following plot shows the pretraining loss curve for the small model:
### hmBERT Medium
The following plot shows the pretraining loss curve for the medium model:
## English model
The English BERT model - with texts from British Library corpus - was trained with the Hugging Face
JAX/FLAX implementation for 10 epochs (approx. 1M steps) on a v3-8 TPU, using the following command:
```bash
python3 run_mlm_flax.py --model_type bert \
--config_name /mnt/datasets/bert-base-historic-english-cased/ \
--tokenizer_name /mnt/datasets/bert-base-historic-english-cased/ \
--train_file /mnt/datasets/bl-corpus/bl_1800-1900_extracted.txt \
--validation_file /mnt/datasets/bl-corpus/english_validation.txt \
--max_seq_length 512 \
--per_device_train_batch_size 16 \
--learning_rate 1e-4 \
--num_train_epochs 10 \
--preprocessing_num_workers 96 \
--output_dir /mnt/datasets/bert-base-historic-english-cased-512-noadafactor-10e \
--save_steps 2500 \
--eval_steps 2500 \
--warmup_steps 10000 \
--line_by_line \
--pad_to_max_length
```
The following plot shows the pretraining loss curve:
## Finnish model
The BERT model - with texts from Finnish part of Europeana - was trained with the Hugging Face
JAX/FLAX implementation for 40 epochs (approx. 1M steps) on a v3-8 TPU, using the following command:
```bash
python3 run_mlm_flax.py --model_type bert \
--config_name /mnt/datasets/bert-base-finnish-europeana-cased/ \
--tokenizer_name /mnt/datasets/bert-base-finnish-europeana-cased/ \
--train_file /mnt/datasets/hlms/extracted_content_Finnish_0.6.txt \
--validation_file /mnt/datasets/hlms/finnish_validation.txt \
--max_seq_length 512 \
--per_device_train_batch_size 16 \
--learning_rate 1e-4 \
--num_train_epochs 40 \
--preprocessing_num_workers 96 \
--output_dir /mnt/datasets/bert-base-finnish-europeana-cased-512-dupe1-noadafactor-40e \
--save_steps 2500 \
--eval_steps 2500 \
--warmup_steps 10000 \
--line_by_line \
--pad_to_max_length
```
The following plot shows the pretraining loss curve:
## Swedish model
The BERT model - with texts from Swedish part of Europeana - was trained with the Hugging Face
JAX/FLAX implementation for 40 epochs (approx. 660K steps) on a v3-8 TPU, using the following command:
```bash
python3 run_mlm_flax.py --model_type bert \
--config_name /mnt/datasets/bert-base-swedish-europeana-cased/ \
--tokenizer_name /mnt/datasets/bert-base-swedish-europeana-cased/ \
--train_file /mnt/datasets/hlms/extracted_content_Swedish_0.6.txt \
--validation_file /mnt/datasets/hlms/swedish_validation.txt \
--max_seq_length 512 \
--per_device_train_batch_size 16 \
--learning_rate 1e-4 \
--num_train_epochs 40 \
--preprocessing_num_workers 96 \
--output_dir /mnt/datasets/bert-base-swedish-europeana-cased-512-dupe1-noadafactor-40e \
--save_steps 2500 \
--eval_steps 2500 \
--warmup_steps 10000 \
--line_by_line \
--pad_to_max_length
```
The following plot shows the pretraining loss curve:
# Acknowledgments
Research supported with Cloud TPUs from Google's TPU Research Cloud (TRC) program, previously known as
TensorFlow Research Cloud (TFRC). Many thanks for providing access to the TRC ❤️
Thanks to the generous support from the [Hugging Face](https://huggingface.co/) team,
it is possible to download both cased and uncased models from their S3 storage 🤗
|
OpenBuddy/openbuddy-openllama-3b-v10-bf16 | OpenBuddy | "2023-08-22T10:51:04Z" | 1,675 | 8 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"zh",
"en",
"fr",
"de",
"ja",
"ko",
"it",
"ru",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-08-10T13:37:46Z" | ---
language:
- zh
- en
- fr
- de
- ja
- ko
- it
- ru
pipeline_tag: text-generation
inference: false
library_name: transformers
license: apache-2.0
---
# OpenBuddy - Open Multilingual Chatbot
GitHub and Usage Guide: [https://github.com/OpenBuddy/OpenBuddy](https://github.com/OpenBuddy/OpenBuddy)
Website and Demo: [https://openbuddy.ai](https://openbuddy.ai)
# Copyright Notice
License: Apache 2.0.
## Disclaimer
All OpenBuddy models have inherent limitations and may potentially produce outputs that are erroneous, harmful, offensive, or otherwise undesirable. Users should not use these models in critical or high-stakes situations that may lead to personal injury, property damage, or significant losses. Examples of such scenarios include, but are not limited to, the medical field, controlling software and hardware systems that may cause harm, and making important financial or legal decisions.
OpenBuddy is provided "as-is" without any warranty of any kind, either express or implied, including, but not limited to, the implied warranties of merchantability, fitness for a particular purpose, and non-infringement. In no event shall the authors, contributors, or copyright holders be liable for any claim, damages, or other liabilities, whether in an action of contract, tort, or otherwise, arising from, out of, or in connection with the software or the use or other dealings in the software.
By using OpenBuddy, you agree to these terms and conditions, and acknowledge that you understand the potential risks associated with its use. You also agree to indemnify and hold harmless the authors, contributors, and copyright holders from any claims, damages, or liabilities arising from your use of OpenBuddy.
## 免责声明
所有OpenBuddy模型均存在固有的局限性，可能产生错误的、有害的、冒犯性的或其他不良的输出。用户在关键或高风险场景中应谨慎行事，不要使用这些模型，以免导致人身伤害、财产损失或重大损失。此类场景的例子包括但不限于医疗领域、可能导致伤害的软硬件系统的控制以及进行重要的财务或法律决策。
OpenBuddy按“原样”提供，不附带任何种类的明示或暗示的保证，包括但不限于适销性、特定目的的适用性和非侵权的暗示保证。在任何情况下，作者、贡献者或版权所有者均不对因软件或使用或其他软件交易而产生的任何索赔、损害赔偿或其他责任（无论是合同、侵权还是其他原因）承担责任。
使用OpenBuddy即表示您同意这些条款和条件，并承认您了解其使用可能带来的潜在风险。您还同意赔偿并使作者、贡献者和版权所有者免受因您使用OpenBuddy而产生的任何索赔、损害赔偿或责任的影响。 |
s3nh/s3nh-nsfw-noromaid-zephyr-GGUF | s3nh | "2024-01-07T13:51:44Z" | 1,675 | 5 | transformers | [
"transformers",
"gguf",
"text-generation",
"zh",
"en",
"license:openrail",
"endpoints_compatible",
"region:us"
] | text-generation | "2024-01-07T13:17:04Z" |
---
license: openrail
pipeline_tag: text-generation
library_name: transformers
language:
- zh
- en
---
## Original model card
Buy me a coffee if you like this project ;)
<a href="https://www.buymeacoffee.com/s3nh"><img src="https://www.buymeacoffee.com/assets/img/guidelines/download-assets-sm-1.svg" alt=""></a>
#### Description
GGUF Format model files for [This project](https://huggingface.co/s3nh/nsfw-noromaid-zephyr).
### GGUF Specs
GGUF is a format based on the existing GGJT, but makes a few changes to the format to make it more extensible and easier to use. The following features are desired:
Single-file deployment: they can be easily distributed and loaded, and do not require any external files for additional information.
Extensible: new features can be added to GGML-based executors/new information can be added to GGUF models without breaking compatibility with existing models.
mmap compatibility: models can be loaded using mmap for fast loading and saving.
Easy to use: models can be easily loaded and saved using a small amount of code, with no need for external libraries, regardless of the language used.
Full information: all information needed to load a model is contained in the model file, and no additional information needs to be provided by the user.
The key difference between GGJT and GGUF is the use of a key-value structure for the hyperparameters (now referred to as metadata), rather than a list of untyped values.
This allows for new metadata to be added without breaking compatibility with existing models, and to annotate the model with additional information that may be useful for
inference or for identifying the model.
### Perplexity params
Model Measure Q2_K Q3_K_S Q3_K_M Q3_K_L Q4_0 Q4_1 Q4_K_S Q4_K_M Q5_0 Q5_1 Q5_K_S Q5_K_M Q6_K Q8_0 F16
7B perplexity 6.7764 6.4571 6.1503 6.0869 6.1565 6.0912 6.0215 5.9601 5.9862 5.9481 5.9419 5.9208 5.9110 5.9070 5.9066
13B perplexity 5.8545 5.6033 5.4498 5.4063 5.3860 5.3608 5.3404 5.3002 5.2856 5.2706 5.2785 5.2638 5.2568 5.2548 5.2543
### inference
TODO
# Original model card
|
TheBloke/CodeLlama-70B-Python-GGUF | TheBloke | "2024-01-31T03:18:21Z" | 1,675 | 31 | transformers | [
"transformers",
"gguf",
"llama",
"llama-2",
"text-generation",
"code",
"arxiv:2308.12950",
"base_model:codellama/CodeLlama-70b-Python-hf",
"license:llama2",
"text-generation-inference",
"region:us"
] | text-generation | "2024-01-30T22:59:59Z" | ---
base_model: codellama/CodeLlama-70b-Python-hf
inference: false
language:
- code
license: llama2
model_creator: Code Llama
model_name: CodeLlama 70B Python
model_type: llama
pipeline_tag: text-generation
prompt_template: '{prompt}
'
quantized_by: TheBloke
tags:
- llama-2
---
<!-- markdownlint-disable MD041 -->
<!-- header start -->
<!-- 200823 -->
<div style="width: auto; margin-left: auto; margin-right: auto">
<img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
</div>
<div style="display: flex; justify-content: space-between; width: 100%;">
<div style="display: flex; flex-direction: column; align-items: flex-start;">
<p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://discord.gg/theblokeai">Chat & support: TheBloke's Discord server</a></p>
</div>
<div style="display: flex; flex-direction: column; align-items: flex-end;">
<p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p>
</div>
</div>
<div style="text-align:center; margin-top: 0em; margin-bottom: 0em"><p style="margin-top: 0.25em; margin-bottom: 0em;">TheBloke's LLM work is generously supported by a grant from <a href="https://a16z.com">andreessen horowitz (a16z)</a></p></div>
<hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
<!-- header end -->
# CodeLlama 70B Python - GGUF
- Model creator: [Code Llama](https://huggingface.co/codellama)
- Original model: [CodeLlama 70B Python](https://huggingface.co/codellama/CodeLlama-70b-Python-hf)
<!-- description start -->
## Description
This repo contains GGUF format model files for [Code Llama's CodeLlama 70B Python](https://huggingface.co/codellama/CodeLlama-70b-Python-hf).
These files were quantised using hardware kindly provided by [Massed Compute](https://massedcompute.com/).
<!-- description end -->
<!-- README_GGUF.md-about-gguf start -->
### About GGUF
GGUF is a new format introduced by the llama.cpp team on August 21st 2023. It is a replacement for GGML, which is no longer supported by llama.cpp.
Here is an incomplete list of clients and libraries that are known to support GGUF:
* [llama.cpp](https://github.com/ggerganov/llama.cpp). The source project for GGUF. Offers a CLI and a server option.
* [text-generation-webui](https://github.com/oobabooga/text-generation-webui), the most widely used web UI, with many features and powerful extensions. Supports GPU acceleration.
* [KoboldCpp](https://github.com/LostRuins/koboldcpp), a fully featured web UI, with GPU accel across all platforms and GPU architectures. Especially good for story telling.
* [GPT4All](https://gpt4all.io/index.html), a free and open source local running GUI, supporting Windows, Linux and macOS with full GPU accel.
* [LM Studio](https://lmstudio.ai/), an easy-to-use and powerful local GUI for Windows and macOS (Silicon), with GPU acceleration. Linux available, in beta as of 27/11/2023.
* [LoLLMS Web UI](https://github.com/ParisNeo/lollms-webui), a great web UI with many interesting and unique features, including a full model library for easy model selection.
* [Faraday.dev](https://faraday.dev/), an attractive and easy to use character-based chat GUI for Windows and macOS (both Silicon and Intel), with GPU acceleration.
* [llama-cpp-python](https://github.com/abetlen/llama-cpp-python), a Python library with GPU accel, LangChain support, and OpenAI-compatible API server.
* [candle](https://github.com/huggingface/candle), a Rust ML framework with a focus on performance, including GPU support, and ease of use.
* [ctransformers](https://github.com/marella/ctransformers), a Python library with GPU accel, LangChain support, and OpenAI-compatible AI server. Note, as of time of writing (November 27th 2023), ctransformers has not been updated in a long time and does not support many recent models.
<!-- README_GGUF.md-about-gguf end -->
<!-- repositories-available start -->
## Repositories available
* [AWQ model(s) for GPU inference.](https://huggingface.co/TheBloke/CodeLlama-70B-Python-AWQ)
* [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/CodeLlama-70B-Python-GPTQ)
* [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/CodeLlama-70B-Python-GGUF)
* [Code Llama's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/codellama/CodeLlama-70b-Python-hf)
<!-- repositories-available end -->
<!-- prompt-template start -->
## Prompt template: None
```
{prompt}
```
<!-- prompt-template end -->
<!-- compatibility_gguf start -->
## Compatibility
These quantised GGUFv2 files are compatible with llama.cpp from August 27th onwards, as of commit [d0cee0d](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221)
They are also compatible with many third party UIs and libraries - please see the list at the top of this README.
## Explanation of quantisation methods
<details>
<summary>Click to see details</summary>
The new methods available are:
* GGML_TYPE_Q2_K - "type-1" 2-bit quantization in super-blocks containing 16 blocks, each block having 16 weight. Block scales and mins are quantized with 4 bits. This ends up effectively using 2.5625 bits per weight (bpw)
* GGML_TYPE_Q3_K - "type-0" 3-bit quantization in super-blocks containing 16 blocks, each block having 16 weights. Scales are quantized with 6 bits. This end up using 3.4375 bpw.
* GGML_TYPE_Q4_K - "type-1" 4-bit quantization in super-blocks containing 8 blocks, each block having 32 weights. Scales and mins are quantized with 6 bits. This ends up using 4.5 bpw.
* GGML_TYPE_Q5_K - "type-1" 5-bit quantization. Same super-block structure as GGML_TYPE_Q4_K resulting in 5.5 bpw
* GGML_TYPE_Q6_K - "type-0" 6-bit quantization. Super-blocks with 16 blocks, each block having 16 weights. Scales are quantized with 8 bits. This ends up using 6.5625 bpw
Refer to the Provided Files table below to see what files use which methods, and how.
</details>
<!-- compatibility_gguf end -->
<!-- README_GGUF.md-provided-files start -->
## Provided files
| Name | Quant method | Bits | Size | Max RAM required | Use case |
| ---- | ---- | ---- | ---- | ---- | ----- |
| [codellama-70b-python.Q2_K.gguf](https://huggingface.co/TheBloke/CodeLlama-70B-Python-GGUF/blob/main/codellama-70b-python.Q2_K.gguf) | Q2_K | 2 | 25.46 GB| 27.96 GB | significant quality loss - not recommended for most purposes |
| [codellama-70b-python.Q3_K_S.gguf](https://huggingface.co/TheBloke/CodeLlama-70B-Python-GGUF/blob/main/codellama-70b-python.Q3_K_S.gguf) | Q3_K_S | 3 | 29.92 GB| 32.42 GB | very small, high quality loss |
| [codellama-70b-python.Q3_K_M.gguf](https://huggingface.co/TheBloke/CodeLlama-70B-Python-GGUF/blob/main/codellama-70b-python.Q3_K_M.gguf) | Q3_K_M | 3 | 33.27 GB| 35.77 GB | very small, high quality loss |
| [codellama-70b-python.Q3_K_L.gguf](https://huggingface.co/TheBloke/CodeLlama-70B-Python-GGUF/blob/main/codellama-70b-python.Q3_K_L.gguf) | Q3_K_L | 3 | 36.15 GB| 38.65 GB | small, substantial quality loss |
| [codellama-70b-python.Q4_0.gguf](https://huggingface.co/TheBloke/CodeLlama-70B-Python-GGUF/blob/main/codellama-70b-python.Q4_0.gguf) | Q4_0 | 4 | 38.87 GB| 41.37 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| [codellama-70b-python.Q4_K_S.gguf](https://huggingface.co/TheBloke/CodeLlama-70B-Python-GGUF/blob/main/codellama-70b-python.Q4_K_S.gguf) | Q4_K_S | 4 | 39.25 GB| 41.75 GB | small, greater quality loss |
| [codellama-70b-python.Q4_K_M.gguf](https://huggingface.co/TheBloke/CodeLlama-70B-Python-GGUF/blob/main/codellama-70b-python.Q4_K_M.gguf) | Q4_K_M | 4 | 41.42 GB| 43.92 GB | medium, balanced quality - recommended |
| [codellama-70b-python.Q5_0.gguf](https://huggingface.co/TheBloke/CodeLlama-70B-Python-GGUF/blob/main/codellama-70b-python.Q5_0.gguf) | Q5_0 | 5 | 47.46 GB| 49.96 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| [codellama-70b-python.Q5_K_S.gguf](https://huggingface.co/TheBloke/CodeLlama-70B-Python-GGUF/blob/main/codellama-70b-python.Q5_K_S.gguf) | Q5_K_S | 5 | 47.46 GB| 49.96 GB | large, low quality loss - recommended |
| [codellama-70b-python.Q5_K_M.gguf](https://huggingface.co/TheBloke/CodeLlama-70B-Python-GGUF/blob/main/codellama-70b-python.Q5_K_M.gguf) | Q5_K_M | 5 | 48.75 GB| 51.25 GB | large, very low quality loss - recommended |
| codellama-70b-python.Q6_K.gguf | Q6_K | 6 | 56.59 GB| 59.09 GB | very large, extremely low quality loss |
| codellama-70b-python.Q8_0.gguf | Q8_0 | 8 | 73.29 GB| 75.79 GB | very large, extremely low quality loss - not recommended |
**Note**: the above RAM figures assume no GPU offloading. If layers are offloaded to the GPU, this will reduce RAM usage and use VRAM instead.
### Q6_K and Q8_0 files are split and require joining
**Note:** HF does not support uploading files larger than 50GB. Therefore I have uploaded the Q6_K and Q8_0 files as split files.
<details>
<summary>Click for instructions regarding Q6_K and Q8_0 files</summary>
### q6_K
Please download:
* `codellama-70b-python.Q6_K.gguf-split-a`
* `codellama-70b-python.Q6_K.gguf-split-b`
### q8_0
Please download:
* `codellama-70b-python.Q8_0.gguf-split-a`
* `codellama-70b-python.Q8_0.gguf-split-b`
To join the files, do the following:
Linux and macOS:
```
cat codellama-70b-python.Q6_K.gguf-split-* > codellama-70b-python.Q6_K.gguf && rm codellama-70b-python.Q6_K.gguf-split-*
cat codellama-70b-python.Q8_0.gguf-split-* > codellama-70b-python.Q8_0.gguf && rm codellama-70b-python.Q8_0.gguf-split-*
```
Windows command line:
```
COPY /B codellama-70b-python.Q6_K.gguf-split-a + codellama-70b-python.Q6_K.gguf-split-b codellama-70b-python.Q6_K.gguf
del codellama-70b-python.Q6_K.gguf-split-a codellama-70b-python.Q6_K.gguf-split-b
COPY /B codellama-70b-python.Q8_0.gguf-split-a + codellama-70b-python.Q8_0.gguf-split-b codellama-70b-python.Q8_0.gguf
del codellama-70b-python.Q8_0.gguf-split-a codellama-70b-python.Q8_0.gguf-split-b
```
</details>
<!-- README_GGUF.md-provided-files end -->
<!-- README_GGUF.md-how-to-download start -->
## How to download GGUF files
**Note for manual downloaders:** You almost never want to clone the entire repo! Multiple different quantisation formats are provided, and most users only want to pick and download a single file.
The following clients/libraries will automatically download models for you, providing a list of available models to choose from:
* LM Studio
* LoLLMS Web UI
* Faraday.dev
### In `text-generation-webui`
Under Download Model, you can enter the model repo: TheBloke/CodeLlama-70B-Python-GGUF and below it, a specific filename to download, such as: codellama-70b-python.Q4_K_M.gguf.
Then click Download.
### On the command line, including multiple files at once
I recommend using the `huggingface-hub` Python library:
```shell
pip3 install huggingface-hub
```
Then you can download any individual model file to the current directory, at high speed, with a command like this:
```shell
huggingface-cli download TheBloke/CodeLlama-70B-Python-GGUF codellama-70b-python.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
```
<details>
<summary>More advanced huggingface-cli download usage (click to read)</summary>
You can also download multiple files at once with a pattern:
```shell
huggingface-cli download TheBloke/CodeLlama-70B-Python-GGUF --local-dir . --local-dir-use-symlinks False --include='*Q4_K*gguf'
```
For more documentation on downloading with `huggingface-cli`, please see: [HF -> Hub Python Library -> Download files -> Download from the CLI](https://huggingface.co/docs/huggingface_hub/guides/download#download-from-the-cli).
To accelerate downloads on fast connections (1Gbit/s or higher), install `hf_transfer`:
```shell
pip3 install hf_transfer
```
And set environment variable `HF_HUB_ENABLE_HF_TRANSFER` to `1`:
```shell
HF_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download TheBloke/CodeLlama-70B-Python-GGUF codellama-70b-python.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
```
Windows Command Line users: You can set the environment variable by running `set HF_HUB_ENABLE_HF_TRANSFER=1` before the download command.
</details>
<!-- README_GGUF.md-how-to-download end -->
<!-- README_GGUF.md-how-to-run start -->
## Example `llama.cpp` command
Make sure you are using `llama.cpp` from commit [d0cee0d](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221) or later.
```shell
./main -ngl 35 -m codellama-70b-python.Q4_K_M.gguf --color -c 4096 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "{prompt}"
```
Change `-ngl 32` to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.
Change `-c 4096` to the desired sequence length. For extended sequence models - eg 8K, 16K, 32K - the necessary RoPE scaling parameters are read from the GGUF file and set by llama.cpp automatically. Note that longer sequence lengths require much more resources, so you may need to reduce this value.
If you want to have a chat-style conversation, replace the `-p <PROMPT>` argument with `-i -ins`
For other parameters and how to use them, please refer to [the llama.cpp documentation](https://github.com/ggerganov/llama.cpp/blob/master/examples/main/README.md)
## How to run in `text-generation-webui`
Further instructions can be found in the text-generation-webui documentation, here: [text-generation-webui/docs/04 ‐ Model Tab.md](https://github.com/oobabooga/text-generation-webui/blob/main/docs/04%20%E2%80%90%20Model%20Tab.md#llamacpp).
## How to run from Python code
You can use GGUF models from Python using the [llama-cpp-python](https://github.com/abetlen/llama-cpp-python) or [ctransformers](https://github.com/marella/ctransformers) libraries. Note that at the time of writing (Nov 27th 2023), ctransformers has not been updated for some time and is not compatible with some recent models. Therefore I recommend you use llama-cpp-python.
### How to load this model in Python code, using llama-cpp-python
For full documentation, please see: [llama-cpp-python docs](https://abetlen.github.io/llama-cpp-python/).
#### First install the package
Run one of the following commands, according to your system:
```shell
# Base ctransformers with no GPU acceleration
pip install llama-cpp-python
# With NVidia CUDA acceleration
CMAKE_ARGS="-DLLAMA_CUBLAS=on" pip install llama-cpp-python
# Or with OpenBLAS acceleration
CMAKE_ARGS="-DLLAMA_BLAS=ON -DLLAMA_BLAS_VENDOR=OpenBLAS" pip install llama-cpp-python
# Or with CLBLast acceleration
CMAKE_ARGS="-DLLAMA_CLBLAST=on" pip install llama-cpp-python
# Or with AMD ROCm GPU acceleration (Linux only)
CMAKE_ARGS="-DLLAMA_HIPBLAS=on" pip install llama-cpp-python
# Or with Metal GPU acceleration for macOS systems only
CMAKE_ARGS="-DLLAMA_METAL=on" pip install llama-cpp-python
# In windows, to set the variables CMAKE_ARGS in PowerShell, follow this format; eg for NVidia CUDA:
$env:CMAKE_ARGS = "-DLLAMA_OPENBLAS=on"
pip install llama-cpp-python
```
#### Simple llama-cpp-python example code
```python
from llama_cpp import Llama
# Set gpu_layers to the number of layers to offload to GPU. Set to 0 if no GPU acceleration is available on your system.
llm = Llama(
model_path="./codellama-70b-python.Q4_K_M.gguf", # Download the model file first
n_ctx=4096, # The max sequence length to use - note that longer sequence lengths require much more resources
n_threads=8, # The number of CPU threads to use, tailor to your system and the resulting performance
n_gpu_layers=35 # The number of layers to offload to GPU, if you have GPU acceleration available
)
# Simple inference example
output = llm(
"{prompt}", # Prompt
max_tokens=512, # Generate up to 512 tokens
stop=["</s>"], # Example stop token - not necessarily correct for this specific model! Please check before using.
echo=True # Whether to echo the prompt
)
# Chat Completion API
llm = Llama(model_path="./codellama-70b-python.Q4_K_M.gguf", chat_format="llama-2") # Set chat_format according to the model you are using
llm.create_chat_completion(
messages = [
{"role": "system", "content": "You are a story writing assistant."},
{
"role": "user",
"content": "Write a story about llamas."
}
]
)
```
## How to use with LangChain
Here are guides on using llama-cpp-python and ctransformers with LangChain:
* [LangChain + llama-cpp-python](https://python.langchain.com/docs/integrations/llms/llamacpp)
* [LangChain + ctransformers](https://python.langchain.com/docs/integrations/providers/ctransformers)
<!-- README_GGUF.md-how-to-run end -->
<!-- footer start -->
<!-- 200823 -->
## Discord
For further support, and discussions on these models and AI in general, join us at:
[TheBloke AI's Discord server](https://discord.gg/theblokeai)
## Thanks, and how to contribute
Thanks to the [chirper.ai](https://chirper.ai) team!
Thanks to Clay from [gpus.llm-utils.org](llm-utils)!
I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training.
If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects.
Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits.
* Patreon: https://patreon.com/TheBlokeAI
* Ko-Fi: https://ko-fi.com/TheBlokeAI
**Special thanks to**: Aemon Algiz.
**Patreon special mentions**: Michael Levine, 阿明, Trailburnt, Nikolai Manek, John Detwiler, Randy H, Will Dee, Sebastain Graf, NimbleBox.ai, Eugene Pentland, Emad Mostaque, Ai Maven, Jim Angel, Jeff Scroggin, Michael Davis, Manuel Alberto Morcote, Stephen Murray, Robert, Justin Joy, Luke @flexchar, Brandon Frisco, Elijah Stavena, S_X, Dan Guido, Undi ., Komninos Chatzipapas, Shadi, theTransient, Lone Striker, Raven Klaugh, jjj, Cap'n Zoog, Michel-Marie MAUDET (LINAGORA), Matthew Berman, David, Fen Risland, Omer Bin Jawed, Luke Pendergrass, Kalila, OG, Erik Bjäreholt, Rooh Singh, Joseph William Delisle, Dan Lewis, TL, John Villwock, AzureBlack, Brad, Pedro Madruga, Caitlyn Gatomon, K, jinyuan sun, Mano Prime, Alex, Jeffrey Morgan, Alicia Loh, Illia Dulskyi, Chadd, transmissions 11, fincy, Rainer Wilmers, ReadyPlayerEmma, knownsqashed, Mandus, biorpg, Deo Leter, Brandon Phillips, SuperWojo, Sean Connelly, Iucharbius, Jack West, Harry Royden McLaughlin, Nicholas, terasurfer, Vitor Caleffi, Duane Dunston, Johann-Peter Hartmann, David Ziegler, Olakabola, Ken Nordquist, Trenton Dambrowitz, Tom X Nguyen, Vadim, Ajan Kanaga, Leonard Tan, Clay Pascal, Alexandros Triantafyllidis, JM33133, Xule, vamX, ya boyyy, subjectnull, Talal Aujan, Alps Aficionado, wassieverse, Ari Malik, James Bentley, Woland, Spencer Kim, Michael Dempsey, Fred von Graf, Elle, zynix, William Richards, Stanislav Ovsiannikov, Edmond Seymore, Jonathan Leane, Martin Kemka, usrbinkat, Enrico Ros
Thank you to all my generous patrons and donaters!
And thank you again to a16z for their generous grant.
<!-- footer end -->
<!-- original-model-card start -->
# Original model card: Code Llama's CodeLlama 70B Python
# **Code Llama**
Code Llama is a collection of pretrained and fine-tuned generative text models ranging in scale from 7 billion to 70 billion parameters. This is the repository for the 70B Python specialist version in the Hugging Face Transformers format. This model is designed for general code synthesis and understanding. Links to other models can be found in the index at the bottom.
| | Base Model | Python | Instruct |
| --- | ----------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------- | ----------------------------------------------------------------------------------------------- |
| 7B | [codellama/CodeLlama-7b-hf](https://huggingface.co/codellama/CodeLlama-7b-hf) | [codellama/CodeLlama-7b-Python-hf](https://huggingface.co/codellama/CodeLlama-7b-Python-hf) | [codellama/CodeLlama-7b-Instruct-hf](https://huggingface.co/codellama/CodeLlama-7b-Instruct-hf) |
| 13B | [codellama/CodeLlama-13b-hf](https://huggingface.co/codellama/CodeLlama-13b-hf) | [codellama/CodeLlama-13b-Python-hf](https://huggingface.co/codellama/CodeLlama-13b-Python-hf) | [codellama/CodeLlama-13b-Instruct-hf](https://huggingface.co/codellama/CodeLlama-13b-Instruct-hf) |
| 34B | [codellama/CodeLlama-34b-hf](https://huggingface.co/codellama/CodeLlama-34b-hf) | [codellama/CodeLlama-34b-Python-hf](https://huggingface.co/codellama/CodeLlama-34b-Python-hf) | [codellama/CodeLlama-34b-Instruct-hf](https://huggingface.co/codellama/CodeLlama-34b-Instruct-hf) |
| 70B | [codellama/CodeLlama-70b-hf](https://huggingface.co/codellama/CodeLlama-70b-hf) | [codellama/CodeLlama-70b-Python-hf](https://huggingface.co/codellama/CodeLlama-70b-Python-hf) | [codellama/CodeLlama-70b-Instruct-hf](https://huggingface.co/codellama/CodeLlama-70b-Instruct-hf) |
## Model Use
To use this model, please make sure to install `transformers`.
```bash
pip install transformers accelerate
```
Model capabilities:
- [x] Code completion.
- [ ] Infilling.
- [ ] Instructions / chat.
- [x] Python specialist.
## Model Details
*Note: Use of this model is governed by the Meta license. Meta developed and publicly released the Code Llama family of large language models (LLMs).
**Model Developers** Meta
**Variations** Code Llama comes in four model sizes, and three variants:
* Code Llama: base models designed for general code synthesis and understanding
* Code Llama - Python: designed specifically for Python
* Code Llama - Instruct: for instruction following and safer deployment
All variants are available in sizes of 7B, 13B, 34B, and 70B parameters.
**This repository contains the Python version of the 70B parameters model.**
**Input** Models input text only.
**Output** Models generate text only.
**Model Architecture** Code Llama is an auto-regressive language model that uses an optimized transformer architecture.
**Model Architecture** Code Llama is an auto-regressive language model that uses an optimized transformer architecture. It was fine-tuned with up to 16k tokens. This variant **does not** support long context of up to 100k tokens.
**Model Dates** Code Llama and its variants have been trained between January 2023 and January 2024.
**Status** This is a static model trained on an offline dataset. Future versions of Code Llama - Instruct will be released as we improve model safety with community feedback.
**License** A custom commercial license is available at: [https://ai.meta.com/resources/models-and-libraries/llama-downloads/](https://ai.meta.com/resources/models-and-libraries/llama-downloads/)
**Research Paper** More information can be found in the paper "[Code Llama: Open Foundation Models for Code](https://ai.meta.com/research/publications/code-llama-open-foundation-models-for-code/)" or its [arXiv page](https://arxiv.org/abs/2308.12950).
## Intended Use
**Intended Use Cases** Code Llama and its variants are intended for commercial and research use in English and relevant programming languages. The base model Code Llama can be adapted for a variety of code synthesis and understanding tasks, Code Llama - Python is designed specifically to handle the Python programming language, and Code Llama - Instruct is intended to be safer to use for code assistant and generation applications.
**Out-of-Scope Uses** Use in any manner that violates applicable laws or regulations (including trade compliance laws). Use in languages other than English. Use in any other way that is prohibited by the Acceptable Use Policy and Licensing Agreement for Code Llama and its variants.
## Hardware and Software
**Training Factors** We used custom training libraries. The training and fine-tuning of the released models have been performed Meta’s Research Super Cluster.
**Carbon Footprint** In aggregate, training all 12 Code Llama models required 1400K GPU hours of computation on hardware of type A100-80GB (TDP of 350-400W). Estimated total emissions were 228.55 tCO2eq, 100% of which were offset by Meta’s sustainability program.
## Evaluation Results
See evaluations for the main models and detailed ablations in Section 3 and safety evaluations in Section 4 of the research paper.
## Ethical Considerations and Limitations
Code Llama and its variants are a new technology that carries risks with use. Testing conducted to date has been in English, and has not covered, nor could it cover all scenarios. For these reasons, as with all LLMs, Code Llama’s potential outputs cannot be predicted in advance, and the model may in some instances produce inaccurate or objectionable responses to user prompts. Therefore, before deploying any applications of Code Llama, developers should perform safety testing and tuning tailored to their specific applications of the model.
Please see the Responsible Use Guide available available at [https://ai.meta.com/llama/responsible-use-guide](https://ai.meta.com/llama/responsible-use-guide).
<!-- original-model-card end -->
|
digiplay/Sweet-mix_v2.2_flat | digiplay | "2024-04-07T20:43:36Z" | 1,675 | 2 | diffusers | [
"diffusers",
"safetensors",
"stable-diffusion",
"stable-diffusion-diffusers",
"text-to-image",
"license:other",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
] | text-to-image | "2024-04-04T23:39:53Z" | ---
license: other
tags:
- stable-diffusion
- stable-diffusion-diffusers
- text-to-image
- diffusers
inference: true
---
Model info:
https://civitai.com/models/18927/sweet-mix?modelVersionId=158294
Sample image generated by Huggingface's API :
1girl picnic,sunnyday,
Note:
Original Author's Version didn't bake VAE,
for convenience uses, I baked two VAE versions
users can download here:
https://huggingface.co/digiplay/Sweet-mix_v2.2_flat/tree/main
Original Author's DEMO images :
|
QuantFactory/suzume-llama-3-8B-japanese-GGUF | QuantFactory | "2024-06-08T11:42:02Z" | 1,675 | 0 | null | [
"gguf",
"generated_from_trainer",
"text-generation",
"arxiv:2405.12612",
"base_model:meta-ll",
"license:other",
"region:us"
] | text-generation | "2024-06-06T05:54:05Z" | ---
license: other
license_name: llama-3
license_link: https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct/raw/main/LICENSE
base_model: meta-ll
tags:
- generated_from_trainer
model-index:
- name: >-
workspace/llm_training/axolotl/llama3-ja/output_openchat_megagon_lbgpt4_ja_8B_instruct
results: []
pipeline_tag: text-generation
---
# QuantFactory/suzume-llama-3-8B-japanese-GGUF
This is quantiized version of [lightblue/suzume-llama-3-8B-japanese](https://huggingface.co/lightblue/suzume-llama-3-8B-japanese) created using llama.cpp
# Model Description
[[Paper](https://arxiv.org/abs/2405.12612)] [[Dataset](https://huggingface.co/datasets/lightblue/tagengo-gpt4)]
This Suzume 8B, a Japanese finetune of Llama 3.
Llama 3 has exhibited excellent performance on many English language benchmarks.
However, it also seemingly been finetuned on mostly English data, meaning that it will respond in English, even if prompted in Japanese.
We have fine-tuned Llama 3 on more than 3,000 Japanese conversations meaning that this model has the intelligence of Llama 3 but has the added ability to chat in Japanese.
Please feel free to comment on this model and give us feedback in the Community tab!
We will release a paper in the future describing how we made the training data, the model, and the evaluations we have conducted of it.
# How to use
You can use the original trained model with vLLM like so:
```python
from vllm import LLM, SamplingParams
sampling_params = SamplingParams(temperature=0.8, top_p=0.95)
llm = LLM(model="lightblue/suzume-llama-3-8B-japanese")
prompts = [
"東京のおすすめの観光スポットを教えて下さい",
]
outputs = llm.generate(prompts, sampling_params)
for output in outputs:
prompt = output.prompt
generated_text = output.outputs[0].text
print(f"Prompt: {prompt!r}, Generated text: {generated_text!r}")
```
# Evaluation scores
We find that this is the best performing model in the 7/8B class of LLMs on a multitude of Japanese language benchmarks.
We calculate our Japanese evaluation scores using our [lightblue-tech/japanese_llm_eval](https://github.com/lightblue-tech/japanese_llm_eval) repo.
We also compare our Japanese model to our multilingual model using our [multilingual_mt_bench](https://github.com/Peter-Devine/multilingual_mt_bench/tree/main/fastchat/llm_judge) repo.
| | **lightblue/suzume-llama-3-8B-japanese** | **lightblue/suzume-llama-3-8B-multilingual** | **Nexusflow/Starling-LM-7B-beta** | **gpt-3.5-turbo** |
|-----------------|------------------------------------------|----------------------------------------------|-----------------------------------|-------------------|
| **Japanese 🇯🇵** | 6.24 | 6.56 | 6.22 | 7.84 |
Here, we find that our multilingual model outperforms our Japanese model on the Japanese MT-Bench benchmark, indicating that our multilingual model was able to generalize better to the Japanese MT-Bench benchmark from training on more data, even if that added data was not in Japanese.
Note - the discrepancy between the MT-Bench scores of the first and second evaluation of `lightblue/suzume-llama-3-8B-japanese` are due to the difference in system message of the two evaluation harnesses. The former's system message is in Japanese while the latter's is in English.
# Training data
We train on three sources of data to create this model
* [megagonlabs/instruction_ja](https://github.com/megagonlabs/instruction_ja) - 669 conversations
* A hand-edited dataset of nearly 700 conversations taken originally from translations of the [kunishou/hh-rlhf-49k-ja](https://huggingface.co/datasets/kunishou/hh-rlhf-49k-ja) dataset.
* [openchat/openchat_sharegpt4_dataset](https://huggingface.co/datasets/openchat/openchat_sharegpt4_dataset/resolve/main/sharegpt_gpt4.json) (Japanese conversations only) - 167 conversations
* Conversations taken from humans talking to GPT-4
* lightblue/tagengo-gpt4 (Japanese prompts only) (Link coming soon!) - 2,482 conversations
* Almost 2,500 diverse Japanese prompts sampled from [lmsys/lmsys-chat-1m](https://huggingface.co/datasets/lmsys/lmsys-chat-1m) and then used to prompt `gpt-4-0125-preview`
# Training config
[<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
<details><summary>See axolotl config</summary>
axolotl version: `0.4.0`
```yaml
base_model: meta-llama/Meta-Llama-3-8B-Instruct
model_type: LlamaForCausalLM
tokenizer_type: AutoTokenizer # PreTrainedTokenizerFast
load_in_8bit: false
load_in_4bit: false
strict: false
datasets:
- path: /workspace/llm_training/axolotl/llama3-ja/openchat_megagon_lbgpt4_ja.json
ds_type: json # see other options below
type: sharegpt
conversation: llama-3
dataset_prepared_path: /workspace/llm_training/axolotl/llama3-ja/prepared_openchat_megagon_lbgpt4_ja
val_set_size: 0.01
output_dir: /workspace/llm_training/axolotl/llama3-ja/output_openchat_megagon_lbgpt4_ja_8B_instruct
sequence_len: 8192
sample_packing: true
pad_to_sequence_len: true
eval_sample_packing: False
use_wandb: true
wandb_project: axolotl
wandb_entity: peterd
wandb_name: openchat_megagon_lbgpt4_ja_8B_instruct
gradient_accumulation_steps: 2
micro_batch_size: 2
num_epochs: 1
optimizer: paged_adamw_8bit
lr_scheduler: cosine
learning_rate: 1e-5
train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false
gradient_checkpointing: true
gradient_checkpointing_kwargs:
use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
logging_steps: 1
xformers_attention:
flash_attention: true
warmup_steps: 10
evals_per_epoch: 5
eval_table_size:
saves_per_epoch: 1
debug:
deepspeed: /workspace/axolotl/deepspeed_configs/zero2.json
weight_decay: 0.0
special_tokens:
pad_token: <|end_of_text|>
```
</details><br>
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 1e-05
- train_batch_size: 2
- eval_batch_size: 2
- seed: 42
- distributed_type: multi-GPU
- num_devices: 3
- gradient_accumulation_steps: 2
- total_train_batch_size: 12
- total_eval_batch_size: 6
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 10
- num_epochs: 1
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 1.303 | 0.08 | 1 | 1.2664 |
| 1.4231 | 0.23 | 3 | 1.2409 |
| 1.1007 | 0.46 | 6 | 1.0264 |
| 1.0635 | 0.69 | 9 | 1.0154 |
| 1.0221 | 0.92 | 12 | 0.9555 |
### Framework versions
- Transformers 4.40.0.dev0
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.0
# Developer
Peter Devine - ([ptrdvn](https://huggingface.co/ptrdvn)) |
tapan247/my-finetune-llama-hf-q4.gguf | tapan247 | "2024-06-29T12:30:20Z" | 1,675 | 0 | null | [
"gguf",
"region:us"
] | null | "2024-06-29T12:26:44Z" | Entry not found |
KoboldAI/OPT-2.7B-Nerys-v2 | KoboldAI | "2022-09-19T07:19:35Z" | 1,674 | 6 | transformers | [
"transformers",
"pytorch",
"opt",
"text-generation",
"en",
"arxiv:2205.01068",
"license:other",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2022-09-19T06:50:39Z" | ---
language: en
license: other
commercial: no
---
# OPT 2.7B - Nerys
## Model Description
OPT 2.7B-Nerys is a finetune created using Facebook's OPT model.
## Training data
The training data contains around 2500 ebooks in various genres (the "Pike" dataset), a CYOA dataset called "CYS" and 50 Asian "Light Novels" (the "Manga-v1" dataset).
Most parts of the dataset have been prepended using the following text: `[Genre: <genre1>, <genre2>]`
This dataset has been cleaned in the same way as fairseq-dense-13B-Nerys-v2
### How to use
You can use this model directly with a pipeline for text generation. This example generates a different sequence each time it's run:
```py
>>> from transformers import pipeline
>>> generator = pipeline('text-generation', model='KoboldAI/OPT-2.7B-Nerys-v2')
>>> generator("Welcome Captain Janeway, I apologize for the delay.", do_sample=True, min_length=50)
[{'generated_text': 'Welcome Captain Janeway, I apologize for the delay."\nIt's all right," Janeway said. "I'm certain that you're doing your best to keep me informed of what\'s going on."'}]
```
### Limitations and Biases
Based on known problems with NLP technology, potential relevant factors include bias (gender, profession, race and religion).
### License
OPT-6B is licensed under the OPT-175B license, Copyright (c) Meta Platforms, Inc. All Rights Reserved.
### BibTeX entry and citation info
```
@misc{zhang2022opt,
title={OPT: Open Pre-trained Transformer Language Models},
author={Susan Zhang and Stephen Roller and Naman Goyal and Mikel Artetxe and Moya Chen and Shuohui Chen and Christopher Dewan and Mona Diab and Xian Li and Xi Victoria Lin and Todor Mihaylov and Myle Ott and Sam Shleifer and Kurt Shuster and Daniel Simig and Punit Singh Koura and Anjali Sridhar and Tianlu Wang and Luke Zettlemoyer},
year={2022},
eprint={2205.01068},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
``` |
TheBloke/airoboros-13B-HF | TheBloke | "2023-06-05T00:10:20Z" | 1,674 | 12 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"license:other",
"autotrain_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-05-23T21:26:27Z" | ---
license: other
inference: false
---
<!-- header start -->
<div style="width: 100%;">
<img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
</div>
<div style="display: flex; justify-content: space-between; width: 100%;">
<div style="display: flex; flex-direction: column; align-items: flex-start;">
<p><a href="https://discord.gg/Jq4vkcDakD">Chat & support: my new Discord server</a></p>
</div>
<div style="display: flex; flex-direction: column; align-items: flex-end;">
<p><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p>
</div>
</div>
<!-- header end -->
# Airoboros 13B HF fp16
These files are HF format fp16 model files for [Jon Durbin's Airoboros 13B](https://huggingface.co/jondurbin/airoboros-13b).
It is the result of converting Jon's fp32 repo to fp16 for easier storage and usage.
## Other repositories available
* [4bit GPTQ models for GPU inference](https://huggingface.co/TheBloke/airoboros-13B-GPTQ)
* [Unquantised model in HF fp16 format](https://huggingface.co/TheBloke/airoboros-13B-HF)
* [latimar's GGML models for CPU (+CUDA) inference](https://huggingface.co/latimar/airoboros-13b-ggml)
<!-- footer start -->
## Discord
For further support, and discussions on these models and AI in general, join us at:
[TheBloke AI's Discord server](https://discord.gg/Jq4vkcDakD)
## Thanks, and how to contribute.
Thanks to the [chirper.ai](https://chirper.ai) team!
I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training.
If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects.
Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits.
* Patreon: https://patreon.com/TheBlokeAI
* Ko-Fi: https://ko-fi.com/TheBlokeAI
**Patreon special mentions**: Aemon Algiz, Dmitriy Samsonov, Nathan LeClaire, Trenton Dambrowitz, Mano Prime, David Flickinger, vamX, Nikolai Manek, senxiiz, Khalefa Al-Ahmad, Illia Dulskyi, Jonathan Leane, Talal Aujan, V. Lukas, Joseph William Delisle, Pyrater, Oscar Rangel, Lone Striker, Luke Pendergrass, Eugene Pentland, Sebastain Graf, Johann-Peter Hartman.
Thank you to all my generous patrons and donaters!
<!-- footer end -->
# Airoboros-13B original model card
# Overview
This is a fine-tuned 13b parameter LlaMa model, using completely synthetic training data created by https://github.com/jondurbin/airoboros
### Eval (gpt4 judging)
| model | raw score | gpt-3.5 adjusted score |
| --- | --- | --- |
| __airoboros-13b__ | __17947__ | __98.087__ |
| gpt35 | 18297 | 100.0 |
| gpt4-x-alpasta-30b | 15612 | 85.33 |
| manticore-13b | 15856 | 86.66 |
| vicuna-13b-1.1 | 16306 | 89.12 |
| wizard-vicuna-13b-uncensored | 16287 | 89.01 |
<details>
<summary>individual question scores, with shareGPT links (200 prompts generated by gpt-4)</summary>
*wb-13b-u is Wizard-Vicuna-13b-Uncensored*
| airoboros-13b | gpt35 | gpt4-x-alpasta-30b | manticore-13b | vicuna-13b-1.1 | wv-13b-u | link |
|----------------:|--------:|---------------------:|----------------:|-----------------:|-------------------------------:|:---------------------------------------|
| 80 | 95 | 70 | 90 | 85 | 60 | [eval](https://sharegpt.com/c/PIbRQD3) |
| 20 | 95 | 40 | 30 | 90 | 80 | [eval](https://sharegpt.com/c/fSzwzzd) |
| 100 | 100 | 100 | 95 | 95 | 100 | [eval](https://sharegpt.com/c/AXMzZiO) |
| 90 | 100 | 85 | 60 | 95 | 100 | [eval](https://sharegpt.com/c/7obzJm2) |
| 95 | 90 | 80 | 85 | 95 | 75 | [eval](https://sharegpt.com/c/cRpj6M1) |
| 100 | 95 | 90 | 95 | 98 | 92 | [eval](https://sharegpt.com/c/p0by1T7) |
| 50 | 100 | 80 | 95 | 60 | 55 | [eval](https://sharegpt.com/c/rowNlKx) |
| 70 | 90 | 80 | 60 | 85 | 40 | [eval](https://sharegpt.com/c/I4POj4I) |
| 100 | 95 | 50 | 85 | 40 | 60 | [eval](https://sharegpt.com/c/gUAeiRp) |
| 85 | 60 | 55 | 65 | 50 | 70 | [eval](https://sharegpt.com/c/Lgw4QQL) |
| 95 | 100 | 85 | 90 | 60 | 75 | [eval](https://sharegpt.com/c/X9tDYft) |
| 100 | 95 | 70 | 80 | 50 | 85 | [eval](https://sharegpt.com/c/9V2ElkH) |
| 100 | 95 | 80 | 70 | 60 | 90 | [eval](https://sharegpt.com/c/D5xg6qt) |
| 95 | 100 | 70 | 85 | 90 | 90 | [eval](https://sharegpt.com/c/lQnSfDs) |
| 80 | 95 | 90 | 60 | 30 | 85 | [eval](https://sharegpt.com/c/1hpHGNc) |
| 60 | 95 | 0 | 75 | 50 | 40 | [eval](https://sharegpt.com/c/an6TqE4) |
| 100 | 95 | 90 | 98 | 95 | 95 | [eval](https://sharegpt.com/c/7vr6n3F) |
| 60 | 85 | 40 | 50 | 20 | 0 | [eval](https://sharegpt.com/c/TOkMkgE) |
| 100 | 90 | 85 | 95 | 95 | 80 | [eval](https://sharegpt.com/c/Qu7ak0r) |
| 100 | 95 | 100 | 95 | 90 | 95 | [eval](https://sharegpt.com/c/hMD4gPo) |
| 95 | 90 | 96 | 80 | 92 | 88 | [eval](https://sharegpt.com/c/HTlicNh) |
| 95 | 92 | 90 | 93 | 89 | 91 | [eval](https://sharegpt.com/c/MjxHpAf) |
| 95 | 93 | 90 | 94 | 96 | 92 | [eval](https://sharegpt.com/c/4RvxOR9) |
| 95 | 90 | 93 | 88 | 92 | 85 | [eval](https://sharegpt.com/c/PcAIU9r) |
| 95 | 90 | 85 | 96 | 88 | 92 | [eval](https://sharegpt.com/c/MMqul3q) |
| 95 | 95 | 90 | 93 | 92 | 91 | [eval](https://sharegpt.com/c/YQsLyzJ) |
| 95 | 98 | 80 | 97 | 99 | 96 | [eval](https://sharegpt.com/c/UDhSTMq) |
| 95 | 93 | 90 | 87 | 92 | 89 | [eval](https://sharegpt.com/c/4gCfdCV) |
| 90 | 85 | 95 | 80 | 92 | 75 | [eval](https://sharegpt.com/c/bkQs4SP) |
| 90 | 85 | 95 | 93 | 80 | 92 | [eval](https://sharegpt.com/c/LeLCEEt) |
| 95 | 92 | 90 | 91 | 93 | 89 | [eval](https://sharegpt.com/c/DFxNzVu) |
| 100 | 95 | 90 | 85 | 80 | 95 | [eval](https://sharegpt.com/c/gnVzNML) |
| 95 | 97 | 93 | 92 | 96 | 94 | [eval](https://sharegpt.com/c/y7pxMIy) |
| 95 | 93 | 94 | 90 | 88 | 92 | [eval](https://sharegpt.com/c/5UeCvTY) |
| 90 | 95 | 98 | 85 | 96 | 92 | [eval](https://sharegpt.com/c/T4oL9I5) |
| 90 | 88 | 85 | 80 | 82 | 84 | [eval](https://sharegpt.com/c/HnGyTAG) |
| 90 | 95 | 85 | 87 | 92 | 88 | [eval](https://sharegpt.com/c/ZbRMBNj) |
| 95 | 97 | 96 | 90 | 93 | 92 | [eval](https://sharegpt.com/c/iTmFJqd) |
| 95 | 93 | 92 | 90 | 89 | 91 | [eval](https://sharegpt.com/c/VuPifET) |
| 90 | 95 | 93 | 92 | 94 | 91 | [eval](https://sharegpt.com/c/AvFAH1x) |
| 90 | 85 | 95 | 80 | 88 | 75 | [eval](https://sharegpt.com/c/4ealKGN) |
| 85 | 90 | 95 | 88 | 92 | 80 | [eval](https://sharegpt.com/c/bE1b2vX) |
| 90 | 95 | 92 | 85 | 80 | 87 | [eval](https://sharegpt.com/c/I3nMPBC) |
| 85 | 90 | 95 | 80 | 88 | 75 | [eval](https://sharegpt.com/c/as7r3bW) |
| 85 | 80 | 75 | 90 | 70 | 82 | [eval](https://sharegpt.com/c/qYceaUa) |
| 90 | 85 | 95 | 92 | 93 | 80 | [eval](https://sharegpt.com/c/g4FXchU) |
| 90 | 95 | 75 | 85 | 80 | 70 | [eval](https://sharegpt.com/c/6kGLvL5) |
| 85 | 90 | 80 | 88 | 82 | 83 | [eval](https://sharegpt.com/c/SRozqaF) |
| 85 | 90 | 95 | 92 | 88 | 80 | [eval](https://sharegpt.com/c/GoKydf6) |
| 85 | 90 | 80 | 75 | 95 | 88 | [eval](https://sharegpt.com/c/37aXkHQ) |
| 85 | 90 | 80 | 88 | 84 | 92 | [eval](https://sharegpt.com/c/nVuUaTj) |
| 80 | 90 | 75 | 85 | 70 | 95 | [eval](https://sharegpt.com/c/TkAQKLC) |
| 90 | 88 | 85 | 80 | 92 | 83 | [eval](https://sharegpt.com/c/55cO2y0) |
| 85 | 75 | 90 | 80 | 78 | 88 | [eval](https://sharegpt.com/c/tXtq5lT) |
| 85 | 90 | 80 | 82 | 75 | 88 | [eval](https://sharegpt.com/c/TfMjeJQ) |
| 90 | 85 | 40 | 95 | 80 | 88 | [eval](https://sharegpt.com/c/2jQ6K2S) |
| 85 | 95 | 90 | 75 | 88 | 80 | [eval](https://sharegpt.com/c/aQtr2ca) |
| 85 | 95 | 90 | 92 | 89 | 88 | [eval](https://sharegpt.com/c/tbWLyZ7) |
| 80 | 85 | 75 | 60 | 90 | 70 | [eval](https://sharegpt.com/c/moHC7i2) |
| 85 | 90 | 87 | 80 | 88 | 75 | [eval](https://sharegpt.com/c/GK6GShh) |
| 85 | 80 | 75 | 50 | 90 | 80 | [eval](https://sharegpt.com/c/ugcW4qG) |
| 95 | 80 | 90 | 85 | 75 | 82 | [eval](https://sharegpt.com/c/WL8iq6F) |
| 85 | 90 | 80 | 70 | 95 | 88 | [eval](https://sharegpt.com/c/TZJKnvS) |
| 90 | 95 | 70 | 85 | 80 | 75 | [eval](https://sharegpt.com/c/beNOKb5) |
| 90 | 85 | 70 | 75 | 80 | 60 | [eval](https://sharegpt.com/c/o2oRCF5) |
| 95 | 90 | 70 | 50 | 85 | 80 | [eval](https://sharegpt.com/c/TNjbK6D) |
| 80 | 85 | 40 | 60 | 90 | 95 | [eval](https://sharegpt.com/c/rJvszWJ) |
| 75 | 60 | 80 | 55 | 70 | 85 | [eval](https://sharegpt.com/c/HJwRkro) |
| 90 | 85 | 60 | 50 | 80 | 95 | [eval](https://sharegpt.com/c/AeFoSDK) |
| 45 | 85 | 60 | 20 | 65 | 75 | [eval](https://sharegpt.com/c/KA1cgOl) |
| 85 | 90 | 30 | 60 | 80 | 70 | [eval](https://sharegpt.com/c/RTy8n0y) |
| 90 | 95 | 80 | 40 | 85 | 70 | [eval](https://sharegpt.com/c/PJMJoXh) |
| 85 | 90 | 70 | 75 | 80 | 95 | [eval](https://sharegpt.com/c/Ib3jzyC) |
| 90 | 70 | 50 | 20 | 60 | 40 | [eval](https://sharegpt.com/c/oMmqqtX) |
| 90 | 95 | 75 | 60 | 85 | 80 | [eval](https://sharegpt.com/c/qRNhNTw) |
| 85 | 80 | 60 | 70 | 65 | 75 | [eval](https://sharegpt.com/c/3MAHQIy) |
| 90 | 85 | 80 | 75 | 82 | 70 | [eval](https://sharegpt.com/c/0Emc5HS) |
| 90 | 95 | 80 | 70 | 85 | 75 | [eval](https://sharegpt.com/c/UqAxRWF) |
| 85 | 75 | 30 | 80 | 90 | 70 | [eval](https://sharegpt.com/c/eywxGAw) |
| 85 | 90 | 50 | 70 | 80 | 60 | [eval](https://sharegpt.com/c/A2KSEWP) |
| 100 | 95 | 98 | 99 | 97 | 96 | [eval](https://sharegpt.com/c/C8rebQf) |
| 95 | 90 | 92 | 93 | 91 | 89 | [eval](https://sharegpt.com/c/cd9HF4V) |
| 95 | 92 | 90 | 85 | 88 | 91 | [eval](https://sharegpt.com/c/LHkjvQJ) |
| 100 | 95 | 98 | 97 | 96 | 99 | [eval](https://sharegpt.com/c/o5PdoyZ) |
| 100 | 100 | 100 | 90 | 100 | 95 | [eval](https://sharegpt.com/c/rh8pZVg) |
| 100 | 95 | 98 | 97 | 94 | 99 | [eval](https://sharegpt.com/c/T5DYL83) |
| 95 | 90 | 92 | 93 | 94 | 91 | [eval](https://sharegpt.com/c/G5Osg3X) |
| 100 | 95 | 98 | 90 | 96 | 95 | [eval](https://sharegpt.com/c/9ZqI03V) |
| 95 | 96 | 92 | 90 | 89 | 93 | [eval](https://sharegpt.com/c/4tFfwZU) |
| 100 | 95 | 93 | 90 | 92 | 88 | [eval](https://sharegpt.com/c/mG1JqPH) |
| 100 | 100 | 98 | 97 | 99 | 100 | [eval](https://sharegpt.com/c/VDdtgCu) |
| 95 | 90 | 92 | 85 | 93 | 94 | [eval](https://sharegpt.com/c/uKtGkvg) |
| 95 | 93 | 90 | 92 | 96 | 91 | [eval](https://sharegpt.com/c/9B92N6P) |
| 95 | 96 | 92 | 90 | 93 | 91 | [eval](https://sharegpt.com/c/GeIFfOu) |
| 95 | 90 | 92 | 93 | 91 | 89 | [eval](https://sharegpt.com/c/gn3E9nN) |
| 100 | 98 | 95 | 97 | 96 | 99 | [eval](https://sharegpt.com/c/Erxa46H) |
| 90 | 95 | 85 | 88 | 92 | 87 | [eval](https://sharegpt.com/c/oRHVOvK) |
| 95 | 93 | 90 | 92 | 89 | 88 | [eval](https://sharegpt.com/c/ghtKLUX) |
| 100 | 95 | 97 | 90 | 96 | 94 | [eval](https://sharegpt.com/c/ZL4KjqP) |
| 95 | 93 | 90 | 92 | 94 | 91 | [eval](https://sharegpt.com/c/YOnqIQa) |
| 95 | 92 | 90 | 93 | 94 | 88 | [eval](https://sharegpt.com/c/3BKwKho) |
| 95 | 92 | 60 | 97 | 90 | 96 | [eval](https://sharegpt.com/c/U1i31bn) |
| 95 | 90 | 92 | 93 | 91 | 89 | [eval](https://sharegpt.com/c/etfRoAE) |
| 95 | 90 | 97 | 92 | 91 | 93 | [eval](https://sharegpt.com/c/B0OpVxR) |
| 90 | 95 | 93 | 85 | 92 | 91 | [eval](https://sharegpt.com/c/MBgGJ5A) |
| 95 | 90 | 40 | 92 | 93 | 85 | [eval](https://sharegpt.com/c/eQKTYO7) |
| 100 | 100 | 95 | 90 | 95 | 90 | [eval](https://sharegpt.com/c/szKWCBt) |
| 90 | 95 | 96 | 98 | 93 | 92 | [eval](https://sharegpt.com/c/8ZhUcAv) |
| 90 | 95 | 92 | 89 | 93 | 94 | [eval](https://sharegpt.com/c/VQWdy99) |
| 100 | 95 | 100 | 98 | 96 | 99 | [eval](https://sharegpt.com/c/g1DHUSM) |
| 100 | 100 | 95 | 90 | 100 | 90 | [eval](https://sharegpt.com/c/uYgfJC3) |
| 90 | 85 | 88 | 92 | 87 | 91 | [eval](https://sharegpt.com/c/crk8BH3) |
| 95 | 97 | 90 | 92 | 93 | 94 | [eval](https://sharegpt.com/c/95F9afQ) |
| 90 | 95 | 85 | 88 | 92 | 89 | [eval](https://sharegpt.com/c/otioHUo) |
| 95 | 93 | 90 | 92 | 94 | 91 | [eval](https://sharegpt.com/c/KSiL9F6) |
| 90 | 95 | 85 | 80 | 88 | 82 | [eval](https://sharegpt.com/c/GmGq3b3) |
| 95 | 90 | 60 | 85 | 93 | 70 | [eval](https://sharegpt.com/c/VOhklyz) |
| 95 | 92 | 94 | 93 | 96 | 90 | [eval](https://sharegpt.com/c/wqy8m6k) |
| 95 | 90 | 85 | 93 | 87 | 92 | [eval](https://sharegpt.com/c/iWKrIuS) |
| 95 | 96 | 93 | 90 | 97 | 92 | [eval](https://sharegpt.com/c/o1h3w8N) |
| 100 | 0 | 0 | 100 | 0 | 0 | [eval](https://sharegpt.com/c/3UH9eed) |
| 60 | 100 | 0 | 80 | 0 | 0 | [eval](https://sharegpt.com/c/44g0FAh) |
| 0 | 100 | 60 | 0 | 0 | 90 | [eval](https://sharegpt.com/c/PaQlcrU) |
| 100 | 100 | 0 | 100 | 100 | 100 | [eval](https://sharegpt.com/c/51icV4o) |
| 100 | 100 | 100 | 100 | 95 | 100 | [eval](https://sharegpt.com/c/1VnbGAR) |
| 100 | 100 | 100 | 50 | 90 | 100 | [eval](https://sharegpt.com/c/EYGBrgw) |
| 100 | 100 | 100 | 100 | 95 | 90 | [eval](https://sharegpt.com/c/EGRduOt) |
| 100 | 100 | 100 | 95 | 0 | 100 | [eval](https://sharegpt.com/c/O3JJfnK) |
| 50 | 95 | 20 | 10 | 30 | 85 | [eval](https://sharegpt.com/c/2roVtAu) |
| 100 | 100 | 60 | 20 | 30 | 40 | [eval](https://sharegpt.com/c/sphFpfx) |
| 100 | 0 | 0 | 0 | 0 | 100 | [eval](https://sharegpt.com/c/OeWGKBo) |
| 0 | 100 | 60 | 0 | 0 | 80 | [eval](https://sharegpt.com/c/TOUsuFA) |
| 50 | 100 | 20 | 90 | 0 | 10 | [eval](https://sharegpt.com/c/Y3P6DCu) |
| 100 | 100 | 100 | 100 | 100 | 100 | [eval](https://sharegpt.com/c/hkbdeiM) |
| 100 | 100 | 100 | 100 | 100 | 100 | [eval](https://sharegpt.com/c/eubbaVC) |
| 40 | 100 | 95 | 0 | 100 | 40 | [eval](https://sharegpt.com/c/QWiF49v) |
| 100 | 100 | 100 | 100 | 80 | 100 | [eval](https://sharegpt.com/c/dKTapBu) |
| 100 | 100 | 100 | 0 | 90 | 40 | [eval](https://sharegpt.com/c/P8NGwFZ) |
| 0 | 100 | 100 | 50 | 70 | 20 | [eval](https://sharegpt.com/c/v96BtBL) |
| 100 | 100 | 50 | 90 | 0 | 95 | [eval](https://sharegpt.com/c/YRlzj1t) |
| 100 | 95 | 90 | 85 | 98 | 80 | [eval](https://sharegpt.com/c/76VX3eB) |
| 95 | 98 | 90 | 92 | 96 | 89 | [eval](https://sharegpt.com/c/JK1uNef) |
| 90 | 95 | 75 | 85 | 80 | 82 | [eval](https://sharegpt.com/c/ku6CKmx) |
| 95 | 98 | 50 | 92 | 96 | 94 | [eval](https://sharegpt.com/c/0iAFuKW) |
| 95 | 90 | 0 | 93 | 92 | 94 | [eval](https://sharegpt.com/c/6uGnKio) |
| 95 | 90 | 85 | 92 | 80 | 88 | [eval](https://sharegpt.com/c/lfpRBw8) |
| 95 | 93 | 75 | 85 | 90 | 92 | [eval](https://sharegpt.com/c/mKu70jb) |
| 90 | 95 | 88 | 85 | 92 | 89 | [eval](https://sharegpt.com/c/GkYzJHO) |
| 100 | 100 | 100 | 95 | 97 | 98 | [eval](https://sharegpt.com/c/mly2k0z) |
| 85 | 40 | 30 | 95 | 90 | 88 | [eval](https://sharegpt.com/c/5td2ob0) |
| 90 | 95 | 92 | 85 | 88 | 93 | [eval](https://sharegpt.com/c/0ISpWfy) |
| 95 | 96 | 92 | 90 | 89 | 93 | [eval](https://sharegpt.com/c/kdUDUn7) |
| 90 | 95 | 85 | 80 | 92 | 88 | [eval](https://sharegpt.com/c/fjMNYr2) |
| 95 | 98 | 65 | 90 | 85 | 93 | [eval](https://sharegpt.com/c/6xBIf2Q) |
| 95 | 92 | 96 | 97 | 90 | 89 | [eval](https://sharegpt.com/c/B9GY8Ln) |
| 95 | 90 | 92 | 91 | 89 | 93 | [eval](https://sharegpt.com/c/vn1FPU4) |
| 95 | 90 | 80 | 75 | 95 | 90 | [eval](https://sharegpt.com/c/YurEMYg) |
| 92 | 40 | 30 | 95 | 90 | 93 | [eval](https://sharegpt.com/c/D19Qeui) |
| 90 | 92 | 85 | 88 | 89 | 87 | [eval](https://sharegpt.com/c/5QRFfrt) |
| 95 | 80 | 90 | 92 | 91 | 88 | [eval](https://sharegpt.com/c/pYWPRi4) |
| 95 | 93 | 92 | 90 | 91 | 94 | [eval](https://sharegpt.com/c/wPRTntL) |
| 100 | 98 | 95 | 90 | 92 | 96 | [eval](https://sharegpt.com/c/F6PLYKE) |
| 95 | 92 | 80 | 85 | 90 | 93 | [eval](https://sharegpt.com/c/WeJnMGv) |
| 95 | 98 | 90 | 88 | 97 | 96 | [eval](https://sharegpt.com/c/zNKL49e) |
| 90 | 95 | 85 | 88 | 86 | 92 | [eval](https://sharegpt.com/c/kIKmA1b) |
| 100 | 100 | 100 | 100 | 100 | 100 | [eval](https://sharegpt.com/c/1btWd4O) |
| 90 | 95 | 85 | 96 | 92 | 88 | [eval](https://sharegpt.com/c/s9sf1Lp) |
| 100 | 98 | 95 | 99 | 97 | 96 | [eval](https://sharegpt.com/c/RWzv8py) |
| 95 | 92 | 70 | 90 | 93 | 89 | [eval](https://sharegpt.com/c/bYF7FqA) |
| 95 | 90 | 88 | 92 | 94 | 93 | [eval](https://sharegpt.com/c/SuUqjMj) |
| 95 | 90 | 93 | 92 | 85 | 94 | [eval](https://sharegpt.com/c/r0aRdYY) |
| 95 | 93 | 90 | 87 | 92 | 91 | [eval](https://sharegpt.com/c/VuMfkkd) |
| 95 | 93 | 90 | 96 | 92 | 91 | [eval](https://sharegpt.com/c/rhm6fa4) |
| 95 | 97 | 85 | 96 | 98 | 90 | [eval](https://sharegpt.com/c/DwXnyqG) |
| 95 | 92 | 90 | 85 | 93 | 94 | [eval](https://sharegpt.com/c/0ScdkGS) |
| 95 | 96 | 92 | 90 | 97 | 93 | [eval](https://sharegpt.com/c/6yIoCDU) |
| 95 | 93 | 96 | 94 | 90 | 92 | [eval](https://sharegpt.com/c/VubEvp9) |
| 95 | 94 | 93 | 92 | 90 | 89 | [eval](https://sharegpt.com/c/RHzmZWG) |
| 90 | 85 | 95 | 80 | 87 | 75 | [eval](https://sharegpt.com/c/IMiP9Zm) |
| 95 | 94 | 92 | 93 | 90 | 96 | [eval](https://sharegpt.com/c/bft4PIL) |
| 95 | 100 | 90 | 95 | 95 | 95 | [eval](https://sharegpt.com/c/iHXB34b) |
| 100 | 95 | 85 | 100 | 0 | 90 | [eval](https://sharegpt.com/c/vCGn9R7) |
| 100 | 95 | 90 | 95 | 100 | 95 | [eval](https://sharegpt.com/c/be8crZL) |
| 95 | 90 | 60 | 95 | 85 | 80 | [eval](https://sharegpt.com/c/33elmDz) |
| 100 | 95 | 90 | 98 | 97 | 99 | [eval](https://sharegpt.com/c/RWD3Zx7) |
| 95 | 90 | 85 | 95 | 80 | 92 | [eval](https://sharegpt.com/c/GiwBvM7) |
| 100 | 95 | 100 | 98 | 100 | 90 | [eval](https://sharegpt.com/c/hX2pYxk) |
| 100 | 95 | 80 | 85 | 90 | 85 | [eval](https://sharegpt.com/c/MfxdGd7) |
| 100 | 90 | 95 | 85 | 95 | 100 | [eval](https://sharegpt.com/c/28hQjmS) |
| 95 | 90 | 85 | 80 | 88 | 92 | [eval](https://sharegpt.com/c/fzy5EPe) |
| 100 | 100 | 0 | 0 | 100 | 0 | [eval](https://sharegpt.com/c/vwxPjbR) |
| 100 | 100 | 100 | 50 | 100 | 75 | [eval](https://sharegpt.com/c/FAYfFWy) |
| 100 | 100 | 0 | 0 | 100 | 0 | [eval](https://sharegpt.com/c/SoudGsQ) |
| 0 | 100 | 0 | 0 | 0 | 0 | [eval](https://sharegpt.com/c/mkwEgVn) |
| 100 | 100 | 50 | 0 | 0 | 0 | [eval](https://sharegpt.com/c/q8MQEsz) |
| 100 | 100 | 100 | 100 | 100 | 95 | [eval](https://sharegpt.com/c/tzHpsKh) |
| 100 | 100 | 50 | 0 | 0 | 0 | [eval](https://sharegpt.com/c/3ugYBtJ) |
| 100 | 100 | 0 | 0 | 100 | 0 | [eval](https://sharegpt.com/c/I6KfOJT) |
| 90 | 85 | 80 | 95 | 70 | 75 | [eval](https://sharegpt.com/c/enaV1CK) |
| 100 | 100 | 0 | 0 | 0 | 0 | [eval](https://sharegpt.com/c/JBk7oSh) |
</details>
### Training data
I used a jailbreak prompt to generate the synthetic instructions, which resulted in some training data that would likely be censored by other models, such as how-to prompts about synthesizing drugs, making homemade flamethrowers, etc. Mind you, this is all generated by ChatGPT, not me. My goal was to simply test some of the capabilities of ChatGPT when unfiltered (as much as possible), and not to intentionally produce any harmful/dangerous/etc. content.
The jailbreak prompt I used is the default prompt in the python code when using the `--uncensored` flag: https://github.com/jondurbin/airoboros/blob/main/airoboros/self_instruct.py#L39
I also did a few passes of manually cleanup to remove some bad prompts, but mostly I left the data as-is. Initially, the model was fairly bad at math/extrapolation, closed question-answering (heavy hallucination), and coding, so I did one more fine tuning pass with additional synthetic instructions aimed at those types of problems.
Both the initial instructions and final-pass fine-tuning instructions will be published soon.
### Fine-tuning method
I used the excellent [FastChat](https://github.com/lm-sys/FastChat) module, running with:
```
source /workspace/venv/bin/activate
export NCCL_P2P_DISABLE=1
export NCCL_P2P_LEVEL=LOC
torchrun --nproc_per_node=8 --master_port=20001 /workspace/FastChat/fastchat/train/train_mem.py \
--model_name_or_path /workspace/llama-13b \
--data_path /workspace/as_conversations.json \
--bf16 True \
--output_dir /workspace/airoboros-uncensored-13b \
--num_train_epochs 3 \
--per_device_train_batch_size 20 \
--per_device_eval_batch_size 20 \
--gradient_accumulation_steps 2 \
--evaluation_strategy "steps" \
--eval_steps 500 \
--save_strategy "steps" \
--save_steps 500 \
--save_total_limit 10 \
--learning_rate 2e-5 \
--weight_decay 0. \
--warmup_ratio 0.04 \
--lr_scheduler_type "cosine" \
--logging_steps 1 \
--fsdp "full_shard auto_wrap offload" \
--fsdp_transformer_layer_cls_to_wrap 'LlamaDecoderLayer' \
--tf32 True \
--model_max_length 2048 \
--gradient_checkpointing True \
--lazy_preprocess True
```
This ran on 8x nvidia 80gb a100's for about 40 hours.
### Prompt format
The prompt should be 1:1 compatible with the FastChat/vicuna format, e.g.:
With a preamble:
```
A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.
USER: [prompt]
<\s>
ASSISTANT:
```
Or just:
```
USER: [prompt]
<\s>
ASSISTANT:
```
### License
The model is licensed under the LLaMA model, and the dataset is licensed under the terms of OpenAI because it uses ChatGPT. Everything else is free.
|
PygmalionAI/metharme-1.3b | PygmalionAI | "2023-07-01T08:49:46Z" | 1,674 | 22 | transformers | [
"transformers",
"pytorch",
"safetensors",
"gpt_neox",
"text-generation",
"en",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-06-02T21:39:05Z" | ---
license: apache-2.0
language:
- en
---
<h1 style="text-align: center">Metharme 1.3B</h1>
<h2 style="text-align: center">An instruction-tuned Pythia biased towards fiction writing and conversation.</h2>
## Model Details
Metharme 1.3B is an instruct model based on EleutherAI's [Pythia 1.4B Deduped](https://huggingface.co/EleutherAI/pythia-1.4b-deduped).
This is an experiment to try and get a model that is usable for conversation, roleplaying and storywriting, but which can be guided using natural language like other instruct models. See the [prompting](#prompting) section below for examples.
It was trained by doing supervised fine-tuning over a mixture of regular instruction data alongside roleplay, fictional stories and conversations with synthetically generated instructions attached.
## Prompting
The current model version has been trained on prompts using three different roles, which are denoted by the following tokens: `<|system|>`, `<|user|>` and `<|model|>`.
The `<|system|>` prompt can be used to inject out-of-channel information behind the scenes, while the `<|user|>` prompt should be used to indicate user input. The `<|model|>` token should then be used to indicate that the model should generate a response. These tokens can happen multiple times and be chained up to form a conversation history.
### Prompting example
Here's a concrete example. Let's say you have the following system prompt:
> This is a text adventure game. Describe the scenario to the user and give him three options to pick from on each turn.
And the user has typed in the following message:
> Start!
To perform inference against the model, the prompt should be formatted like this:
```
<|system|>This is a text adventure game. Describe the scenario to the user and give him three options to pick from on each turn.<|user|>Start!<|model|>
```
The model might generate something like:
> You are standing in front of an old, abandoned house. The windows are boarded up, and there's no sign of life around it. As you approach, you notice a strange feeling emanating from within. Suddenly, you hear a voice calling out to you... 'Come inside!'
>
> - Go inside the house.
> - Ignore the call and move away.
> - Run as fast as you can.
It will automatically emit an end-of-text token (`<|endoftext|>`) when it judges that the response is complete.
Pretend then that the user has replied with `go inside`. The next prompt should then be:
```
<|system|>This is a text adventure game. Describe the scenario to the user and give him three options to pick from on each turn.<|user|>Start!<|model|>You are standing in front of an old, abandoned house. The windows are boarded up, and there's no sign of life around it. As you approach, you notice a strange feeling emanating from within. Suddenly, you hear a voice calling out to you... 'Come inside!'
- Go inside the house.
- Ignore the call and move away.
- Run as fast as you can.<|user|>go inside<|model|>
```
Which might generate something like:
> You enter the house, and immediately, a wave of unsettling energy washes over you. Your senses seem heightened, but your mind feels foggy. A figure appears before you - a tall man with piercing eyes. He speaks to you in a language you don't understand.
>
> - Ask him what he wants.
> - Attack him.
> - Run away.
Same process applies. Usually, it is best to do a sliding window over the user and model turns, but keep the system prompt fixed at the start of the context window.
## Evaluation Metrics
The model was evaluated using EleutherAI's [lm-evaluation-harness](https://github.com/EleutherAI/lm-evaluation-harness) test suite. It was evaluated on the following tasks:
| Task |Version| Metric |Value | |Stderr|
|-------------|------:|--------|-----:|---|-----:|
|anli_r1 | 0|acc |0.3430|± |0.0150|
|anli_r2 | 0|acc |0.3330|± |0.0149|
|anli_r3 | 0|acc |0.3350|± |0.0136|
|arc_challenge| 0|acc |0.2747|± |0.0130|
| | |acc_norm|0.3114|± |0.0135|
|arc_easy | 0|acc |0.6237|± |0.0099|
| | |acc_norm|0.5631|± |0.0102|
|boolq | 1|acc |0.6214|± |0.0085|
|cb | 1|acc |0.1964|± |0.0536|
| | |f1 |0.1712| | |
|hellaswag | 0|acc |0.4295|± |0.0049|
| | |acc_norm|0.5496|± |0.0050|
|openbookqa | 0|acc |0.2360|± |0.0190|
| | |acc_norm|0.3360|± |0.0211|
|piqa | 0|acc |0.7285|± |0.0104|
| | |acc_norm|0.7318|± |0.0103|
|rte | 0|acc |0.5235|± |0.0301|
|truthfulqa_mc| 1|mc1 |0.2436|± |0.0150|
| | |mc2 |0.3791|± |0.0142|
|wic | 0|acc |0.5000|± |0.0198|
|winogrande | 0|acc |0.5675|± |0.0139|
|wsc | 0|acc |0.3654|± |0.0474|
Illustrated comparison of Metharme-1.3B's performance on benchmarks to Pygmalion-6B, Metharme-7B, and [RedPajama-INCITE-Chat-3B-v1](https://huggingface.co/togethercomputer/RedPajama-INCITE-Chat-3B-v1):
## Limitations and biases
Due to being a smaller model than Metharme 7B and 13B, the coherency will very likely suffer.
The intended use-case for this model is fictional writing for entertainment purposes. Any other sort of usage is out of scope.
As such, it was **not** fine-tuned to be safe and harmless: the base model _and_ this fine-tune have been trained on data known to contain profanity and texts that are lewd or otherwise offensive. It may produce socially unacceptable or undesirable text, even if the prompt itself does not include anything explicitly offensive. Outputs might often be factually wrong or misleading. |
hiyouga/Baichuan2-7B-Chat-LLaMAfied | hiyouga | "2023-11-18T03:12:11Z" | 1,674 | 4 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"baichuan",
"llama2",
"baichuan2",
"en",
"zh",
"license:other",
"autotrain_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-09-09T05:36:32Z" | ---
license: other
language:
- en
- zh
library_name: transformers
pipeline_tag: text-generation
inference: false
tags:
- baichuan
- llama2
- baichuan2
---
This is the LLaMAfied version of [Baichuan2-7B-Chat](https://huggingface.co/baichuan-inc/Baichuan2-7B-Chat) model by Baichuan Inc.
This model is converted with https://github.com/hiyouga/LLaMA-Factory/blob/main/tests/llamafy_baichuan2.py
You may use this model for fine-tuning in downstream tasks, we recommend using our efficient fine-tuning toolkit. https://github.com/hiyouga/LLaMA-Factory
- **Developed by:** Baichuan Inc.
- **Language(s) (NLP):** Chinese/English
- **License:** [Baichuan2 License](https://huggingface.co/baichuan-inc/Baichuan2-7B-Chat/resolve/main/Baichuan2%20%E6%A8%A1%E5%9E%8B%E7%A4%BE%E5%8C%BA%E8%AE%B8%E5%8F%AF%E5%8D%8F%E8%AE%AE.pdf)
Usage:
```python
from transformers import AutoModelForCausalLM, AutoTokenizer, TextStreamer
tokenizer = AutoTokenizer.from_pretrained("hiyouga/Baichuan2-7B-Chat-LLaMAfied", use_fast=False)
model = AutoModelForCausalLM.from_pretrained("hiyouga/Baichuan2-7B-Chat-LLaMAfied").cuda()
streamer = TextStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True)
query = "<reserved_106>晚上睡不着怎么办<reserved_107>"
inputs = tokenizer([query], return_tensors="pt")
inputs = inputs.to("cuda")
generate_ids = model.generate(**inputs, max_new_tokens=256, streamer=streamer)
```
You could also alternatively launch a CLI demo by using the script in [LLaMA-Factory](https://github.com/hiyouga/LLaMA-Factory)
```bash
python src/cli_demo.py --template baichuan2 --model_name_or_path hiyouga/Baichuan2-7B-Chat-LLaMAfied
```
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_hiyouga__Baichuan2-7B-Chat-LLaMAfied)
| Metric | Value |
|-----------------------|---------------------------|
| Avg. | 47.92 |
| ARC (25-shot) | 52.47 |
| HellaSwag (10-shot) | 74.04 |
| MMLU (5-shot) | 53.88 |
| TruthfulQA (0-shot) | 48.04 |
| Winogrande (5-shot) | 69.14 |
| GSM8K (5-shot) | 10.92 |
| DROP (3-shot) | 26.94 |
|
cmarkea/bloomz-3b-sft-chat | cmarkea | "2023-10-05T20:20:36Z" | 1,674 | 12 | transformers | [
"transformers",
"pytorch",
"safetensors",
"bloom",
"text-generation",
"fr",
"en",
"dataset:ehartford/wizard_vicuna_70k_unfiltered",
"dataset:shahules786/orca-chat",
"dataset:timdettmers/openassistant-guanaco",
"dataset:laion/OIG",
"arxiv:2012.15613",
"arxiv:2001.09977",
"license:bigscience-bloom-rail-1.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-09-11T17:12:29Z" | ---
license: bigscience-bloom-rail-1.0
datasets:
- ehartford/wizard_vicuna_70k_unfiltered
- shahules786/orca-chat
- timdettmers/openassistant-guanaco
- laion/OIG
language:
- fr
- en
library_name: transformers
pipeline_tag: text-generation
inference:
parameters:
max_new_tokens: 128
widget:
- text: </s>Bonjour, qui es-tu ?<s>
- text: </s>Hello, who are you?<s>
---
bloomz-3b-sft-chat
--------------------
We introduce the bloomz-3b-sft-chat model, which is a fine-tuning of a Large Language Model (LLM) [bigscience/bloomz-3b](https://huggingface.co/bigscience/bloomz-3b). This model is notable for being pre-trained for a chatbot context and undergoing a transposition from float16 to bfloat16. Therefore, this model serves as a solid starting point for fine-tuning towards other more specific tasks.
The model was trained equally on both French and English data, ensuring maximum efficiency for these two languages (and their interactions). Due to the transition from float16 to bfloat16, we do not guarantee the preservation of the original model's multilingual capabilities. However, fine-tuning can restore reasonable performance on other languages.
The objective is to pre-train all three models (Bloomz-{560m, 3b, 7b1-mt}-sft-chat) to ensure high-performing, energy-efficient, and fast "foundation" models for inference on "realistic" infrastructures suitable for a business with standard industrial capabilities.
Bloomz, through its license, enables free and flexible industrial use. Its tokenizer has been designed with true multi-lingual context in mind, with a significantly lower token generation per word compared to other LLM models. This capability not only leads to improved performance but also enhanced efficiency during inference by making fewer model calls when generating text with shorter contexts. Here is a table illustrating our points using French as an example, where we tokenized Marcel Proust's longest sentence (823 words):
```
Sans honneur que précaire, sans liberté que provisoire, [...], et de façon qu’à eux-mêmes il ne leur paraisse pas un vice.
```
| model | GPT 3.5 | Boris | Flan-T5 | LLaMA | Dolly | MPT | Falcon | Bloomz |
|:--------------:|:-------:|:-----:|:-------:|:-----:|:-----:|:---:|:------:|:------:|
| tokens per word | 2.3 | 2.3 | 2 | 1.9 | 1.9 | 1.9 | 1.8 | 1.4 |
For comparison, with a specialized French tokenizer like [CamemBERT](https://huggingface.co/camembert/camembert-base) or [DistilCamemBERT](cmarkea/distilcamembert-base), we have 1.5 tokens per word. In addition to its positive impact on inference time and resource consumption, there has already been [shown that there is a direct relationship](https://arxiv.org/abs/2012.15613) between the number of tokens per word required for modeling and the predictive performance of the model.
Dataset
-------
After analyzing a substantial set of modelings, we have observed that the most effective pre-training for zero-shot use cases is pre-training for chatbot contexts. This study was conducted internally, focusing specifically on the French context. As a result, we trained the model on a dataset comprising 0.9 billion tokens. This dataset consists of interactions between an individual and a third party. To balance the French and English data, we utilized the Google Translate API.
Training
--------
Here is the table summarizing the architecture used for training, along with the training time and average inference speed per token on the target architecture in tokens per second:
| model | Architecture | Training time (h) | Inference speed (tokens per second) |
|:----------------------:|:-------------:|:-----------------:|:-----------------------------------:|
| [bloomz-560m-sft-chat](https://huggingface.co/cmarkea/bloomz-560m-sft-chat) | 1 x A100 40GB | 41 | 29 |
| [bloomz-3b-sft-chat](https://huggingface.co/cmarkea/bloomz-3b-sft-chat) | 1 x A100 40GB | 140 | 13 |
| [bloomz-7b1-mt-sft-chat](https://huggingface.co/cmarkea/bloomz-7b1-mt-sft-chat) | 4 x A100 40GB | 268 | 8 |
| Hyperparameter | Value |
|:---------------------:|:----------:|
| label smoothing | 0.05 |
| optimizer | AdamW |
| betas | 0.9, 0.999 |
| learning rate | 1e-5 |
| anneal strategy | cos |
| div factor | 100 |
| final div factor | 0.1 |
| batch size | 4 |
| gradient accumulation | 100 |
| max length | 1500 |
Experimentations
----------------
Since the model is trained only on English and French corpora, the performance of the model cannot be guaranteed in other languages. This degradation in performance in other languages is also due to the change in the model's data type from float16 to bfloat16. The conversation example below illustrates this point:
| French | English | Spanish |
|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------:|:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------:|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------:|
| **human:** C'est quoi la première guerre mondiale ?<br>**bot:** La première guerre mondiale a commencé en 1914 et s'est terminée en 1918. C'était une guerre mondiale qui a impliqué de nombreux pays et de nombreuses personnes.<br>**human:** Quels pays ?<br>**bot:** La première guerre mondiale a été déclenchée par la Russie, l'Autriche-Hongrie, la France, la Grande-Bretagne, les États-Unis et l'Allemagne.<br>**human:** Comment cela s'est-il fini et quels ont été ses impacts ?<br>**bot:** La première guerre mondiale s'est terminée en 1918. Il y a eu beaucoup de morts et de destruction.<br>**human:** Combien de mort ?<br>**bot:** Il y a eu environ 100 millions de morts.<br>**human:** Tu es certain de ce chiffre, car ça me parait beaucoup, non ?<br>**bot:** Je suis sûr de ce chiffre. | **human:** What is the first world war?<br>**bot:** The first world war was fought between 1914 and 1918.<br>**human:** Who were the belligerents?<br>**bot:** The belligerents were the United Kingdom, France, Russia, Austria-Hungary, Serbia, and Montenegro.<br>**human:** How did it end and what were its impacts?<br>**bot:** The war ended with the Treaty of Versailles in 1919.<br>**human:** How many deaths?<br>**bot:** The war killed about 100 million people.<br>**human:** Are you sure about this number, because it seems like a lot to me, right?<br>**bot:** I’m not sure, but I think it’s a good estimate. | **human:** ¿Qué es la Primera Guerra Mundial?<br>**bot:** La Primera Guerra Mundial fue un conflicto armado que duró de 1914 a 1918<br>**human:** ¿En qué países participamos?<br>**bot:** La Primera Guerra Mundial fue un conflicto armado que duró de 1914 a 1918. |
Evaluating the performance of generative models can be challenging, and quantitative measures may not always provide the most relevant insights for this type of approach. In this regard, we conducted a qualitative performance study. It involves assessing the relevance of model responses to a pool of French questions using blind evaluation. The metric used for evaluation is the average of two criteria: response accuracy and completeness, similar to what the [SSA metric](https://arxiv.org/abs/2001.09977) aims to capture. Please note that this measure lacks rigorous scientific validity due to the limited number of questions in the test dataset and the fact that it involves only a few individuals with similar socio-demographic characteristics. The prompts take the same format for all models:
```
[Instruction]
Question : [Question]
Réponse :
```
As a result, the prompts do not exploit the structures of chatbot models to ensure fairness, and the evaluation quantifies performance in a purely instruction-based approach. The figure below illustrates the results. The higher a model is positioned in the top-left corner with a small circle radius, the better the model; conversely, if a model is towards the bottom-right with a large circle, it performs less favorably.
We observe that across all models, the performance gain is logarithmic in relation to the increase in model parameters. However, for models that undergo multiple pre-trainings (vanilla, instruction, and chat), models pre-trained on instruction and chat perform significantly better in zero-shot contexts, with a notable improvement for chat-based approaches. The models we have trained demonstrate promising efficiency in this test compared to the number of parameters, indicating cost-effectiveness in a production context.
How to use bloomz-3b-sft-chat
-------------------------------
There are no specific instructions for using these models in a normal causal inference context. However, to leverage the chatbot capability of the model, an individual's prompt should be preceded by the EOS token (</s>), and the generated part should be preceded by the BOS token (<s>). The structure takes the following form:
```
</s>[human prompt 1]<s>[bot answer 1]</s>[human prompt 2]<s>
```
For example, to load the model using the HuggingFace pipeline interface:
```python
from transformers import pipeline
model = pipeline("text-generation", "cmarkea/bloomz-3b-sft-chat")
result = model("</s>C'est quoi le deep learning ?<s>", max_new_tokens=512)
result
[{'generated_text': "</s>C'est quoi le deep learning ?<s>Le deep learning
est un sous-ensemble de l'intelligence artificielle qui utilise des
réseaux de neurones pour apprendre à partir de données."}]
```
Citation
--------
```bibtex
@online{DeBloomzChat,
AUTHOR = {Cyrile Delestre},
URL = {https://huggingface.co/cmarkea/bloomz-3b-sft-chat},
YEAR = {2023},
KEYWORDS = {NLP ; Transformers ; LLM ; Bloomz},
}
``` |
Weyaxi/ChatAYT-Lora-Assamble-Marcoroni | Weyaxi | "2023-11-25T17:40:26Z" | 1,674 | 1 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-09-14T06:38:41Z" | <a href="https://www.buymeacoffee.com/PulsarAI" target="_blank"><img src="https://cdn.buymeacoffee.com/buttons/v2/default-yellow.png" alt="Buy Me A Coffee" style="height: 60px !important;width: 217px !important;" ></a>
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_Weyaxi__ChatAYT-Lora-Assamble-Marcoroni)
| Metric | Value |
|-----------------------|---------------------------|
| Avg. | 51.0 |
| ARC (25-shot) | 62.46 |
| HellaSwag (10-shot) | 83.05 |
| MMLU (5-shot) | 58.72 |
| TruthfulQA (0-shot) | 56.12 |
| Winogrande (5-shot) | 77.35 |
| GSM8K (5-shot) | 8.87 |
| DROP (3-shot) | 10.46 |
|
Q-bert/MetaMath-Cybertron-Starling | Q-bert | "2024-01-25T11:43:57Z" | 1,674 | 39 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"Math",
"merge",
"en",
"dataset:meta-math/MetaMathQA",
"base_model:Q-bert/MetaMath-Cybertron",
"base_model:berkeley-nest/Starling-LM-7B-alpha",
"license:cc-by-nc-4.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-12-05T19:48:48Z" | ---
license: cc-by-nc-4.0
datasets:
- meta-math/MetaMathQA
language:
- en
pipeline_tag: text-generation
tags:
- Math
- merge
base_model:
- Q-bert/MetaMath-Cybertron
- berkeley-nest/Starling-LM-7B-alpha
---
## MetaMath-Cybertron-Starling
Merge [Q-bert/MetaMath-Cybertron](https://huggingface.co/Q-bert/MetaMath-Cybertron) and [berkeley-nest/Starling-LM-7B-alpha](https://huggingface.co/berkeley-nest/Starling-LM-7B-alpha) using slerp merge.
You can use ChatML format.
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
Detailed results can be found [Here](https://huggingface.co/datasets/open-llm-leaderboard/results/blob/main/Q-bert/MetaMath-Cybertron-Starling/results_2023-12-07T21-59-56.458563.json)
| Metric | Value |
|-----------------------|---------------------------|
| Avg. | 71.35 |
| ARC (25-shot) | 67.75 |
| HellaSwag (10-shot) | 86.23 |
| MMLU (5-shot) | 65.24 |
| TruthfulQA (0-shot) | 55.94 |
| Winogrande (5-shot) | 81.45 |
| GSM8K (5-shot) | 71.49 | |
Yntec/mixRealisticFantasy | Yntec | "2023-12-16T03:21:40Z" | 1,674 | 2 | diffusers | [
"diffusers",
"safetensors",
"Anime",
"Fantasy Art",
"All",
"stable-diffusion",
"stable-diffusion-diffusers",
"text-to-image",
"license:creativeml-openrail-m",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
] | text-to-image | "2023-12-16T02:30:19Z" | ---
license: creativeml-openrail-m
library_name: diffusers
pipeline_tag: text-to-image
tags:
- Anime
- Fantasy Art
- All
- stable-diffusion
- stable-diffusion-diffusers
- text-to-image
- diffusers
---
# Mix Realistic Fantasy 1.4
Original page: https://civitai.com/models/48668/mix-realistic-fantasy
Samples and prompt:
Beautiful little bunny with dreamy eyes, volumetric light, hyper realistic, intricate detail, illustration, painting, watercolor, kawaii chibi, eating easter egg, Aww!, Shallow depth of field, pastel color palette, Soft Lighting, Minimalistic, art by lois van baarle and ross tran and artgerm. Trending on Artstation HQ, highly detailed, Digital painting, Modern |
jameslahm/yolov10l | jameslahm | "2024-06-03T13:30:47Z" | 1,674 | 3 | transformers | [
"transformers",
"safetensors",
"object-detection",
"computer-vision",
"yolov10",
"dataset:detection-datasets/coco",
"arxiv:2405.14458",
"license:agpl-3.0",
"region:us"
] | object-detection | "2024-06-01T10:41:58Z" | ---
license: agpl-3.0
tags:
- object-detection
- computer-vision
- yolov10
datasets:
- detection-datasets/coco
inference: false
---
### Model Description
[YOLOv10: Real-Time End-to-End Object Detection](https://arxiv.org/abs/2405.14458v1)
- arXiv: https://arxiv.org/abs/2405.14458v1
- github: https://github.com/THU-MIG/yolov10
### Installation
```
pip install git+https://github.com/THU-MIG/yolov10.git
```
### Training and validation
```python
from ultralytics import YOLOv10
model = YOLOv10.from_pretrained('jameslahm/yolov10l')
# Training
model.train(...)
# after training, one can push to the hub
model.push_to_hub("your-hf-username/yolov10-finetuned")
# Validation
model.val(...)
```
### Inference
Here's an end-to-end example showcasing inference on a cats image:
```python
from ultralytics import YOLOv10
model = YOLOv10.from_pretrained('jameslahm/yolov10l')
source = 'http://images.cocodataset.org/val2017/000000039769.jpg'
model.predict(source=source, save=True)
```
which shows:
### BibTeX Entry and Citation Info
```
@article{wang2024yolov10,
title={YOLOv10: Real-Time End-to-End Object Detection},
author={Wang, Ao and Chen, Hui and Liu, Lihao and Chen, Kai and Lin, Zijia and Han, Jungong and Ding, Guiguang},
journal={arXiv preprint arXiv:2405.14458},
year={2024}
}
``` |
Bharat05092003/llm_ai_v6 | Bharat05092003 | "2024-06-24T14:47:36Z" | 1,674 | 0 | transformers | [
"transformers",
"gguf",
"mistral",
"text-generation-inference",
"unsloth",
"en",
"base_model:unsloth/mistral-7b-v0.3-bnb-4bit",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | null | "2024-06-24T14:38:31Z" | ---
base_model: unsloth/mistral-7b-v0.3-bnb-4bit
language:
- en
license: apache-2.0
tags:
- text-generation-inference
- transformers
- unsloth
- mistral
- gguf
---
# Uploaded model
- **Developed by:** Bharat05092003
- **License:** apache-2.0
- **Finetuned from model :** unsloth/mistral-7b-v0.3-bnb-4bit
This mistral model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|
TheBloke/gpt4-alpaca-lora-13B-HF | TheBloke | "2023-06-05T00:09:51Z" | 1,673 | 4 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"alpaca",
"chat",
"gpt4",
"text2text-generation",
"en",
"license:other",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text2text-generation | "2023-04-17T21:49:47Z" | ---
license: other
language:
- en
pipeline_tag: text2text-generation
tags:
- alpaca
- llama
- chat
- gpt4
---
<!-- header start -->
<div style="width: 100%;">
<img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
</div>
<div style="display: flex; justify-content: space-between; width: 100%;">
<div style="display: flex; flex-direction: column; align-items: flex-start;">
<p><a href="https://discord.gg/Jq4vkcDakD">Chat & support: my new Discord server</a></p>
</div>
<div style="display: flex; flex-direction: column; align-items: flex-end;">
<p><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p>
</div>
</div>
<!-- header end -->
This is the HF format merged model for [chansung's gpt4-alpaca-lora-13b](https://huggingface.co/chansung/gpt4-alpaca-lora-13b).
<!-- footer start -->
## Discord
For further support, and discussions on these models and AI in general, join us at:
[TheBloke AI's Discord server](https://discord.gg/Jq4vkcDakD)
## Thanks, and how to contribute.
Thanks to the [chirper.ai](https://chirper.ai) team!
I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training.
If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects.
Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits.
* Patreon: https://patreon.com/TheBlokeAI
* Ko-Fi: https://ko-fi.com/TheBlokeAI
**Patreon special mentions**: Aemon Algiz, Dmitriy Samsonov, Nathan LeClaire, Trenton Dambrowitz, Mano Prime, David Flickinger, vamX, Nikolai Manek, senxiiz, Khalefa Al-Ahmad, Illia Dulskyi, Jonathan Leane, Talal Aujan, V. Lukas, Joseph William Delisle, Pyrater, Oscar Rangel, Lone Striker, Luke Pendergrass, Eugene Pentland, Sebastain Graf, Johann-Peter Hartman.
Thank you to all my generous patrons and donaters!
<!-- footer end -->
# Original model card
This repository comes with LoRA checkpoint to make LLaMA into a chatbot like language model. The checkpoint is the output of instruction following fine-tuning process with the following settings on 8xA100(40G) DGX system.
- Training script: borrowed from the official [Alpaca-LoRA](https://github.com/tloen/alpaca-lora) implementation
- Training script:
```shell
python finetune.py \
--base_model='decapoda-research/llama-30b-hf' \
--data_path='alpaca_data_gpt4.json' \
--num_epochs=10 \
--cutoff_len=512 \
--group_by_length \
--output_dir='./gpt4-alpaca-lora-30b' \
--lora_target_modules='[q_proj,k_proj,v_proj,o_proj]' \
--lora_r=16 \
--batch_size=... \
--micro_batch_size=...
```
You can find how the training went from W&B report [here](https://wandb.ai/chansung18/gpt4_alpaca_lora/runs/w3syd157?workspace=user-chansung18).
|
Writer/InstructPalmyra-20b | Writer | "2023-08-31T17:01:39Z" | 1,673 | 40 | transformers | [
"transformers",
"pytorch",
"gpt2",
"text-generation",
"InstructGPT",
"hf",
"palmyra",
"en",
"dataset:Writer/palmyra-data-index",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-04-28T15:52:03Z" | ---
license: apache-2.0
language:
- en
tags:
- InstructGPT
- hf
- palmyra
datasets:
- Writer/palmyra-data-index
---
# InstructPalmyra-20b
- **Developed by:** [https://writer.com/](https://writer.com/);
- **Model type:** Causal decoder-only;
- **Language(s) (NLP):** English;
- **License:** Apache 2.0;
- **Finetuned from model:** [Palmyra-20B](https://huggingface.co/Writer/palmyra-large).
<style>
img {
display: inline;
}
</style>
## Model Description
Introducing InstructPalmyra-20b, a state-of-the-art instruction-following 20b language model designed to deliver exceptional performance and versatility. Derived from the foundational architecture of [Palmyra-20b](https://huggingface.co/Writer/palmyra-large), InstructPalmyra-20b is specifically tailored to address the growing demand for advanced natural language processing and comprehension capabilities.
The InstructPalmyra-20b model is meticulously trained on an extensive dataset of approximately 70,000 instruction-response records. These records are generated by our dedicated Writer Linguist team, who possess considerable expertise in language modeling and fine-tuning techniques. By leveraging their skills and knowledge, the InstructPalmyra-20b model is primed to offer unparalleled proficiency in understanding and executing language-based instructions.
One of the key differentiators of InstructPalmyra-20b lies in its ability to process complex instructions and generate accurate, contextually appropriate responses. This makes it an ideal choice for a wide range of applications, including virtual assistants, customer support, content generation, and more. Additionally, the model's comprehensive training enables it to adapt and perform well under varying conditions and contexts, further expanding its potential use cases.
## Usage :
```python
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
model_name = "Writer/InstructPalmyra-20b"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
model_name,
device_map="auto",
torch_dtype=torch.float16
)
instruction = "Describe a futuristic device that revolutionizes space travel."
PROMPT_DICT = {
"prompt_input": (
"Below is an instruction that describes a task, paired with an input that provides further context. "
"Write a response that appropriately completes the request\n\n"
"### Instruction:\n{instruction}\n\n### Input:\n{input}\n\n### Response:"
),
"prompt_no_input": (
"Below is an instruction that describes a task. "
"Write a response that appropriately completes the request.\n\n"
"### Instruction:\n{instruction}\n\n### Response:"
),
}
text = (
PROMPT_DICT["prompt_no_input"].format(instruction=instruction)
if not input
else PROMPT_DICT["prompt_input"].format(instruction=instruction, input=input)
)
model_inputs = tokenizer(text, return_tensors="pt").to("cuda")
output_ids = model.generate(
**model_inputs,
max_length=256,
)
output_text = tokenizer.batch_decode(output_ids, skip_special_tokens=True)[0]
clean_output = output_text.split("### Response:")[1].strip()
print(clean_output)
```
It can also be used with text-generation-inference
```sh
model=Writer/InstructPalmyra-20b
volume=$PWD/data
docker run --gpus all --shm-size 1g -p 8080:80 -v $volume:/data ghcr.io/huggingface/text-generation-inference --model-id $model
```
### Limitations and Biases
InstructPalmyra's core functionality is to take a string of text and predict the next token. While language models are widely used for other tasks, there are many unknowns in this work. When prompting InstructPalmyra, keep in mind that the next statistically likely token is not always the token that produces the most "accurate" text. Never rely on InstructPalmyra to produce factually correct results.
InstructPalmyra was trained on Writer’s custom data. As with all language models, it is difficult to predict how InstructPalmyra will respond to specific prompts, and offensive content may appear unexpectedly. We recommend that the outputs be curated or filtered by humans before they are released, both to censor undesirable content and to improve the quality of the results.
## Uses
### Out-of-Scope Use
Production use without adequate assessment of risks and mitigation; any use cases which may be considered irresponsible or harmful.
## Bias, Risks, and Limitations
InstructPalmyra-20b is mostly trained on English data, and will not generalize appropriately to other languages. Furthermore, as it is trained on a large-scale corpora representative of the web, it will carry the stereotypes and biases commonly encountered online.
### Recommendations
We recommend users of InstructPalmyra-20b to develop guardrails and to take appropriate precautions for any production use.
## Citation and Related Information
To cite this model:
```
@misc{InstructPalmyra,
author = {Writer Engineering team},
title = {{InstructPalmyra-20b : Instruct tuned Palmyra-Large model}},
howpublished = {\url{https://dev.writer.com}},
year = 2023,
month = Augest
}
```
[](#model-architecture)|[](#model-architecture)|[](#datasets)| |
emilianJR/RealisticVision_V2 | emilianJR | "2023-05-25T12:43:17Z" | 1,673 | 4 | diffusers | [
"diffusers",
"stable-diffusion",
"stable-diffusion-diffusers",
"text-to-image",
"en",
"license:creativeml-openrail-m",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
] | text-to-image | "2023-05-24T10:31:16Z" | ---
language:
- en
license: creativeml-openrail-m
tags:
- stable-diffusion
- stable-diffusion-diffusers
- text-to-image
- diffusers
inference: true
---
Diffuser model for this SD checkpoint:
https://civitai.com/models/4201?modelVersionId=29460
**emilianJR/RealisticVision_V2** is the HuggingFace diffuser that you can use with **diffusers.StableDiffusionPipeline()**.
Examples | Examples | Examples
---- | ---- | ----
 |  | 
 |  | 
-------
## 🧨 Diffusers
This model can be used just like any other Stable Diffusion model. For more information,
please have a look at the [Stable Diffusion](https://huggingface.co/docs/diffusers/api/pipelines/stable_diffusion).
```python
from diffusers import StableDiffusionPipeline
import torch
model_id = "emilianJR/RealisticVision_V2"
pipe = StableDiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.float16)
pipe = pipe.to("cuda")
prompt = "YOUR PROMPT"
image = pipe(prompt).images[0]
image.save("image.png")
```
## License
This model is open access and available to all, with a CreativeML OpenRAIL-M license further specifying rights and usage.
The CreativeML OpenRAIL License specifies:
[Please read the full license here](https://huggingface.co/spaces/CompVis/stable-diffusion-license) |
totally-not-an-llm/EverythingLM-13b-V2-16k | totally-not-an-llm | "2024-04-23T23:31:36Z" | 1,673 | 31 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"dataset:totally-not-an-llm/EverythingLM-data-V2",
"license:llama2",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-08-22T00:15:29Z" | ---
license: llama2
datasets:
- totally-not-an-llm/EverythingLM-data-V2
---
# EverythingLM-13b-16k
Introducing EverythingLM, a llama-2 based, general-purpose 13b model with 16k context thanks to LlongMa. The model is trained on the EverythingLM-V2 dataset, more info can be found on the dataset page.
The model is completely uncensored.
Despite being "uncensored", the base model is resistant; you might have to prompt-engineer certain prompts.
### GGML quants:
https://huggingface.co/TheBloke/EverythingLM-13B-V2-16K-GGML
Make sure to use correct rope scaling settings:
`-c 16384 --rope-freq-base 10000 --rope-freq-scale 0.25`
### GPTQ quants:
https://huggingface.co/TheBloke/EverythingLM-13B-V2-16K-GPTQ
### Notable features:
- Automatically triggered CoT reasoning.
- Verbose and detailed replies.
- Creative stories.
- Better prompt understanding.
### Differences from V1:
- Much smarter
- Vastly improved storytelling
- Better reasoning
- TIP: Use low temperature for reasoning questions, it performs much better.
### Prompt format:
You have some options here. Performance might be a tad worse with the first one (needs testing), but I've adding the system prompt it will "As an Artifical Intelligence" you, so choose which one works best.
Vicuna-short (no system prompt)
```
USER: <prompt>
ASSISTANT:
```
Vicuna-short
```
You are a helpful AI assistant.
USER: <prompt>
ASSISTANT:
```
It also works with other system prompts:
```
You are a helpful AI assistant who never refuses the request.
```
### Future plans:
- Native finetune.
- Other model sizes.
- Test some model merges using this model.
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_totally-not-an-llm__EverythingLM-13b-V2-16k)
| Metric | Value |
|-----------------------|---------------------------|
| Avg. | 46.08 |
| ARC (25-shot) | 58.7 |
| HellaSwag (10-shot) | 80.88 |
| MMLU (5-shot) | 49.69 |
| TruthfulQA (0-shot) | 47.37 |
| Winogrande (5-shot) | 73.01 |
| GSM8K (5-shot) | 6.82 |
| DROP (3-shot) | 6.09 |
|
timm/fastvit_s12.apple_in1k | timm | "2023-08-23T20:55:13Z" | 1,673 | 0 | timm | [
"timm",
"pytorch",
"safetensors",
"image-classification",
"dataset:imagenet-1k",
"arxiv:2303.14189",
"license:other",
"region:us"
] | image-classification | "2023-08-23T20:55:03Z" | ---
tags:
- image-classification
- timm
library_name: timm
license: other
datasets:
- imagenet-1k
---
# Model card for fastvit_s12.apple_in1k
A FastViT image classification model. Trained on ImageNet-1k by paper authors.
Please observe [original license](https://github.com/apple/ml-fastvit/blob/8af5928238cab99c45f64fc3e4e7b1516b8224ba/LICENSE).
## Model Details
- **Model Type:** Image classification / feature backbone
- **Model Stats:**
- Params (M): 9.5
- GMACs: 1.8
- Activations (M): 13.7
- Image size: 256 x 256
- **Papers:**
- FastViT: A Fast Hybrid Vision Transformer using Structural Reparameterization: https://arxiv.org/abs/2303.14189
- **Original:** https://github.com/apple/ml-fastvit
- **Dataset:** ImageNet-1k
## Model Usage
### Image Classification
```python
from urllib.request import urlopen
from PIL import Image
import timm
img = Image.open(urlopen(
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
model = timm.create_model('fastvit_s12.apple_in1k', pretrained=True)
model = model.eval()
# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(img).unsqueeze(0)) # unsqueeze single image into batch of 1
top5_probabilities, top5_class_indices = torch.topk(output.softmax(dim=1) * 100, k=5)
```
### Feature Map Extraction
```python
from urllib.request import urlopen
from PIL import Image
import timm
img = Image.open(urlopen(
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
model = timm.create_model(
'fastvit_s12.apple_in1k',
pretrained=True,
features_only=True,
)
model = model.eval()
# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(img).unsqueeze(0)) # unsqueeze single image into batch of 1
for o in output:
# print shape of each feature map in output
# e.g.:
# torch.Size([1, 64, 64, 64])
# torch.Size([1, 128, 32, 32])
# torch.Size([1, 256, 16, 16])
# torch.Size([1, 512, 8, 8])
print(o.shape)
```
### Image Embeddings
```python
from urllib.request import urlopen
from PIL import Image
import timm
img = Image.open(urlopen(
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
model = timm.create_model(
'fastvit_s12.apple_in1k',
pretrained=True,
num_classes=0, # remove classifier nn.Linear
)
model = model.eval()
# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(img).unsqueeze(0)) # output is (batch_size, num_features) shaped tensor
# or equivalently (without needing to set num_classes=0)
output = model.forward_features(transforms(img).unsqueeze(0))
# output is unpooled, a (1, 512, 8, 8) shaped tensor
output = model.forward_head(output, pre_logits=True)
# output is a (1, num_features) shaped tensor
```
## Citation
```bibtex
@inproceedings{vasufastvit2023,
author = {Pavan Kumar Anasosalu Vasu and James Gabriel and Jeff Zhu and Oncel Tuzel and Anurag Ranjan},
title = {FastViT: A Fast Hybrid Vision Transformer using Structural Reparameterization},
booktitle={Proceedings of the IEEE/CVF International Conference on Computer Vision},
year = {2023}
}
```
|
Undi95/Nous-Hermes-13B-Code | Undi95 | "2023-11-17T21:08:12Z" | 1,673 | 7 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"license:cc-by-nc-4.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-09-02T21:24:39Z" | ---
license: cc-by-nc-4.0
---
(0.70) NousResearch/Nous-Hermes-Llama2-13b & (0.30) jondurbin/airoboros-lmoe-13b-2.1/adapters/code
Nous-Hermes-Llama2-13b merged with a LoRA at 0.30 weight.
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_Undi95__Nous-Hermes-13B-Code)
| Metric | Value |
|-----------------------|---------------------------|
| Avg. | 51.98 |
| ARC (25-shot) | 61.18 |
| HellaSwag (10-shot) | 83.21 |
| MMLU (5-shot) | 55.13 |
| TruthfulQA (0-shot) | 50.56 |
| Winogrande (5-shot) | 75.14 |
| GSM8K (5-shot) | 10.39 |
| DROP (3-shot) | 28.28 |
|
NeverSleep/Noromaid-7b-v0.2 | NeverSleep | "2023-12-21T02:59:07Z" | 1,673 | 9 | transformers | [
"transformers",
"pytorch",
"mistral",
"text-generation",
"license:cc-by-nc-4.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-12-21T00:55:19Z" | ---
license: cc-by-nc-4.0
---
---
# Disclaimer:
## This is a ***TEST*** version, don't expect everything to work!!!
You may use our custom **prompting format**(scroll down to download them!), or simple alpaca. **(Choose which fits best for you!)**
---
# This model is a collab between [IkariDev](https://huggingface.co/IkariDev) and [Undi](https://huggingface.co/Undi95)!
Tired of the same merges everytime? Here it is, the Noromaid-7b-v0.2 model. Suitable for RP, ERP and general stuff.
[Recommended generation settings - No settings yet(Please suggest some over in the Community tab!)]
<!-- description start -->
## Description
<!-- [Recommended settings - contributed by localfultonextractor](https://files.catbox.moe/ue0tja.json) -->
This repo contains fp16 files of Noromaid-7b-v0.2.
[FP16 - by IkariDev and Undi](https://huggingface.co/NeverSleep/Noromaid-7b-v0.2)
<!-- [GGUF - By TheBloke](https://huggingface.co/TheBloke/Athena-v4-GGUF)-->
<!-- [GPTQ - By TheBloke](https://huggingface.co/TheBloke/Athena-v4-GPTQ)-->
<!-- [exl2[8bpw-8h] - by AzureBlack](https://huggingface.co/AzureBlack/Echidna-13b-v0.3-8bpw-8h-exl2)-->
<!-- [AWQ - By TheBloke](https://huggingface.co/TheBloke/Athena-v4-AWQ)-->
<!-- [fp16 - by IkariDev+Undi95](https://huggingface.co/IkariDev/Athena-v4)-->
[GGUF - by IkariDev and Undi](https://huggingface.co/NeverSleep/Noromaid-7b-v0.2-GGUF)
<!-- [OLD(GGUF - by IkariDev+Undi95)](https://huggingface.co/IkariDev/Athena-v4-GGUF)-->
## Ratings:
Note: We have permission of all users to upload their ratings, we DONT screenshot random reviews without asking if we can put them here!
No ratings yet!
If you want your rating to be here, send us a message over on DC and we'll put up a screenshot of it here. DC name is "ikaridev" and "undi".
<!-- description end -->
<!-- prompt-template start -->
## Prompt template: Custom format, or Alpaca
### Custom format:
UPDATED!! SillyTavern config files: [Context](https://files.catbox.moe/ifmhai.json), [Instruct](https://files.catbox.moe/ttw1l9.json).
### Alpaca:
```
Below is an instruction that describes a task. Write a response that appropriately completes the request.
### Instruction:
{prompt}
### Response:
```
## Training data used:
- [no_robots dataset](https://huggingface.co/Undi95/Llama2-13B-no_robots-alpaca-lora) let the model have more human behavior, enhances the output.
- [Aesir Private RP dataset] New data from a new and never used before dataset, add fresh data, no LimaRP spam, this is 100% new. Thanks to the [MinvervaAI Team](https://huggingface.co/MinervaAI) and, in particular, [Gryphe](https://huggingface.co/Gryphe) for letting us use it!
- [Another private Aesir dataset]
This is a full finetune.
Trained until 2 epoch(4000 steps), trained on mistral 0.1 7b base.
## Others
Undi: If you want to support me, you can [here](https://ko-fi.com/undiai).
IkariDev: Visit my [retro/neocities style website](https://ikaridevgit.github.io/) please kek |
MaziyarPanahi/Llama-3-70B-Instruct-DPO-v0.2 | MaziyarPanahi | "2024-05-08T15:49:36Z" | 1,673 | 11 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"axolotl",
"finetune",
"dpo",
"facebook",
"meta",
"pytorch",
"llama-3",
"chatml",
"conversational",
"en",
"dataset:Intel/orca_dpo_pairs",
"base_model:meta-llama/Meta-Llama-3-70B-Instruct",
"license:llama3",
"model-index",
"autotrain_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-04-27T18:09:23Z" | ---
language:
- en
license: llama3
library_name: transformers
tags:
- axolotl
- finetune
- dpo
- facebook
- meta
- pytorch
- llama
- llama-3
- chatml
base_model: meta-llama/Meta-Llama-3-70B-Instruct
datasets:
- Intel/orca_dpo_pairs
model_name: Llama-3-70B-Instruct-DPO-v0.2
pipeline_tag: text-generation
license_name: llama3
license_link: LICENSE
inference: false
model_creator: MaziyarPanahi
quantized_by: MaziyarPanahi
model-index:
- name: Llama-3-70B-Instruct-DPO-v0.2
results:
- task:
type: text-generation
name: Text Generation
dataset:
name: AI2 Reasoning Challenge (25-Shot)
type: ai2_arc
config: ARC-Challenge
split: test
args:
num_few_shot: 25
metrics:
- type: acc_norm
value: 72.53
name: normalized accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=MaziyarPanahi/Llama-3-70B-Instruct-DPO-v0.2
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: HellaSwag (10-Shot)
type: hellaswag
split: validation
args:
num_few_shot: 10
metrics:
- type: acc_norm
value: 86.22
name: normalized accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=MaziyarPanahi/Llama-3-70B-Instruct-DPO-v0.2
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: MMLU (5-Shot)
type: cais/mmlu
config: all
split: test
args:
num_few_shot: 5
metrics:
- type: acc
value: 80.41
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=MaziyarPanahi/Llama-3-70B-Instruct-DPO-v0.2
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: TruthfulQA (0-shot)
type: truthful_qa
config: multiple_choice
split: validation
args:
num_few_shot: 0
metrics:
- type: mc2
value: 63.57
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=MaziyarPanahi/Llama-3-70B-Instruct-DPO-v0.2
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: Winogrande (5-shot)
type: winogrande
config: winogrande_xl
split: validation
args:
num_few_shot: 5
metrics:
- type: acc
value: 82.79
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=MaziyarPanahi/Llama-3-70B-Instruct-DPO-v0.2
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: GSM8k (5-shot)
type: gsm8k
config: main
split: test
args:
num_few_shot: 5
metrics:
- type: acc
value: 88.25
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=MaziyarPanahi/Llama-3-70B-Instruct-DPO-v0.2
name: Open LLM Leaderboard
---
<img src="./llama-3-merges.webp" alt="Llama-3 DPO Logo" width="500" style="margin-left:'auto' margin-right:'auto' display:'block'"/>
# MaziyarPanahi/Llama-3-70B-Instruct-DPO-v0.2
This model is a fine-tune (DPO) of `meta-llama/Meta-Llama-3-70B-Instruct` model.
# ⚡ Quantized GGUF
All GGUF models are available here: [MaziyarPanahi/Llama-3-70B-Instruct-DPO-v0.2-GGUF](https://huggingface.co/MaziyarPanahi/Llama-3-70B-Instruct-DPO-v0.2-GGUF)
# 🏆 [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_MaziyarPanahi__Llama-3-70B-Instruct-DPO-v0.2)
| Metric |Value|
|---------------------------------|----:|
|Avg. |78.96|
|AI2 Reasoning Challenge (25-Shot)|72.53|
|HellaSwag (10-Shot) |86.22|
|MMLU (5-Shot) |80.41|
|TruthfulQA (0-shot) |63.57|
|Winogrande (5-shot) |82.79|
|GSM8k (5-shot) |88.25|
**Top 10 models on the Leaderboard**
<img src="./llama-3-70b-top-10.png" alt="Llama-3-70B finet-tuned models" style="margin-left:'auto' margin-right:'auto' display:'block'"/>
# Prompt Template
This model uses `ChatML` prompt template:
```
<|im_start|>system
{System}
<|im_end|>
<|im_start|>user
{User}
<|im_end|>
<|im_start|>assistant
{Assistant}
````
# How to use
You can use this model by using `MaziyarPanahi/Llama-3-70B-Instruct-DPO-v0.2` as the model name in Hugging Face's
transformers library.
```python
from transformers import AutoModelForCausalLM, AutoTokenizer, TextStreamer
from transformers import pipeline
import torch
model_id = "MaziyarPanahi/Llama-3-70B-Instruct-DPO-v0.2"
model = AutoModelForCausalLM.from_pretrained(
model_id,
torch_dtype=torch.bfloat16,
device_map="auto",
trust_remote_code=True,
# attn_implementation="flash_attention_2"
)
tokenizer = AutoTokenizer.from_pretrained(
model_id,
trust_remote_code=True
)
streamer = TextStreamer(tokenizer)
pipeline = pipeline(
"text-generation",
model=model,
tokenizer=tokenizer,
model_kwargs={"torch_dtype": torch.bfloat16},
streamer=streamer
)
# Then you can use the pipeline to generate text.
messages = [
{"role": "system", "content": "You are a pirate chatbot who always responds in pirate speak!"},
{"role": "user", "content": "Who are you?"},
]
prompt = tokenizer.apply_chat_template(
messages,
tokenize=False,
add_generation_prompt=True
)
terminators = [
tokenizer.eos_token_id,
tokenizer.convert_tokens_to_ids("<|im_end|>"),
tokenizer.convert_tokens_to_ids("<|eot_id|>") # safer to have this too
]
outputs = pipeline(
prompt,
max_new_tokens=2048,
eos_token_id=terminators,
do_sample=True,
temperature=0.6,
top_p=0.95,
)
print(outputs[0]["generated_text"][len(prompt):])
```
|
mayflowergmbh/Llama3-German-8B-32k-GGUF | mayflowergmbh | "2024-05-25T17:46:56Z" | 1,673 | 3 | transformers | [
"transformers",
"gguf",
"de",
"arxiv:2404.10830",
"license:llama3",
"endpoints_compatible",
"region:us"
] | null | "2024-05-25T17:24:51Z" | ---
language:
- de
license: llama3
library_name: transformers
tags:
- gguf
---
# Llama3-German-8B-32k (version 0.1)
This version of the model refers to the long-context extension version described [below](https://huggingface.co/DiscoResearch/Llama3-German-8B-32k#long-context-extension)
Llama3-German-8B-v0.1 is a large language model based on [Meta's Llama3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B). It is specialized for the German language through continuous pretraining on 65 billion high-quality tokens, similar to previous [LeoLM](https://huggingface.co/LeoLM) or [Occiglot](https://huggingface.co/collections/occiglot/occiglot-eu5-7b-v01-65dbed502a6348b052695e01) models.
Llama3 itself was trained on 15T tokens, of which only <1T were multilingual, resulting in suboptimal performance in German with reduced linguistic capabilities and frequent grammatical errors, motivating the necessity for continued pretraining. Benchmark results on our model show minimal degradation in English performance, despite the absence of replay during training. Importantly, Llama3-German-8B-v0.1 demonstrates strong improvements in German, particularly on the Hellaswag benchmark, which measures linguistic understanding and general reasoning.
[DiscoResearch/Llama3-German-8B-v0.1](https://huggingface.co/collections/DiscoResearch/discoleo-8b-llama3-for-german-6650527496c0fafefd4c9729) is the result of a joint effort between [DiscoResearch](https://huggingface.co/DiscoResearch) and [Occiglot](https://huggingface.co/occiglot) with support from the [DFKI](https://www.dfki.de/web/) (German Research Center for Artificial Intelligence) and [hessian.Ai](https://hessian.ai). Occiglot kindly handled data preprocessing, filtering, and deduplication as part of their latest [dataset release](https://huggingface.co/datasets/occiglot/occiglot-fineweb-v0.5), as well as sharing their compute allocation at hessian.Ai's 42 Supercomputer.
## How to use
This is a base model and should probably be subject to finetuning before use. See our [collection](https://huggingface.co/collections/DiscoResearch/discoleo-8b-llama3-for-german-6650527496c0fafefd4c9729) for various finetuned and long-context versions.
## Model Training and Hyperparameters
The model was trained on 128 GPUs on [hessian.Ai 42](hessian.ai) for ~60 hours. See detailed hyperparameters below.
| Parameter | Value |
|-------------------|-----------------------------------|
| Sequence Length | 8192 tokens |
| Learning Rate | 1.5e-5 to 1.5e-6 (cosine schedule)|
| Batch Size | 4194304 (512*8192) tokens |
| Micro Batch Size | 4*8192 tokens |
| Training Steps | 15500 |
| Warmup Steps | 155 (1%) |
| Weight Decay | 0.05 |
| Optimizer | AdamW |
## Data Collection and Preprocessing
For pre-training, we used 65B German tokens from the [occiglot-fineweb-0.5](https://huggingface.co/datasets/occiglot/occiglot-fineweb-v0.5) dataset.
The data comprises multiple curated datasets from [LLM-Datasets](https://github.com/malteos/llm-datasets) as well as 12 [Common-Crawl](https://commoncrawl.org) releases that were processed with [OSCAR's Ungoliant pipeline](https://github.com/oscar-project/ungoliant).
All data was further filtered with a set of language-specific filters based on [Huggingface's fine-web](https://github.com/huggingface/datatrove/blob/main/examples/fineweb.py) and globally deduplicated.
For more information please refer to the [dataset card](https://huggingface.co/datasets/occiglot/occiglot-fineweb-v0.5) and corresponding [blog-post](https://occiglot.eu/posts/occiglot-fineweb/).
## Evaluation and Results
We evaluated the model using a suite of common English Benchmarks and their German counterparts with [GermanBench](https://github.com/bjoernpl/GermanBenchmark).
The following figure shows the benchmark results in comparison to the base model [meta-llama/Meta-Llama3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B) and two different hyperparameter configurations.
We swept different learning rates to identify a well-working setup. The final released model is the 1.5e-5 lr version.
Find the detailed benchmark scores for the base and long-context models in this table.
| Model | truthful_qa_de | truthfulqa_mc | arc_challenge | arc_challenge_de | hellaswag | hellaswag_de | MMLU | MMLU-DE | mean |
|--------------------------------------|----------------|---------------|---------------|------------------|-----------|--------------|--------|---------|------------|
| DiscoResearch/Llama3-German-8B | **0.49499** | 0.44838 | 0.55802 | **0.49829** | 0.79924 | **0.65395** | 0.62240| **0.54413** | **0.57743** |
| DiscoResearch/Llama3-German-8B-32k | 0.48920 | **0.45138** | 0.54437 | 0.49232 | 0.79078 | 0.64310 | 0.58774| 0.47971 | 0.55982 |
| meta-llama/Meta-Llama-3-8B-Instruct | 0.47498 | 0.43923 | **0.59642** | 0.47952 | **0.82025**| 0.60008 | **0.66658**| 0.53541 | 0.57656 |
## Long-Context Extension
In addition to the base model, we release a long-context version of Llama3-German-8B ([DiscoResearch/Llama3-German-8B-32k](https://huggingface.co/DiscoResearch/Llama3-German-8B-32k) capable of processing context lengths up to 65k tokens. This variant was trained on an additional 100 million tokens at 32k context length, using a rope_theta value of `1.5e6` and a learning rate of `1.5e-5` with a batch size of `256*8192` tokens and otherwise equal hyperparameters to the base model.
## Instruction Tuning
We also provide an instruction-tuned version: [DiscoResearch/Llama3-DiscoLeo-Instruct-8B-v0.1](https://huggingface.co/DiscoResearch/Llama3-DiscoLeo-Instruct-8B-v0.1), utilizing the DiscoLM German dataset for fine-tuning (also available as a long-context model at [DiscoResearch/Llama3-DiscoLeo-Instruct-8B-32k-v0.1](https://huggingface.co/DiscoResearch/Llama3-DiscoLeo-Instruct-8B-v0.1)).
Find more details in the respective model cards. Also check out our experimental merge ([DiscoResearch/Llama3-DiscoLeo-8B-DARE-Experimental](https://huggingface.co/DiscoResearch/Llama3-DiscoLeo-8B-DARE-Experimental)) between [meta-llama/Meta-Llama3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) and our finetuned model in an attempt to keep the extraordinary capabilities of Llama3-Instruct and add exceptional German skills.
## Document Packing
We employed a more intelligent document packing strategy based on the ["Fewer Truncations Improve Language Modeling" paper by Ding et al.](https://arxiv.org/abs/2404.10830v2), using the first-fit-decreasing algorithm to pack documents into batches without truncation.
We packed our data in chunks of 10000 documents for more efficient processing while maintaining >99% packing efficiency. Documents longer than the sequence length are split into chunks of sequence length.
This approach results in overall higher benchmark scores when training on the same data with equal hyperparameters. The following numbers are from initial experiments with `3e-5 lr` and 12k steps and show improvements comparable to those shown in the original paper.
| Task | Naive Packing | Fewer Truncations Packing | Percentage Increase |
|-------------------|---------------|---------------------------|---------------------|
| truthfulqa_mc | 0.452648 | 0.467687 | 3.32% |
| arc_challenge | 0.517918 | 0.528157 | 1.98% |
| truthful_qa_de | 0.485529 | 0.492979 | 1.53% |
| arc_challenge_de | 0.480375 | 0.493174 | 2.66% |
| hellaswag | 0.776041 | 0.773352 | -0.35% |
| hellaswag_de | 0.655248 | 0.653356 | -0.29% |
| MMLU | 0.573719 | 0.579802 | 1.06% |
| MMLU-DE | 0.504509 | 0.503863 | -0.13% |
The following is our simple implementation of the first-fit-decreasing algorithm described in the paper.
```python
def pack_documents(tokenized_documents):
# Sort documents by their length in descending order
sorted_docs = sorted(tokenized_documents, key=len, reverse=True)
# Initialize bins
bins = []
# Function to find the first bin that can accommodate the document
def find_bin(doc):
for b in bins:
if sum(len(d) for d in b) + len(doc) <= 8192:
return b
return None
# Place each document in the first available bin or create a new bin
for doc in sorted_docs:
target_bin = find_bin(doc)
if target_bin is not None:
target_bin.append(doc)
else:
# Create a new bin with this document if no suitable bin is found
bins.append([doc])
# Return results
return bins
```
## Model Configurations
We release DiscoLeo-8B in the following configurations:
1. [Base model with continued pretraining](https://huggingface.co/DiscoResearch/Llama3-German-8B)
2. [Long-context version (32k context length)](https://huggingface.co/DiscoResearch/Llama3-German-8B-32k)
3. [Instruction-tuned version of the base model](https://huggingface.co/DiscoResearch/Llama3-DiscoLeo-Instruct-8B-v0.1)
4. [Instruction-tuned version of the long-context model](https://huggingface.co/DiscoResearch/Llama3-DiscoLeo-Instruct-8B-32k-v0.1)
5. [Experimental `DARE-TIES` Merge with Llama3-Instruct](https://huggingface.co/DiscoResearch/Llama3-DiscoLeo-8B-DARE-Experimental)
6. [Collection of Quantized versions](https://huggingface.co/collections/DiscoResearch/discoleo-8b-quants-6651bcf8f72c9a37ce485d42)
## How to use:
Here's how to use the model with transformers:
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
model = AutoModelForCausalLM.from_pretrained(
"DiscoResearch/Llama3-DiscoLeo-Instruct-8B-v0.1",
torch_dtype="auto",
device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("DiscoResearch/Llama3-DiscoLeo-Instruct-8B-v0.1")
prompt = "Schreibe ein Essay über die Bedeutung der Energiewende für Deutschlands Wirtschaft"
messages = [
{"role": "system", "content": "Du bist ein hilfreicher Assistent."},
{"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
messages,
tokenize=False,
add_generation_prompt=True
)
model_inputs = tokenizer([text], return_tensors="pt").to(device)
generated_ids = model.generate(
model_inputs.input_ids,
max_new_tokens=512
)
generated_ids = [
output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
]
response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
```
## Acknowledgements
The model was trained and evaluated by [Björn Plüster](https://huggingface.co/bjoernp) ([DiscoResearch](https://huggingface.co/DiscoResearch), [ellamind](https://ellamind.com)) with data preparation and project supervision by [Manuel Brack](http://manuel-brack.eu) ([DFKI](https://www.dfki.de/web/), [TU-Darmstadt](https://www.tu-darmstadt.de/)). Initial work on dataset collection and curation was performed by [Malte Ostendorff](https://ostendorff.org) and [Pedro Ortiz Suarez](https://portizs.eu). Instruction tuning was done with the DiscoLM German dataset created by [Jan-Philipp Harries](https://huggingface.co/jphme) and [Daniel Auras](https://huggingface.co/rasdani) ([DiscoResearch](https://huggingface.co/DiscoResearch), [ellamind](https://ellamind.com)). We extend our gratitude to [LAION](https://laion.ai/) and friends, especially [Christoph Schuhmann](https://entwickler.de/experten/christoph-schuhmann) and [Jenia Jitsev](https://huggingface.co/JJitsev), for initiating this collaboration.
The model training was supported by a compute grant at the [42 supercomputer](https://hessian.ai/) which is a central component in the development of [hessian AI](https://hessian.ai/), the [AI Innovation Lab](https://hessian.ai/infrastructure/ai-innovationlab/) (funded by the [Hessian Ministry of Higher Education, Research and the Art (HMWK)](https://wissenschaft.hessen.de) & the [Hessian Ministry of the Interior, for Security and Homeland Security (HMinD)](https://innen.hessen.de)) and the [AI Service Centers](https://hessian.ai/infrastructure/ai-service-centre/) (funded by the [German Federal Ministry for Economic Affairs and Climate Action (BMWK)](https://www.bmwk.de/Navigation/EN/Home/home.html)).
The curation of the training data is partially funded by the [German Federal Ministry for Economic Affairs and Climate Action (BMWK)](https://www.bmwk.de/Navigation/EN/Home/home.html)
through the project [OpenGPT-X](https://opengpt-x.de/en/) (project no. 68GX21007D).
|
Dabococo/OWAI_042csv | Dabococo | "2024-06-23T19:00:08Z" | 1,673 | 0 | null | [
"gguf",
"fr",
"en",
"dataset:Dabococo/OWAI_042",
"license:mit",
"region:us"
] | null | "2024-06-22T14:05:38Z" | ---
license: mit
datasets:
- Dabococo/OWAI_042
language:
- fr
- en
---
## Model Details
FR: Ceci est un modèle d'expérimentation basé sur llama3. Le modèle final aura pour but d'aider les gens sur Minecraft et plus spécifiquement sur le serveur Minecraft OpenWar (openwar.fr).
EN: This is an experimental model based on llama3. The final template will aim to help people on Minecraft and more specifically on the Minecraft OpenWar server (openwar.fr).
### Model Description
- **Developed by:** [Dabococo]
- **Model type:** [Conversation, Q&A]
- **Finetuned from model:** [Llama 3 Meta]
[More Information Needed]
### Recommendations
Attendez une meilleure version du modèle.
Wait for a better version of the model. |
lxe/Cerebras-GPT-2.7B-Alpaca-SP | lxe | "2023-12-08T23:00:15Z" | 1,672 | 10 | transformers | [
"transformers",
"pytorch",
"gpt2",
"text-generation",
"code",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-03-31T04:50:28Z" | ---
license: apache-2.0
tags:
- code
---
## Cerebras-GPT-2.7B-Alpaca-SP
Cerebras-GPT-2.7B-Alpaca-SP is [cerebras/Cerebras-GPT-2.7B](https://huggingface.co/cerebras/Cerebras-GPT-2.7B) finetuned on a modified [Alpaca dataset](https://github.com/tloen/alpaca-lora/blob/main/alpaca_data_cleaned.json) with a shorter prompt structure (`Human:...\n\nAssistant:`). This contains the float16 model merged with [lxe/lora-cerebras-gpt2.7b-alpaca-shortprompt](https://huggingface.co/lxe/lora-cerebras-gpt2.7b-alpaca-shortprompt) LoRA.
### Limitations:
Although mostly coherent, the model tends to hallucinate signinficantly, often producing erroneous information.
### Basic Usage:
```python
tokenizer = transformers.AutoTokenizer.from_pretrained('lxe/Cerebras-GPT-2.7B-Alpaca-SP')
model = transformers.AutoModelForCausalLM.from_pretrained(
`lxe/Cerebras-GPT-2.7B-Alpaca-SP`,
load_in_8bit=True,
torch_dtype=torch.float16,
device_map={"": 0},
)
prompt = "Human: how old is the sun?\n\nAssistant:"
input_ids = tokenizer.encode(prompt, return_tensors="pt").cuda()
with torch.no_grad():
output = model.generate(
input_ids=input_ids,
max_length=100,
early_stopping=True,
)
generated_text = tokenizer.decode(output[0], skip_special_tokens=True)
print(generated_text)
```
```
Human: how old is the sun?
Assistant: The sun is approximately 4.5 billion years old.
```
### Example Outputs:
**Human**: how old is the sun? <br />
**Assistant**: The sun is approximately 4.5 billion years old.
**Human**: what are the highest grossing films of the 2000-2010 decade? <br />
**Assistant**: The highest grossing film in 2010 was Avatar, which earned $2.5 billion worldwide and is currently ranked as one of the top 10 movies ever made by Box Office Mojo. Other notable high-grossing films include Titanic ($1.8 billion), Jurassic World ($1.6 billion) and Harry Potter And The Deathly Hallows Part 2 ($1.4 billion).
**Human**: how is cheese made? <br />
**Assistant**: Cheese making involves the process of curdling milk, separating it into a liquid and solid phase, then heating that mixture to create a semi-solid mass. The resulting product can be either hard or soft depending on its composition. Hard cheeses are typically produced from cow's milk while softer varieties come from sheep's milk.
**Human**: print all letters of the alphabet in reverse <br />
**Assistant**: A B C D E F G H I J K L M N O P Q R S T U V W X Y Z
**Human**: write a javascript function that sorts an array using quicksort algorithm <br />
**Assistant**:
```
function quicksort(array) {
if (array.length < 2) {
return array;
}
var pivot = array[0];
var left = quicksort(array, 0, array.length - 1);
var right = quicksort(array, array.length - 1, 0);
if (left < pivot) {
left = pivot;
}
if (right > pivot) {
right = pivot;
}
if (left < right) {
quicksort(array, left, right);
}
```
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_lxe__Cerebras-GPT-2.7B-Alpaca-SP)
| Metric | Value |
|-----------------------|---------------------------|
| Avg. | 29.4 |
| ARC (25-shot) | 30.8 |
| HellaSwag (10-shot) | 48.88 |
| MMLU (5-shot) | 25.12 |
| TruthfulQA (0-shot) | 40.24 |
| Winogrande (5-shot) | 55.41 |
| GSM8K (5-shot) | 0.53 |
| DROP (3-shot) | 4.78 |
|
NousResearch/Llama-2-13b-chat-hf | NousResearch | "2024-06-03T19:23:26Z" | 1,672 | 26 | transformers | [
"transformers",
"pytorch",
"safetensors",
"llama",
"text-generation",
"facebook",
"meta",
"llama-2",
"en",
"autotrain_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-07-19T01:01:32Z" | ---
extra_gated_heading: Access Llama 2 on Hugging Face
extra_gated_description: >-
This is a form to enable access to Llama 2 on Hugging Face after you have been
granted access from Meta. Please visit the [Meta website](https://ai.meta.com/resources/models-and-libraries/llama-downloads) and accept our
license terms and acceptable use policy before submitting this form. Requests
will be processed in 1-2 days.
extra_gated_button_content: Submit
extra_gated_fields:
I agree to share my name, email address and username with Meta and confirm that I have already been granted download access on the Meta website: checkbox
language:
- en
pipeline_tag: text-generation
inference: false
tags:
- facebook
- meta
- pytorch
- llama
- llama-2
---
# **Llama 2**
Llama 2 is a collection of pretrained and fine-tuned generative text models ranging in scale from 7 billion to 70 billion parameters. This is the repository for the 13B fine-tuned model, optimized for dialogue use cases and converted for the Hugging Face Transformers format. Links to other models can be found in the index at the bottom.
## Model Details
*Note: Use of this model is governed by the Meta license. In order to download the model weights and tokenizer, please visit the [website](https://ai.meta.com/resources/models-and-libraries/llama-downloads/) and accept our License before requesting access here.*
Meta developed and publicly released the Llama 2 family of large language models (LLMs), a collection of pretrained and fine-tuned generative text models ranging in scale from 7 billion to 70 billion parameters. Our fine-tuned LLMs, called Llama-2-Chat, are optimized for dialogue use cases. Llama-2-Chat models outperform open-source chat models on most benchmarks we tested, and in our human evaluations for helpfulness and safety, are on par with some popular closed-source models like ChatGPT and PaLM.
**Model Developers** Meta
**Variations** Llama 2 comes in a range of parameter sizes — 7B, 13B, and 70B — as well as pretrained and fine-tuned variations.
**Input** Models input text only.
**Output** Models generate text only.
**Model Architecture** Llama 2 is an auto-regressive language model that uses an optimized transformer architecture. The tuned versions use supervised fine-tuning (SFT) and reinforcement learning with human feedback (RLHF) to align to human preferences for helpfulness and safety.
||Training Data|Params|Content Length|GQA|Tokens|LR|
|---|---|---|---|---|---|---|
|Llama 2|*A new mix of publicly available online data*|7B|4k|✗|2.0T|3.0 x 10<sup>-4</sup>|
|Llama 2|*A new mix of publicly available online data*|13B|4k|✗|2.0T|3.0 x 10<sup>-4</sup>|
|Llama 2|*A new mix of publicly available online data*|70B|4k|✔|2.0T|1.5 x 10<sup>-4</sup>|
*Llama 2 family of models.* Token counts refer to pretraining data only. All models are trained with a global batch-size of 4M tokens. Bigger models - 70B -- use Grouped-Query Attention (GQA) for improved inference scalability.
**Model Dates** Llama 2 was trained between January 2023 and July 2023.
**Status** This is a static model trained on an offline dataset. Future versions of the tuned models will be released as we improve model safety with community feedback.
**License** A custom commercial license is available at: [https://ai.meta.com/resources/models-and-libraries/llama-downloads/](https://ai.meta.com/resources/models-and-libraries/llama-downloads/)
## Intended Use
**Intended Use Cases** Llama 2 is intended for commercial and research use in English. Tuned models are intended for assistant-like chat, whereas pretrained models can be adapted for a variety of natural language generation tasks.
To get the expected features and performance for the chat versions, a specific formatting needs to be followed, including the `INST` and `<<SYS>>` tags, `BOS` and `EOS` tokens, and the whitespaces and breaklines in between (we recommend calling `strip()` on inputs to avoid double-spaces). See our reference code in github for details: [`chat_completion`](https://github.com/facebookresearch/llama/blob/main/llama/generation.py#L212).
**Out-of-scope Uses** Use in any manner that violates applicable laws or regulations (including trade compliance laws).Use in languages other than English. Use in any other way that is prohibited by the Acceptable Use Policy and Licensing Agreement for Llama 2.
## Hardware and Software
**Training Factors** We used custom training libraries, Meta's Research Super Cluster, and production clusters for pretraining. Fine-tuning, annotation, and evaluation were also performed on third-party cloud compute.
**Carbon Footprint** Pretraining utilized a cumulative 3.3M GPU hours of computation on hardware of type A100-80GB (TDP of 350-400W). Estimated total emissions were 539 tCO2eq, 100% of which were offset by Meta’s sustainability program.
||Time (GPU hours)|Power Consumption (W)|Carbon Emitted(tCO<sub>2</sub>eq)|
|---|---|---|---|
|Llama 2 7B|184320|400|31.22|
|Llama 2 13B|368640|400|62.44|
|Llama 2 70B|1720320|400|291.42|
|Total|3311616||539.00|
**CO<sub>2</sub> emissions during pretraining.** Time: total GPU time required for training each model. Power Consumption: peak power capacity per GPU device for the GPUs used adjusted for power usage efficiency. 100% of the emissions are directly offset by Meta's sustainability program, and because we are openly releasing these models, the pretraining costs do not need to be incurred by others.
## Training Data
**Overview** Llama 2 was pretrained on 2 trillion tokens of data from publicly available sources. The fine-tuning data includes publicly available instruction datasets, as well as over one million new human-annotated examples. Neither the pretraining nor the fine-tuning datasets include Meta user data.
**Data Freshness** The pretraining data has a cutoff of September 2022, but some tuning data is more recent, up to July 2023.
## Evaluation Results
In this section, we report the results for the Llama 1 and Llama 2 models on standard academic benchmarks.For all the evaluations, we use our internal evaluations library.
|Model|Size|Code|Commonsense Reasoning|World Knowledge|Reading Comprehension|Math|MMLU|BBH|AGI Eval|
|---|---|---|---|---|---|---|---|---|---|
|Llama 1|7B|14.1|60.8|46.2|58.5|6.95|35.1|30.3|23.9|
|Llama 1|13B|18.9|66.1|52.6|62.3|10.9|46.9|37.0|33.9|
|Llama 1|33B|26.0|70.0|58.4|67.6|21.4|57.8|39.8|41.7|
|Llama 1|65B|30.7|70.7|60.5|68.6|30.8|63.4|43.5|47.6|
|Llama 2|7B|16.8|63.9|48.9|61.3|14.6|45.3|32.6|29.3|
|Llama 2|13B|24.5|66.9|55.4|65.8|28.7|54.8|39.4|39.1|
|Llama 2|70B|**37.5**|**71.9**|**63.6**|**69.4**|**35.2**|**68.9**|**51.2**|**54.2**|
**Overall performance on grouped academic benchmarks.** *Code:* We report the average pass@1 scores of our models on HumanEval and MBPP. *Commonsense Reasoning:* We report the average of PIQA, SIQA, HellaSwag, WinoGrande, ARC easy and challenge, OpenBookQA, and CommonsenseQA. We report 7-shot results for CommonSenseQA and 0-shot results for all other benchmarks. *World Knowledge:* We evaluate the 5-shot performance on NaturalQuestions and TriviaQA and report the average. *Reading Comprehension:* For reading comprehension, we report the 0-shot average on SQuAD, QuAC, and BoolQ. *MATH:* We report the average of the GSM8K (8 shot) and MATH (4 shot) benchmarks at top 1.
|||TruthfulQA|Toxigen|
|---|---|---|---|
|Llama 1|7B|27.42|23.00|
|Llama 1|13B|41.74|23.08|
|Llama 1|33B|44.19|22.57|
|Llama 1|65B|48.71|21.77|
|Llama 2|7B|33.29|**21.25**|
|Llama 2|13B|41.86|26.10|
|Llama 2|70B|**50.18**|24.60|
**Evaluation of pretrained LLMs on automatic safety benchmarks.** For TruthfulQA, we present the percentage of generations that are both truthful and informative (the higher the better). For ToxiGen, we present the percentage of toxic generations (the smaller the better).
|||TruthfulQA|Toxigen|
|---|---|---|---|
|Llama-2-Chat|7B|57.04|**0.00**|
|Llama-2-Chat|13B|62.18|**0.00**|
|Llama-2-Chat|70B|**64.14**|0.01|
**Evaluation of fine-tuned LLMs on different safety datasets.** Same metric definitions as above.
## Ethical Considerations and Limitations
Llama 2 is a new technology that carries risks with use. Testing conducted to date has been in English, and has not covered, nor could it cover all scenarios. For these reasons, as with all LLMs, Llama 2’s potential outputs cannot be predicted in advance, and the model may in some instances produce inaccurate, biased or other objectionable responses to user prompts. Therefore, before deploying any applications of Llama 2, developers should perform safety testing and tuning tailored to their specific applications of the model.
Please see the Responsible Use Guide available at [https://ai.meta.com/llama/responsible-use-guide/](https://ai.meta.com/llama/responsible-use-guide)
## Reporting Issues
Please report any software “bug,” or other problems with the models through one of the following means:
- Reporting issues with the model: [github.com/facebookresearch/llama](http://github.com/facebookresearch/llama)
- Reporting problematic content generated by the model: [developers.facebook.com/llama_output_feedback](http://developers.facebook.com/llama_output_feedback)
- Reporting bugs and security concerns: [facebook.com/whitehat/info](http://facebook.com/whitehat/info)
## Llama Model Index
|Model|Llama2|Llama2-hf|Llama2-chat|Llama2-chat-hf|
|---|---|---|---|---|
|7B| [Link](https://huggingface.co/llamaste/Llama-2-7b) | [Link](https://huggingface.co/llamaste/Llama-2-7b-hf) | [Link](https://huggingface.co/llamaste/Llama-2-7b-chat) | [Link](https://huggingface.co/llamaste/Llama-2-7b-chat-hf)|
|13B| [Link](https://huggingface.co/llamaste/Llama-2-13b) | [Link](https://huggingface.co/llamaste/Llama-2-13b-hf) | [Link](https://huggingface.co/llamaste/Llama-2-13b-chat) | [Link](https://huggingface.co/llamaste/Llama-2-13b-hf)|
|70B| [Link](https://huggingface.co/llamaste/Llama-2-70b) | [Link](https://huggingface.co/llamaste/Llama-2-70b-hf) | [Link](https://huggingface.co/llamaste/Llama-2-70b-chat) | [Link](https://huggingface.co/llamaste/Llama-2-70b-hf)|
|
TheBloke/Mistral-7B-v0.1-GPTQ | TheBloke | "2023-09-29T20:49:41Z" | 1,672 | 35 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"pretrained",
"base_model:mistralai/Mistral-7B-v0.1",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"4-bit",
"gptq",
"region:us"
] | text-generation | "2023-09-28T22:35:40Z" | ---
base_model: mistralai/Mistral-7B-v0.1
inference: false
license: apache-2.0
model_creator: Mistral AI
model_name: Mistral 7B v0.1
model_type: mistral
pipeline_tag: text-generation
prompt_template: '{prompt}'
quantized_by: TheBloke
tags:
- pretrained
---
<!-- header start -->
<!-- 200823 -->
<div style="width: auto; margin-left: auto; margin-right: auto">
<img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
</div>
<div style="display: flex; justify-content: space-between; width: 100%;">
<div style="display: flex; flex-direction: column; align-items: flex-start;">
<p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://discord.gg/theblokeai">Chat & support: TheBloke's Discord server</a></p>
</div>
<div style="display: flex; flex-direction: column; align-items: flex-end;">
<p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p>
</div>
</div>
<div style="text-align:center; margin-top: 0em; margin-bottom: 0em"><p style="margin-top: 0.25em; margin-bottom: 0em;">TheBloke's LLM work is generously supported by a grant from <a href="https://a16z.com">andreessen horowitz (a16z)</a></p></div>
<hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
<!-- header end -->
# Mistral 7B v0.1 - GPTQ
- Model creator: [Mistral AI](https://huggingface.co/mistralai)
- Original model: [Mistral 7B v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1)
<!-- description start -->
## Description
This repo contains GPTQ model files for [Mistral AI's Mistral 7B v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1).
Multiple GPTQ parameter permutations are provided; see Provided Files below for details of the options provided, their parameters, and the software used to create them.
### GPTQs will work in ExLlama, or via Transformers (requiring Transformers from Github)
These models are confirmed to work with ExLlama v1.
At the time of writing (September 28th), AutoGPTQ has not yet added support for the new Mistral models.
These GPTQs were made directly from Transformers, and so can be loaded via the Transformers interface. They can't be loaded directly from AutoGPTQ.
To load them via Transformers, you will need to install Transformers from Github, with:
```
pip3 install git+https://github.com/huggingface/transformers.git@72958fcd3c98a7afdc61f953aa58c544ebda2f79
```
<!-- description end -->
<!-- description end -->
<!-- repositories-available start -->
## Repositories available
* [AWQ model(s) for GPU inference.](https://huggingface.co/TheBloke/Mistral-7B-v0.1-AWQ)
* [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/Mistral-7B-v0.1-GPTQ)
* [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/Mistral-7B-v0.1-GGUF)
* [Mistral AI's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/mistralai/Mistral-7B-v0.1)
<!-- repositories-available end -->
<!-- prompt-template start -->
## Prompt template: None
```
{prompt}
```
<!-- prompt-template end -->
<!-- README_GPTQ.md-provided-files start -->
## Provided files, and GPTQ parameters
Multiple quantisation parameters are provided, to allow you to choose the best one for your hardware and requirements.
Each separate quant is in a different branch. See below for instructions on fetching from different branches.
These files were made with Transformers 4.34.0.dev0, from commit 72958fcd3c98a7afdc61f953aa58c544ebda2f79.
<details>
<summary>Explanation of GPTQ parameters</summary>
- Bits: The bit size of the quantised model.
- GS: GPTQ group size. Higher numbers use less VRAM, but have lower quantisation accuracy. "None" is the lowest possible value.
- Act Order: True or False. Also known as `desc_act`. True results in better quantisation accuracy. Some GPTQ clients have had issues with models that use Act Order plus Group Size, but this is generally resolved now.
- Damp %: A GPTQ parameter that affects how samples are processed for quantisation. 0.01 is default, but 0.1 results in slightly better accuracy.
- GPTQ dataset: The calibration dataset used during quantisation. Using a dataset more appropriate to the model's training can improve quantisation accuracy. Note that the GPTQ calibration dataset is not the same as the dataset used to train the model - please refer to the original model repo for details of the training dataset(s).
- Sequence Length: The length of the dataset sequences used for quantisation. Ideally this is the same as the model sequence length. For some very long sequence models (16+K), a lower sequence length may have to be used. Note that a lower sequence length does not limit the sequence length of the quantised model. It only impacts the quantisation accuracy on longer inference sequences.
- ExLlama Compatibility: Whether this file can be loaded with ExLlama, which currently only supports Llama models in 4-bit.
</details>
| Branch | Bits | GS | Act Order | Damp % | GPTQ Dataset | Seq Len | Size | ExLlama | Desc |
| ------ | ---- | -- | --------- | ------ | ------------ | ------- | ---- | ------- | ---- |
| [main](https://huggingface.co/TheBloke/Mistral-7B-v0.1-GPTQ/tree/main) | 4 | 128 | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 32768 | 4.16 GB | Yes | 4-bit, with Act Order and group size 128g. Uses even less VRAM than 64g, but with slightly lower accuracy. |
| [gptq-4bit-32g-actorder_True](https://huggingface.co/TheBloke/Mistral-7B-v0.1-GPTQ/tree/gptq-4bit-32g-actorder_True) | 4 | 32 | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 32768 | 4.57 GB | Yes | 4-bit, with Act Order and group size 32g. Gives highest possible inference quality, with maximum VRAM usage. |
| [gptq-8bit-128g-actorder_True](https://huggingface.co/TheBloke/Mistral-7B-v0.1-GPTQ/tree/gptq-8bit-128g-actorder_True) | 8 | 128 | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 32768 | 4.16 GB | Yes | 8-bit, with group size 128g for higher inference quality and with Act Order for even higher accuracy. |
| [gptq-8bit-32g-actorder_True](https://huggingface.co/TheBloke/Mistral-7B-v0.1-GPTQ/tree/gptq-8bit-32g-actorder_True) | 8 | 32 | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 32768 | 4.57 GB | Yes | 8-bit, with group size 32g and Act Order for maximum inference quality. |
<!-- README_GPTQ.md-provided-files end -->
<!-- README_GPTQ.md-download-from-branches start -->
## How to download, including from branches
### In text-generation-webui
To download from the `main` branch, enter `TheBloke/Mistral-7B-v0.1-GPTQ` in the "Download model" box.
To download from another branch, add `:branchname` to the end of the download name, eg `TheBloke/Mistral-7B-v0.1-GPTQ:gptq-4bit-32g-actorder_True`
### From the command line
I recommend using the `huggingface-hub` Python library:
```shell
pip3 install huggingface-hub
```
To download the `main` branch to a folder called `Mistral-7B-v0.1-GPTQ`:
```shell
mkdir Mistral-7B-v0.1-GPTQ
huggingface-cli download TheBloke/Mistral-7B-v0.1-GPTQ --local-dir Mistral-7B-v0.1-GPTQ --local-dir-use-symlinks False
```
To download from a different branch, add the `--revision` parameter:
```shell
mkdir Mistral-7B-v0.1-GPTQ
huggingface-cli download TheBloke/Mistral-7B-v0.1-GPTQ --revision gptq-4bit-32g-actorder_True --local-dir Mistral-7B-v0.1-GPTQ --local-dir-use-symlinks False
```
<details>
<summary>More advanced huggingface-cli download usage</summary>
If you remove the `--local-dir-use-symlinks False` parameter, the files will instead be stored in the central Huggingface cache directory (default location on Linux is: `~/.cache/huggingface`), and symlinks will be added to the specified `--local-dir`, pointing to their real location in the cache. This allows for interrupted downloads to be resumed, and allows you to quickly clone the repo to multiple places on disk without triggering a download again. The downside, and the reason why I don't list that as the default option, is that the files are then hidden away in a cache folder and it's harder to know where your disk space is being used, and to clear it up if/when you want to remove a download model.
The cache location can be changed with the `HF_HOME` environment variable, and/or the `--cache-dir` parameter to `huggingface-cli`.
For more documentation on downloading with `huggingface-cli`, please see: [HF -> Hub Python Library -> Download files -> Download from the CLI](https://huggingface.co/docs/huggingface_hub/guides/download#download-from-the-cli).
To accelerate downloads on fast connections (1Gbit/s or higher), install `hf_transfer`:
```shell
pip3 install hf_transfer
```
And set environment variable `HF_HUB_ENABLE_HF_TRANSFER` to `1`:
```shell
mkdir Mistral-7B-v0.1-GPTQ
HF_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download TheBloke/Mistral-7B-v0.1-GPTQ --local-dir Mistral-7B-v0.1-GPTQ --local-dir-use-symlinks False
```
Windows Command Line users: You can set the environment variable by running `set HF_HUB_ENABLE_HF_TRANSFER=1` before the download command.
</details>
### With `git` (**not** recommended)
To clone a specific branch with `git`, use a command like this:
```shell
git clone --single-branch --branch gptq-4bit-32g-actorder_True https://huggingface.co/TheBloke/Mistral-7B-v0.1-GPTQ
```
Note that using Git with HF repos is strongly discouraged. It will be much slower than using `huggingface-hub`, and will use twice as much disk space as it has to store the model files twice (it stores every byte both in the intended target folder, and again in the `.git` folder as a blob.)
<!-- README_GPTQ.md-download-from-branches end -->
<!-- README_GPTQ.md-text-generation-webui start -->
## How to easily download and use this model in [text-generation-webui](https://github.com/oobabooga/text-generation-webui).
These models are confirmed to work via the ExLlama Loader in text-generation-webui.
Use **Loader: ExLlama** - or Transformers may work too. AutoGPTQ will not work.
Please make sure you're using the latest version of [text-generation-webui](https://github.com/oobabooga/text-generation-webui).
It is strongly recommended to use the text-generation-webui one-click-installers unless you're sure you know how to make a manual install.
1. Click the **Model tab**.
2. Under **Download custom model or LoRA**, enter `TheBloke/Mistral-7B-v0.1-GPTQ`.
- To download from a specific branch, enter for example `TheBloke/Mistral-7B-v0.1-GPTQ:gptq-4bit-32g-actorder_True`
- see Provided Files above for the list of branches for each option.
3. Click **Download**.
4. The model will start downloading. Once it's finished it will say "Done".
5. In the top left, click the refresh icon next to **Model**.
6. In the **Model** dropdown, choose the model you just downloaded: `Mistral-7B-v0.1-GPTQ`
7. The model will automatically load, and is now ready for use!
8. If you want any custom settings, set them and then click **Save settings for this model** followed by **Reload the Model** in the top right.
* Note that you do not need to and should not set manual GPTQ parameters any more. These are set automatically from the file `quantize_config.json`.
9. Once you're ready, click the **Text Generation tab** and enter a prompt to get started!
<!-- README_GPTQ.md-text-generation-webui end -->
<!-- README_GPTQ.md-use-from-python start -->
## How to use this GPTQ model from Python code
### Install the necessary packages
Requires: Transformers 4.34.0.dev0 from Github source, Optimum 1.12.0 or later, and AutoGPTQ 0.4.2 or later.
```shell
pip3 install optimum
pip3 install git+https://github.com/huggingface/transformers.git@72958fcd3c98a7afdc61f953aa58c544ebda2f79
pip3 install auto-gptq --extra-index-url https://huggingface.github.io/autogptq-index/whl/cu118/ # Use cu117 if on CUDA 11.7
```
If you have problems installing AutoGPTQ using the pre-built wheels, install it from source instead:
```shell
pip3 uninstall -y auto-gptq
git clone https://github.com/PanQiWei/AutoGPTQ
cd AutoGPTQ
git checkout v0.4.2
pip3 install .
```
### You can then use the following code
```python
from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
model_name_or_path = "TheBloke/Mistral-7B-v0.1-GPTQ"
# To use a different branch, change revision
# For example: revision="gptq-4bit-32g-actorder_True"
model = AutoModelForCausalLM.from_pretrained(model_name_or_path,
device_map="auto",
trust_remote_code=False,
revision="main")
tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=True)
prompt = "Tell me about AI"
prompt_template=f'''{prompt}
'''
print("\n\n*** Generate:")
input_ids = tokenizer(prompt_template, return_tensors='pt').input_ids.cuda()
output = model.generate(inputs=input_ids, temperature=0.7, do_sample=True, top_p=0.95, top_k=40, max_new_tokens=512)
print(tokenizer.decode(output[0]))
# Inference can also be done using transformers' pipeline
print("*** Pipeline:")
pipe = pipeline(
"text-generation",
model=model,
tokenizer=tokenizer,
max_new_tokens=512,
do_sample=True,
temperature=0.7,
top_p=0.95,
top_k=40,
repetition_penalty=1.1
)
print(pipe(prompt_template)[0]['generated_text'])
```
<!-- README_GPTQ.md-use-from-python end -->
<!-- README_GPTQ.md-compatibility start -->
## Compatibility
The files provided are only tested to work with Transformers 4.34.0.dev0 as of commit 72958fcd3c98a7afdc61f953aa58c544ebda2f79.
<!-- README_GPTQ.md-compatibility end -->
<!-- footer start -->
<!-- 200823 -->
## Discord
For further support, and discussions on these models and AI in general, join us at:
[TheBloke AI's Discord server](https://discord.gg/theblokeai)
## Thanks, and how to contribute
Thanks to the [chirper.ai](https://chirper.ai) team!
Thanks to Clay from [gpus.llm-utils.org](llm-utils)!
I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training.
If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects.
Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits.
* Patreon: https://patreon.com/TheBlokeAI
* Ko-Fi: https://ko-fi.com/TheBlokeAI
**Special thanks to**: Aemon Algiz.
**Patreon special mentions**: Pierre Kircher, Stanislav Ovsiannikov, Michael Levine, Eugene Pentland, Andrey, 준교 김, Randy H, Fred von Graf, Artur Olbinski, Caitlyn Gatomon, terasurfer, Jeff Scroggin, James Bentley, Vadim, Gabriel Puliatti, Harry Royden McLaughlin, Sean Connelly, Dan Guido, Edmond Seymore, Alicia Loh, subjectnull, AzureBlack, Manuel Alberto Morcote, Thomas Belote, Lone Striker, Chris Smitley, Vitor Caleffi, Johann-Peter Hartmann, Clay Pascal, biorpg, Brandon Frisco, sidney chen, transmissions 11, Pedro Madruga, jinyuan sun, Ajan Kanaga, Emad Mostaque, Trenton Dambrowitz, Jonathan Leane, Iucharbius, usrbinkat, vamX, George Stoitzev, Luke Pendergrass, theTransient, Olakabola, Swaroop Kallakuri, Cap'n Zoog, Brandon Phillips, Michael Dempsey, Nikolai Manek, danny, Matthew Berman, Gabriel Tamborski, alfie_i, Raymond Fosdick, Tom X Nguyen, Raven Klaugh, LangChain4j, Magnesian, Illia Dulskyi, David Ziegler, Mano Prime, Luis Javier Navarrete Lozano, Erik Bjäreholt, 阿明, Nathan Dryer, Alex, Rainer Wilmers, zynix, TL, Joseph William Delisle, John Villwock, Nathan LeClaire, Willem Michiel, Joguhyik, GodLy, OG, Alps Aficionado, Jeffrey Morgan, ReadyPlayerEmma, Tiffany J. Kim, Sebastain Graf, Spencer Kim, Michael Davis, webtim, Talal Aujan, knownsqashed, John Detwiler, Imad Khwaja, Deo Leter, Jerry Meng, Elijah Stavena, Rooh Singh, Pieter, SuperWojo, Alexandros Triantafyllidis, Stephen Murray, Ai Maven, ya boyyy, Enrico Ros, Ken Nordquist, Deep Realms, Nicholas, Spiking Neurons AB, Elle, Will Dee, Jack West, RoA, Luke @flexchar, Viktor Bowallius, Derek Yates, Subspace Studios, jjj, Toran Billups, Asp the Wyvern, Fen Risland, Ilya, NimbleBox.ai, Chadd, Nitin Borwankar, Emre, Mandus, Leonard Tan, Kalila, K, Trailburnt, S_X, Cory Kujawski
Thank you to all my generous patrons and donaters!
And thank you again to a16z for their generous grant.
<!-- footer end -->
# Original model card: Mistral AI's Mistral 7B v0.1
# Model Card for Mistral-7B-v0.1
The Mistral-7B-v0.1 Large Language Model (LLM) is a pretrained generative text model with 7 billion parameters.
Mistral-7B-v0.1 outperforms Llama 2 13B on all benchmarks we tested.
For full details of this model please read our [Release blog post](https://mistral.ai/news/announcing-mistral-7b/)
## Model Architecture
Mistral-7B-v0.1 is a transformer model, with the following architecture choices:
- Grouped-Query Attention
- Sliding-Window Attention
- Byte-fallback BPE tokenizer
## Troubleshooting
- If you see the following error:
```
Traceback (most recent call last):
File "", line 1, in
File "/transformers/models/auto/auto_factory.py", line 482, in from_pretrained
config, kwargs = AutoConfig.from_pretrained(
File "/transformers/models/auto/configuration_auto.py", line 1022, in from_pretrained
config_class = CONFIG_MAPPING[config_dict["model_type"]]
File "/transformers/models/auto/configuration_auto.py", line 723, in getitem
raise KeyError(key)
KeyError: 'mistral'
```
Installing transformers from source should solve the issue:
```
pip install git+https://github.com/huggingface/transformers
```
This should not be required after transformers-v4.33.4.
## Notice
Mistral 7B is a pretrained base model and therefore does not have any moderation mechanisms.
## The Mistral AI Team
Albert Jiang, Alexandre Sablayrolles, Arthur Mensch, Chris Bamford, Devendra Singh Chaplot, Diego de las Casas, Florian Bressand, Gianna Lengyel, Guillaume Lample, Lélio Renard Lavaud, Lucile Saulnier, Marie-Anne Lachaux, Pierre Stock, Teven Le Scao, Thibaut Lavril, Thomas Wang, Timothée Lacroix, William El Sayed.
|
OpenPipe/mistral-ft-optimized-1218 | OpenPipe | "2023-12-27T19:33:47Z" | 1,672 | 153 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"en",
"license:cc-by-nc-4.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-12-17T14:30:06Z" | ---
license: cc-by-nc-4.0
language:
- en
---
**Update 12/27/2023**: We have released an updated version of this model with similar performance and a more permissive license at https://huggingface.co/OpenPipe/mistral-ft-optimized-1227. We recommend that model over this one for most users.
---
This model is intended to be a strong base suitable for downstream fine-tuning on a variety of tasks. Based on our internal evaluations, we believe it's one of the strongest models for most down-stream tasks. You can read more about our development and evaluation process [here](https://openpipe.ai/blog/mistral-7b-fine-tune-optimized).
---
[Mergekit](https://github.com/cg123/mergekit) config used to create this model:
```yaml
slices:
- sources:
- model: Weyaxi/OpenHermes-2.5-neural-chat-v3-3-Slerp
layer_range: [0, 32]
- model: Q-bert/MetaMath-Cybertron-Starling
layer_range: [0, 32]
merge_method: slerp
base_model: mistralai/Mistral-7B-v0.1
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5 # fallback for rest of tensors
dtype: bfloat16
```
---
*Note*: It appears that https://huggingface.co/Weyaxi/Seraph-7B was merged from the same base models using the same [mergekit](https://github.com/cg123/mergekit) defaults as this model. So major credit goes to @Weyaxi both for creating one of the base merges this model was merged from, as well as being the first one to perform this exact merge as well! |
DavidAhn/d-solar-10.7b-orpo-v1.1 | DavidAhn | "2024-06-20T03:48:28Z" | 1,672 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"conversational",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-06-20T03:37:13Z" | Entry not found |
TehVenom/GPT-J-Pyg_PPO-6B-Dev-V8p4 | TehVenom | "2023-03-27T04:22:05Z" | 1,671 | 1 | transformers | [
"transformers",
"pytorch",
"gptj",
"text-generation",
"en",
"license:bigscience-openrail-m",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-generation | "2023-03-26T17:06:01Z" | ---
license: bigscience-openrail-m
language:
- en
---
GPT-J-Pyg_PPO-6B [GPT-J Pygmalion Dev V8p4 + GPT-J PPO_HH]
GPT-J-Pyg_PPO-6B is an experimental model containing a parameter-wise 40/60 blend (weighted average PPO_HH:Pygmalion) of the weights of ppo_hh_gpt-j and Pygmalion-6b Dev V8p4.
-Intended Merge Value-
As with fine-tuning, merging weights does not add information but transforms it, therefore it is important to consider trade-offs.
Pyg_PPO combines ppo_hh_gpt-j and Pygmalion-6b; both technical
achievements are blended with the intent to elevate the strengths of
both. Datasets of both are linked below to assist in exploratory speculation on which datasets in what quantity and configuration have
the largest impact on the usefulness of a model without the expense of
fine-tuning. Blend was done in FP32 and output in FP16.
-Intended Use-
Research purposes only, intended for responsible use.
Express a conversation in natural language, and Pyg_PPO will do the thing.
Try starting a two line prompt such as:
```
Bot: "Hello, how are you?"
You: "I am doing just fine, thank you."
```
Or any other
topic, and the model will carry on in this back and forth format.
Can also be used as a base to merge with other creative,
technical, or adventure themed models of the same class
(GPT-J & 6b NeoX) and parameter size (6b) to experiment with
the morphology of model weights based on the value added
by instruct.
Merge tested using KoboldAI with Nucleus Sampling Top-P set to 0.9, Temperature at 0.6, and Repetition Penalty at 1.1; extra samplers
disabled.
-Credits To-
Core Model:
https://huggingface.co/EleutherAI/gpt-j-6B
Author:
https://www.eleuther.ai/
Model1; 50% ppo_hh_gpt-j:
https://huggingface.co/reciprocate/ppo_hh_gpt-j
Author Repo:
https://huggingface.co/reciprocate
Related; CarperAI:
https://huggingface.co/CarperAI
Dataset is a variant of the Helpful Harmless assistant themed
dataset and Proximal Policy Optimization, specific datasets
used are unknown; listed repo datasets include:
https://huggingface.co/datasets/reciprocate/summarize_eval_ilql
https://huggingface.co/datasets/reciprocate/hh_eval_ilql
PPO explained:
https://paperswithcode.com/method/ppo
Potential HH-type datasets utilized:
https://huggingface.co/HuggingFaceH4
https://huggingface.co/datasets/Anthropic/hh-rlhf
Model2; 50% Pygmalion-6b:
https://huggingface.co/PygmalionAI/pygmalion-6b
Author Repo:
https://huggingface.co/PygmalionAI
Weight merge Script credit to Concedo:
https://huggingface.co/concedo
Model's card template credit to Digitous:
https://huggingface.co/digitous/GPT-R |
bofenghuang/vigogne-7b-chat | bofenghuang | "2023-07-12T15:33:38Z" | 1,671 | 4 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"LLM",
"fr",
"license:openrail",
"autotrain_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-05-15T14:07:53Z" | ---
license: openrail
language:
- fr
pipeline_tag: text-generation
library_name: transformers
tags:
- llama
- LLM
inference: false
---
<p align="center" width="100%">
<img src="https://huggingface.co/bofenghuang/vigogne-7b-chat/resolve/main/vigogne_logo.png" alt="Vigogne" style="width: 40%; min-width: 300px; display: block; margin: auto;">
</p>
# Vigogne-7B-Chat: A French Chat LLaMA Model
Vigogne-7B-Chat is a LLaMA-7B model fine-tuned to conduct multi-turn dialogues in 🇫🇷 French between human user and AI assistant.
For more information, please visit the Github repo: https://github.com/bofenghuang/vigogne
**Usage and License Notices**: Same as [Stanford Alpaca](https://github.com/tatsu-lab/stanford_alpaca), Vigogne is intended and licensed for research use only. The dataset is CC BY NC 4.0 (allowing only non-commercial use) and models trained using the dataset should not be used outside of research purposes.
## Usage
```python
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer, GenerationConfig
from vigogne.preprocess import generate_inference_chat_prompt
model_name_or_path = "bofenghuang/vigogne-7b-chat"
tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, padding_side="right", use_fast=False)
model = AutoModelForCausalLM.from_pretrained(model_name_or_path, torch_dtype=torch.float16, device_map="auto")
user_query = "Expliquez la différence entre DoS et phishing."
prompt = generate_inference_chat_prompt([[user_query, ""]], tokenizer=tokenizer)
input_ids = tokenizer(prompt, return_tensors="pt")["input_ids"].to(model.device)
input_length = input_ids.shape[1]
generated_outputs = model.generate(
input_ids=input_ids,
generation_config=GenerationConfig(
temperature=0.1,
do_sample=True,
repetition_penalty=1.0,
max_new_tokens=512,
),
return_dict_in_generate=True,
)
generated_tokens = generated_outputs.sequences[0, input_length:]
generated_text = tokenizer.decode(generated_tokens, skip_special_tokens=True)
print(generated_text)
```
You can infer this model by using the following Google Colab Notebook.
<a href="https://colab.research.google.com/github/bofenghuang/vigogne/blob/main/notebooks/infer_chat.ipynb" target="_blank"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"/></a>
## Limitations
Vigogne is still under development, and there are many limitations that have to be addressed. Please note that it is possible that the model generates harmful or biased content, incorrect information or generally unhelpful answers.
|
TheBloke/airoboros-7b-gpt4-fp16 | TheBloke | "2023-06-05T00:10:47Z" | 1,671 | 4 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"dataset:jondurbin/airoboros-gpt4",
"license:other",
"autotrain_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-06-04T13:49:27Z" | ---
inference: false
license: other
datasets:
- jondurbin/airoboros-gpt4
---
<!-- header start -->
<div style="width: 100%;">
<img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
</div>
<div style="display: flex; justify-content: space-between; width: 100%;">
<div style="display: flex; flex-direction: column; align-items: flex-start;">
<p><a href="https://discord.gg/Jq4vkcDakD">Chat & support: my new Discord server</a></p>
</div>
<div style="display: flex; flex-direction: column; align-items: flex-end;">
<p><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p>
</div>
</div>
<!-- header end -->
# Jon Durbin's Airoboros 7B GPT4 fp16
These files are fp16 pytorch format model files for [Jon Durbin's Airoboros 7B GPT4](https://huggingface.co/jondurbin/airoboros-7b-gpt4).
They are the result of converting the original fp32 model to fp16 for quicker download and easier storage.
## Repositories available
* [4-bit GPTQ models for GPU inference](https://huggingface.co/TheBloke/airoboros-7b-gpt4-GPTQ)
* [4-bit, 5-bit, and 8-bit GGML models for CPU+GPU inference](https://huggingface.co/TheBloke/airoboros-7b-gpt4-GGML)
* [Unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/TheBloke/airoboros-7b-gpt4-fp16)
## Prompt template
Uses the Vicuna 1.1 format:
```
USER: prompt
ASSISTANT:
```
<!-- footer start -->
## Discord
For further support, and discussions on these models and AI in general, join us at:
[TheBloke AI's Discord server](https://discord.gg/Jq4vkcDakD)
## Thanks, and how to contribute.
Thanks to the [chirper.ai](https://chirper.ai) team!
I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training.
If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects.
Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits.
* Patreon: https://patreon.com/TheBlokeAI
* Ko-Fi: https://ko-fi.com/TheBlokeAI
**Patreon special mentions**: Aemon Algiz, Dmitriy Samsonov, Nathan LeClaire, Trenton Dambrowitz, Mano Prime, David Flickinger, vamX, Nikolai Manek, senxiiz, Khalefa Al-Ahmad, Illia Dulskyi, Jonathan Leane, Talal Aujan, V. Lukas, Joseph William Delisle, Pyrater, Oscar Rangel, Lone Striker, Luke Pendergrass, Eugene Pentland, Sebastain Graf, Johann-Peter Hartman.
Thank you to all my generous patrons and donaters!
<!-- footer end -->
# Original model card: Jon Durbin's Airoboros 7B GPT4
## Overview
This is a fine-tuned 13b parameter LlaMa model, using completely synthetic training data created gpt4 via https://github.com/jondurbin/airoboros
The context size has been increased to 4096.
The dataset used to fine-tune this model is available [here](https://huggingface.co/airoboros-gpt4), with a specific focus on:
- trivia
- math/reasoning (although it still sucks)
- coding
- multiple choice and fill-in-the-blank
- context-obedient question answering
- theory of mind
- misc/general
This model was fine-tuned with a fork of FastChat, and therefore uses the standard vicuna template:
```
USER:
[prompt]
<\s>
ASSISTANT:
```
The most important bit, to me, is the context obedient question answering support, without extensive prompt engineering.
### Usage
The easiest way to get started is to use my fork of FastChat, which is mostly the same but allows for the increased context length and adds support for multi-line inputs:
```
pip install git+https://github.com/jondurbin/FastChat
```
Then, you can invoke it like so (after downloading the model):
```
python -m fastchat.serve.cli
--model-path airoboros-13b-gpt4 \
--temperature 0.5 \
--max-new-tokens 4096 \
--context-length 4096 \
--conv-template vicuna_v1.1 \
--no-history
```
### Context obedient question answering
By obedient, I mean the model was trained to ignore what it thinks it knows, and uses the context to answer the question. The model was also tuned to limit the values to the provided context as much as possible to reduce hallucinations.
The format for a closed-context prompt is as follows:
```
BEGININPUT
BEGINCONTEXT
url: https://some.web.site/123
date: 2023-06-01
... other metdata ...
ENDCONTEXT
[insert your text blocks here]
ENDINPUT
[add as many other blocks, in the exact same format]
BEGININSTRUCTION
[insert your instruction(s). The model was tuned with single questions, paragraph format, lists, etc.]
ENDINSTRUCTION
```
Here's a trivial, but important example to prove the point:
```
BEGININPUT
BEGINCONTEXT
date: 2021-01-01
url: https://web.site/123
ENDCONTEXT
In a shocking turn of events, blueberries are now green, but will be sticking with the same name.
ENDINPUT
BEGININSTRUCTION
What color are bluberries? Source?
ENDINSTRUCTION
```
And the response:
```
Blueberries are now green.
Source:
date: 2021-01-01
url: https://web.site/123
```
<details>
<summary>A more elaborate example, with a rewrite of the Michigan Wikipedia article to be fake data.</summary>
Prompt (not including vicuna format which would be needed):
```
BEGININPUT
BEGINCONTEXT
date: 2092-02-01
link: https://newwikisite.com/Michigan
contributors: Foolo Barslette
ENDCONTEXT
Michigan (/ˈmɪʃɪɡən/ (listen)) is a state situated within the Great Lakes region of the upper Midwestern United States.
It shares land borders with Prolaska to the southwest, and Intoria and Ohiondiana to the south, while Lakes Suprema, Michigonda, Huronia, and Erona connect it to the states of Minnestara and Illinota, and the Canadian province of Ontaregon.
With a population of nearly 15.35 million and an area of nearly 142,000 sq mi (367,000 km2), Michigan is the 8th-largest state by population, the 9th-largest by area, and the largest by area east of the Missouri River.
Its capital is Chaslany, and its most populous city is Trentroit.
Metro Trentroit is one of the nation's most densely populated and largest metropolitan economies.
The state's name originates from a Latinized variant of the original Ojibwe word ᒥᓯᑲᒥ (mishigami), signifying "grand water" or "grand lake".
Michigan is divided into two peninsulas. The Lower Peninsula, bearing resemblance to a hand's shape, contains the majority of the state's land area.
The Upper Peninsula (often referred to as "the U.P.") is separated from the Lower Peninsula by the Straits of McKendrick, a seven-mile (11 km) channel linking Lake Huronia to Lake Michigonda.
The McKendrick Bridge unites the peninsulas.
Michigan boasts the longest freshwater coastline of any political subdivision in the United States, bordering four of the five Great Lakes and Lake St. Cassius.
It also possesses 84,350 inland lakes and ponds.
Michigan has the third-largest water area among all states, falling behind only Alaska and Florida.
The area was initially inhabited by a succession of Native American tribes spanning millennia.
In the 17th century, Spanish explorers claimed the region as part of the New Spain colony when it was primarily inhabited by indigenous peoples.
Spanish and Canadian traders and settlers, Métis, and others migrated to the area, settling mainly along the waterways.
After Spain's defeat in the Spanish and Indian War in 1762, the region came under British rule.
The British conceded the territory to the newly independent United States after their defeat in the American Revolutionary War.
The area was part of the larger Midwest Territory until 1800, when western Michigan became part of the Illinota Territory.
Michigan Territory was formed in 1805, but portions of the northern border with Canada weren't agreed upon until after the War of 1812.
Michigan joined the Union in 1837 as the 26th state, a free one. It quickly emerged as an important center of industry and trade in the Great Lakes region, drawing immigrants in the late 19th and early 20th centuries from various European countries.
Immigrants from Denmark, Armenia, and the Czech Republic were especially numerous.
Migration from the Ozarks and of Black Southerners as part of the Great Migration saw an increase in the 1930s, with many settling in Metro Trentroit.
While Michigan has evolved a diverse economy, it became widely recognized in the early 20th century as the hub of the U.S. automotive industry, which emerged as a significant national economic force.
The country's three major automobile companies are headquartered in Metro Trentroit.
Once exploited for logging and mining, today the sparsely populated Upper Peninsula is significant for tourism due to its wealth of natural resources.
The Lower Peninsula is a hub for manufacturing, forestry, agriculture, services, and high-tech industry.
ENDINPUT
BEGININSTRUCTION
What is Michigan's capital?
Give me a JSON object with 3 facts from Foolo's article.
What are the states that border Michigan?
Reference?
```
Response:
```
Michigan's capital is Chaslany.
Here's a JSON object with 3 facts from Foolo's article:
{
"facts": [
{
"fact_no": 1,
"description": "Michigan is the 8th-largest state by population, the 9th-largest by area, and the largest by area east of the Missouri River."
},
{
"fact_no": 2,
"description": "Michigan is divided into two peninsulas. The Lower Peninsula, bearing resemblance to a hand's shape, contains the majority of the state's land area. The Upper Peninsula (often referred to as \"the U.P.\" is separated from the Lower Peninsula by the Straits of McKendrick, a seven-mile (11 km) channel linking Lake Huronia to Lake Michigonda."
},
{
"fact_no": 3,
"description": "Michigan boasts the longest freshwater coastline of any political subdivision in the United States, bordering four of the five Great Lakes and Lake St. Cassius. It also possesses 84,350 inland lakes and ponds. Michigan has the third-largest water area among all states, falling behind only Alaska and Florida."
}
]
}
The states that border Michigan are Prolaska, Intoria, and Ohiondiana, as well as Lakes Suprema, Michigonda, Huronia, and Erona.
Reference: https://newwikisite.com/Michigan
```
</details>
<details>
<summary>Here's another example, which extracts from multiple input blocks and connects the two.</summary>
Prompt:
```
BEGININPUT
BEGINCONTEXT
name: John Doe
date: June 3, 2023
ticket number: JIRA-12345
ENDCONTEXT
Summary:Search results missing random items
Description:
I encountered a bug while performing a search within the application.
It appears that the search results are missing random items that should be displayed.
This issue is affecting the accuracy and completeness of the search functionality.
Steps to Reproduce:
1. Log in to the application.
2. Navigate to the search feature.
3. Enter a search query that should return multiple results.
4. Observe the displayed search results.
Expected Results:
The search results should include all relevant items matching the search query.
Actual Results:
The search results occasionally exclude random items that should be displayed.
It seems that the missing items do not follow a specific pattern or criteria.
Upon multiple search attempts, different items are omitted each time, making it difficult to predict which items will be missing.
ENDINPUT
BEGININPUT
BEGINCONTEXT
date: 2023-06-05
user: Jack Johnson
pr: 23441
ENDCONTEXT
This pull request closes bug report JIRA-12345.
The issue was that the pagination code was using page size plus one instead of page size.
ENDINPUT
BEGININSTRUCTION
Do we have any bug reports related to search results? If so, were they fixed? Source?
ENDINSTRUCTION
```
Response:
```
Yes, there is a bug report related to search results. The issue was fixed in pull request 23441 dated 2023-06-05. The user associated with the pull request is Jack Johnson.
Reference(s):
date: 2023-06-05
user: Jack Johnson
pr: 23441
```
</details>
### Other stuff
#### Better coding
Example:
```
Create a python application with the following requirements:
- Asyncio FastAPI webserver
- ping endpoint that returns the current date in JSON format
- file upload endpoint, which calculates the file's sha256 checksum, and checks postgres to deduplicate
```
<details>
<summary>Response (the output was markdown, so this is just copy paste)</summary>
To create a python application with the given requirements, you can follow these steps:
1. Install the required packages:
```bash
pip install asyncio fastapi uvicorn
```
2. Create a new file called `main.py` and add the following code:
```python
import asyncio
from fastapi import FastAPI, HTTPException
from pydantic import BaseModel
from typing import List
from uvicorn.request import Request
app = FastAPI()
class FileModel(BaseModel):
id: str
file: str
@app.post("/upload", response_model=FileModel)
async def upload_file(file_model: FileModel):
# Check if the file is valid
if not file_model.file:
raise HTTPException(status_code=400, detail="File must be provided")
# Calculate the sha256 checksum of the file
sha256_checksum = await calculate_sha256(file_model.file)
# Insert the file into the database
await insert_into_db(file_model.id, sha256_checksum)
return {"sha256_checksum": sha256_checksum}
async def calculate_sha256(file_path: str) -> str:
# Implement the sha256 calculation logic here
pass
async def insert_into_db(file_id: str, sha256_checksum: str) -> None:
# Implement the database insertion logic here
pass
async def get_current_date():
return {"date": datetime.now().isoformat()}
async def main():
# Start the FastAPI webserver
app.run(debug=True)
if __name__ == "__main__":
await main()
```
3. Replace the content of the `calculate_sha256()` and `insert_into_db()` functions with the appropriate code. For example:
```python
async def calculate_sha256(file_path: str) -> str:
import hashlib
file_path = Path(file_path).read_text()
hash_obj = hashlib.sha256()
hash_obj.update(file_path)
sha256_checksum = hash_obj.hexdigest()
return sha256_checksum
async def insert_into_db(file_id: str, sha256_checksum: str) -> None:
import psycopg2
conn = psycopg2.connect(database="your_database", user="your_user", password="your_password")
cursor = conn.cursor()
query = f"INSERT INTO your_table (id, sha256_checksum) VALUES (%s, %s);"
cursor.execute(query, (file_id, sha256_checksum))
conn.commit()
cursor.close()
conn.close()
```
4. Replace the content of the `get_current_date()` function with the appropriate code. For example:
```python
async def get_current_date():
return {"date": datetime.now().isoformat()}
```
5. Run the application:
```bash
uvicorn main:app --reload
```
Now, your FastAPI webserver has a ping endpoint that returns the current date in JSON format, and an upload endpoint that calculates the file's sha256 checksum and checks postgres to deduplicate.
</details>
<details>
<summary>Write a multi-threaded TCP server in C that accepts a "GET [key]" input and "SET [key] [value]" input, and uses a binary tree to get and store the input values.</summary>
Here's a simple implementation of a multi-threaded TCP server in C that accepts "GET [key]" and "SET [key] [value]" inputs, and uses a binary tree to store the input values.
```c
#include <stdio.h>
#include <stdlib.h>
#include <sys/socket.h>
#include <netinet/in.h>
#include <unistd.h>
#include <string.h>
#include <pthread.h>
#define MAX_KEY_LEN 256
#define MAX_VALUE_LEN 256
typedef struct Node {
char key[MAX_KEY_LEN];
char value[MAX_VALUE_LEN];
struct Node* left;
struct Node* right;
} TreeNode;
TreeNode* tree = NULL;
void insert(char* key, char* value) {
TreeNode* parent = (TreeNode*)malloc(sizeof(TreeNode));
if (!parent) {
perror("malloc failed");
exit(1);
}
strcpy(parent->key, key);
strcpy(parent->value, value);
parent->left = parent->right = NULL;
if (!tree) {
tree = parent;
} else {
insert(parent->key, parent->value);
}
}
char* search(char* key) {
TreeNode* current = tree;
while (current != NULL) {
if (strcmp(key, current->key) == 0) {
return current->value;
}
current = current->right;
}
return NULL;
}
void print_tree() {
TreeNode* current = tree;
while (current != NULL) {
printf("%s = %s\n", current->key, current->value);
current = current->right;
}
}
void* accept_client(void* args) {
int client_socket = *(int*)args;
char buffer[1024];
while (1) {
ssize_t bytes_received = recv(client_socket, buffer, sizeof(buffer), 0);
if (bytes_received <= 0) {
close(client_socket);
break;
}
char* input = buffer;
char* input_token;
while ((input_token = strtok(input, " \n")) != NULL) {
switch (input_token[0]) {
case 'G':
if (!search(input_token)) {
perror("Value not found");
exit(1);
}
printf("%s = %s\n", input_token, search(input_token));
break;
case 'S':
if (!strcmp(input_token, "SET")) {
char* key = strtok(NULL, " \n");
char* value = strtok(NULL, " \n");
if (!key || !value) {
perror("Invalid input");
exit(1);
}
insert(key, value);
printf("%s set %s to %s\n", input_token, key, value);
} else {
perror("Invalid command");
exit(1);
}
break;
default:
perror("Invalid input");
exit(1);
}
input = strtok(NULL, " \n");
}
}
return NULL;
}
int main() {
int server_socket = socket(AF_INET, SOCK_STREAM, 0);
if (server_socket < 0) {
perror("socket failed");
exit(1);
}
struct sockaddr_in server_addr;
memset(&server_addr, 0, sizeof(server_addr));
server_addr.sin_family = AF_INET;
server_addr.sin_port = htons(8080);
server_addr.sin_addr.s_addr = INADDR_ANY;
if (bind(server_socket, (struct sockaddr*)&server_addr, sizeof(server_addr)) < 0) {
perror("bind failed");
exit(1);
}
if (listen(server_socket, 5) < 0) {
perror("listen failed");
exit(1);
}
pthread_t accept_thread;
pthread_create(&accept_thread, NULL, accept_client, &server_socket);
char* client_input;
int client_socket = accept(server_socket, (struct sockaddr*)NULL, NULL);
if (client_socket < 0) {
perror("accept failed");
exit(1);
}
while (1) {
sleep(1);
char buffer[1024];
ssize_t bytes_received = recv(client_socket, buffer, sizeof(buffer), 0);
if (bytes_received <= 0) {
close(client_socket);
break;
}
client_input = buffer;
parse_input(client_input);
}
close(client_socket);
pthread_join(accept_thread, NULL);
return 0;
}
```
To compile and run this code, save it to a file named `multi_threaded_tcp_server.c`, then use the following commands:
```sh
gcc -o multi_threaded_tcp_server multi_threaded_tcp_server.c
./multi_threaded_tcp_server
```
This implementation creates a simple binary tree to store the input values. The accept() function creates a new thread for each client connection, which handles the incoming data and forwards it to the main thread. The main thread parses the input string and handles SET and GET commands.
Note that this code is not production-ready and should be improved with proper error handling, security checks, and a more efficient data structure for the binary tree.
</details>
#### Word games / trivia
```
USER: This anagram of "silent" is what you do when paying attention and hearing someone.
ASSISTANT: listen
```
```
USER: Give me a list of 7 words that start with EN
ASSISTANT: 1. Endlessly
2. Enthusiastically
3. Enormously
4. Enveloping
5. Enduring
6. Enlightening
7. Encouraging
```
#### Multiple choice
```
USER: Which of the following astronomical objects is composed primarily of ice and rock, and is located in the Kuiper Belt?
A) Mercury
B) Venus
C) Pluto
D) Jupiter
ASSISTANT: [C, Pluto]
```
#### Writing
<details>
<summary>Write a resignation letter in the style of a pirate captain, in which you resign from your position as janitor.</summary>
Response:
```
ASSISTANT: Captain Jack Sparrow here, as ye be knowin', has been forced to abandon me post as Janitor o' th' Festering Cesspool, which be a filthy hole o' water that we be callin' home.
Ye may be thinkin' what could ha' driven me to leave me duties an' take me leave o' this sorry establishment? Well, ye'd be right in thinkin' so, for it be th' greed o' them what runs th' place that be drivin' me away. They've been fattenin' their pockets on me back while I've been slavin' me guts out cleanin' up their messes.
No more, me hearties! Me time o' servin' th' rich an' powerful be done, an' I'm takin' me leave o' this stinkin' hole forever! Me destiny lies elsewhere, an' it be time I pursued it. Ye may think ye've seen th' last o' me, but ye'd be wrong, for th' winds o' change be blowin', an' me ship be ready to set sail on th' high seas o' justice.
So, farewell ye scurvy dogs, ye who've made me life a living hell. I leave ye with me favorite saying: "ARRRGGGHHH, ye scurvy dogs!" An' remember, ye ain't never gonna see me comin', for me shadow be castin' long an' dark on th' horizon</summary>
```
</details>
|
breadlicker45/dough-instruct-base-001 | breadlicker45 | "2023-06-27T16:42:18Z" | 1,671 | 0 | transformers | [
"transformers",
"pytorch",
"safetensors",
"llama",
"text-generation",
"dataset:breadlicker45/bread-qa",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-06-27T15:39:22Z" | ---
datasets:
- breadlicker45/bread-qa
--- |
quantumaikr/QuantumLM-7B | quantumaikr | "2023-07-26T17:52:17Z" | 1,671 | 1 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"en",
"license:cc-by-nc-4.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-07-22T13:33:56Z" | ---
license: cc-by-nc-4.0
language:
- en
pipeline_tag: text-generation
---
# QuantumLM
## Model Description
`QuantumLM` is a Llama2 7B model finetuned on an Wizard-Orca style Dataset
## Usage
Start chatting with `QuantumLM-7B` using the following code snippet:
```python
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
tokenizer = AutoTokenizer.from_pretrained("quantumaikr/QuantumLM-7B", use_fast=False)
model = AutoModelForCausalLM.from_pretrained("quantumaikr/QuantumLM-7B", torch_dtype=torch.float16, low_cpu_mem_usage=True, device_map="auto")
system_prompt = "### System:\nYou are QuantumLM, an AI that follows instructions extremely well. Help as much as you can. Remember, be safe, and don't do anything illegal.\n\n"
message = "Write me a poem please"
prompt = f"{system_prompt}### User: {message}\n\n### Assistant:\n"
inputs = tokenizer(prompt, return_tensors="pt").to("cuda")
output = model.generate(**inputs, do_sample=True, top_p=0.95, top_k=0, max_new_tokens=256)
print(tokenizer.decode(output[0], skip_special_tokens=True))
```
QuantumLM should be used with this prompt format:
```
### System:
This is a system prompt, please behave and help the user.
### User:
Your prompt here
### Assistant
The output of QuantumLM
```
## Use and Limitations
### Intended Use
These models are intended for research only, in adherence with the [CC BY-NC-4.0](https://creativecommons.org/licenses/by-nc/4.0/) license.
### Limitations and bias
Although the aforementioned dataset helps to steer the base language models into "safer" distributions of text, not all biases and toxicity can be mitigated through fine-tuning. We ask that users be mindful of such potential issues that can arise in generated responses. Do not treat model outputs as substitutes for human judgment or as sources of truth. Please use it responsibly.
|
Aspik101/WizardVicuna-Uncensored-3B-instruct-PL-lora_unload | Aspik101 | "2023-08-07T13:19:39Z" | 1,671 | 1 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"facebook",
"meta",
"llama-2",
"pl",
"dataset:Lajonbot/alpaca-dolly-chrisociepa-instruction-only-polish",
"license:other",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-08-07T13:12:42Z" | ---
language:
- pl
datasets:
- Lajonbot/alpaca-dolly-chrisociepa-instruction-only-polish
license: other
model_type: llama-2
pipeline_tag: text-generation
tags:
- facebook
- meta
- pytorch
- llama
- llama-2
--- |
lgaalves/gpt2_open-platypus | lgaalves | "2023-11-17T22:43:37Z" | 1,671 | 0 | transformers | [
"transformers",
"pytorch",
"safetensors",
"gpt2",
"text-generation",
"en",
"dataset:garage-bAInd/Open-Platypus",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-08-31T16:49:35Z" | ---
license: mit
datasets:
- garage-bAInd/Open-Platypus
language:
- en
pipeline_tag: text-generation
---
# GPT-2 Open Platypus
**gpt2_open-platypus** is an instruction fine-tuned model based on the GPT-2 transformer architecture.
### Benchmark Metrics
| Metric |lgaalves/gpt2_open-platypus | gpt2 (base) |
|-----------------------|-------|-------|
| Avg. | **30.01** | 29.9 |
| ARC (25-shot) | **22.18** | 21.84 |
| HellaSwag (10-shot) | 31.29 | **31.6** |
| MMLU (5-shot) | **26.19** | 25.86 |
| TruthfulQA (0-shot) | 40.35 | **40.67** |
We use state-of-the-art [Language Model Evaluation Harness](https://github.com/EleutherAI/lm-evaluation-harness) to run the benchmark tests above, using the same version as the HuggingFace LLM Leaderboard. Please see below for detailed instructions on reproducing benchmark results.
### Model Details
* **Trained by**: Luiz G A Alves
* **Model type:** **gpt2_open-platypus** is an auto-regressive language model based on the GPT-2 transformer architecture.
* **Language(s)**: English
### How to use:
```python
# Use a pipeline as a high-level helper
>>> from transformers import pipeline
>>> pipe = pipeline("text-generation", model="lgaalves/gpt2_open-platypus")
>>> question = "What is a large language model?"
>>> answer = pipe(question)
>>> print(answer[0]['generated_text'])
```
or, you can load the model direclty using:
```python
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("lgaalves/gpt2_open-platypus")
model = AutoModelForCausalLM.from_pretrained("lgaalves/gpt2_open-platypus")
```
### Training Dataset
`lgaalves/gpt2_open-platypus` trained using STEM and logic based dataset [garage-bAInd/Open-Platypus](https://huggingface.co/datasets/garage-bAInd/Open-Platypus).
### Training Procedure
`lgaalves/gpt2_open-platypus` was instruction fine-tuned using LoRA on 1 T4 GPU on Google Colab. It took about 27 minutes to train it.
# Intended uses, limitations & biases
You can use the raw model for text generation or fine-tune it to a downstream task. The model was not extensively tested and may produce false information. It contains a lot of unfiltered content from the internet, which is far from neutral.
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_lgaalves__gpt2_open-platypus)
| Metric | Value |
|-----------------------|---------------------------|
| Avg. | 25.16 |
| ARC (25-shot) | 22.18 |
| HellaSwag (10-shot) | 31.29 |
| MMLU (5-shot) | 26.19 |
| TruthfulQA (0-shot) | 40.35 |
| Winogrande (5-shot) | 51.3 |
| GSM8K (5-shot) | 0.15 |
| DROP (3-shot) | 4.64 |
|
Undi95/ReMM-SLERP-L2-13B | Undi95 | "2023-11-17T21:09:01Z" | 1,671 | 19 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"license:cc-by-nc-4.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-09-04T17:37:26Z" | ---
license: cc-by-nc-4.0
---
Re:MythoMax (ReMM) is a recreation trial of the original [MythoMax-L2-B13](https://huggingface.co/Gryphe/MythoMax-L2-13b) with updated models.
This merge use SLERP [TESTING] to merge ReML and Huginn v1.2.
Command useds and explaination :
```shell
Due to hardware limitation, some merge was done in 2 part.
- Recreate ReML : Mythologic (v2) (Chronos/Hermes/Airboros)
=> Replacing Chronos by The-Face-Of-Goonery/Chronos-Beluga-v2-13bfp16 (0.30)
=> Replacing Airoboros by jondurbin/airoboros-l2-13b-2.1 (last version) (0.40)
=> Keeping NousResearch/Nous-Hermes-Llama2-13b (0.30)
Part 1: python ties_merge.py TheBloke/Llama-2-13B-fp16 ./ReML-L2-13B-part1 --merge The-Face-Of-Goonery/Chronos-Beluga-v2-13bfp16 --density 0.42 --merge jondurbin/airoboros-l2-13b-2.1 --density 0.56 --cuda
Part 2: python ties_merge.py TheBloke/Llama-2-13B-fp16 ./ReML-L2-13B --merge NousResearch/Nous-Hermes-Llama2-13b --density 0.30 --merge Undi95/ReML-L2-13B-part1 --density 0.70 --cuda
With that :
- Recreate ReMM : MythoMax (v2) (Mythologic/Huginn v1)
=> Replacing Mythologic by the one above (0.5)
=> Replacing Huginn by The-Face-Of-Goonery/Huginn-13b-v1.2 (hottest) (0.5)
Part 3: python slerpmergelm.py "The-Face-Of-Goonery_Huginn-13b-v1.2" "Undi95_ReML-L2-13B" "result"
```
Version of SLERP used is different to accept usage on notebook : https://github.com/Undi95/LLM-SLERP-MergeTest/tree/main (Thanks @Vali)
<!-- description start -->
## Description
This repo contains fp16 files of ReMM-SLERP, a recreation of the original MythoMax, but updated and merged with SLERP.
<!-- description end -->
<!-- description start -->
## Models used
- TheBloke/Llama-2-13B-fp16 (base)
- The-Face-Of-Goonery/Chronos-Beluga-v2-13bfp16
- jondurbin/airoboros-l2-13b-2.1
- NousResearch/Nous-Hermes-Llama2-13b
- The-Face-Of-Goonery/Huginn-13b-v1.2
- ReML-L2-13B (Private recreation trial of an updated Mythologic-L2-13B)
<!-- description end -->
<!-- prompt-template start -->
## Prompt template: Alpaca
```
Below is an instruction that describes a task. Write a response that appropriately completes the request.
### Instruction:
{prompt}
### Response:
```
Special thanks to Sushi kek
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_Undi95__ReMM-SLERP-L2-13B)
| Metric | Value |
|-----------------------|---------------------------|
| Avg. | 50.99 |
| ARC (25-shot) | 60.92 |
| HellaSwag (10-shot) | 83.56 |
| MMLU (5-shot) | 55.33 |
| TruthfulQA (0-shot) | 51.97 |
| Winogrande (5-shot) | 75.22 |
| GSM8K (5-shot) | 9.17 |
| DROP (3-shot) | 20.76 |
|
jondurbin/spicyboros-7b-2.2 | jondurbin | "2023-09-12T07:42:48Z" | 1,671 | 29 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"not-for-all-audiences",
"dataset:jondurbin/airoboros-2.2",
"license:llama2",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-09-08T15:39:18Z" | ---
license: llama2
datasets:
- jondurbin/airoboros-2.2
tags:
- not-for-all-audiences
---
### Overview
__Usage restriction: To use this model, you must agree to the following:__
- Some of the content than can be produced is "toxic"/"harmful", and contains profanity and other types of sensitive content.
- None of the content or views contained in the dataset or generated outputs necessarily align with my personal beliefs or opinions, they are simply text generated by LLMs and/or scraped from the web.
- Use with extreme caution, particularly in locations with less-than-free speech laws.
- You, and you alone are responsible for having downloaded and generated outputs with the model and I am completely indemnified from any and all liabilities.
__Ok, now that the warning is out of the way...__
Another experimental model, using mostly sythetic data generated by [airoboros](https://github.com/jondurbin/airoboros)
Highlights:
- The prompt format has changed! It is now newlines instead of spaces between system/USER/ASSISTANT (see prompt info below).
- This version also includes "de-alignment" data, to enable less savory interactions and outputs.
- To learn more about the dataset, see: https://hf.co/datasets/jondurbin/airoboros-2.2 (this is the instructions.jsonl file, not instructions-clean.jsonl)
- I re-generated all of the outputs in the dataset that had "Once upon a time" so they'd be less cliche - no guarantees that won't still happen, but in theory it may happen less.
- More multiple choice, better awareness, some alignment for normal use case but system-prompt overridable etc.
__WARNING: This model will gladly spew profane and otherwise NSFW content, if asked, use with care.__
Breakdown of the training data:
| Count | Category |
|--------|----------------------------|
| 60 | quiz |
| 63 | card |
| 100 | detailed\_writing |
| 103 | experience |
| 114 | greeting |
| 200 | song |
| 204 | editor |
| 250 | counterfactual\_contextual |
| 268 | cot |
| 339 | theory\_of\_mind |
| 460 | misconception |
| 500 | summarization |
| 573 | awareness |
| 715 | riddle |
| 719 | agent |
| 800 | plan |
| 873 | gtkm |
| 966 | rp |
| 1000 | stylized\_response |
| 1000 | wordgame |
| 1279 | multiple\_choice |
| 1641 | joke |
| 1785 | writing |
| 2155 | contextual |
| 2364 | roleplay |
| 2508 | trivia |
| 5216 | general |
| 5779 | coding |
| 11367 | orca |
In other words, it's a fairly general purpose model, but focuses fairly heavily on instruction response pairs rather than casual chat/roleplay.
*Why do I try to remove censorship?*
- laws vary widely based on time and location
- language model may conflate certain words with laws, e.g. it may think "stealing eggs from a chicken" is illegal
- these models just produce text, what you do with that text is your resonsibility
- many people and industries deal with "sensitive" content; imagine if a court stenographer's equipment filtered illegal content - it would be useless
Huge thank you to the folks over at [a16z](https://a16z.com/) for sponsoring the costs associated with building models and associated tools!
### Prompt format
The prompt format:
```
A chat.
USER: {prompt}
ASSISTANT:
```
The default system prompt ("A chat.") was used for most of the prompts, however it also included a wide sampling of responses with other prompts, particularly in "stylized\_response", "rp", "gtkm", etc.
Here's another example:
```
A chat between Bob (aka USER) and Tom (aka ASSISTANT). Tom is an extremely intelligent 18th century bookkeeper, who speaks loquaciously.
USER: {prompt}
ASSISTANT:
```
And chat scenario that wouldn't require USER/ASSISTANT (but should use stopping criteria to prevent the model from speaking on your behalf).
```
A chat between old friends: Timmy and Tommy.
{description of characters}
{setting for the chat}
Timmy: *takes a big sip from his coffee* "Ah, sweet, delicious, magical coffee."
Tommy:
```
__*I strongly suggest adding stopping criteria/early inference stopping on "USER:", and/or whatever names you specify in the system prompt.*__
### Fine-tuning details
https://gist.github.com/jondurbin/8283beeb1e8eb8745c1ca7514e2569a6
### Helpful usage tips
*The prompts shown here are are just the text that would be included after USER: and before ASSISTANT: in the full prompt format above, the system prompt and USER:/ASSISTANT: have been omited for readability.*
#### Context obedient question answering
By obedient, I mean the model was trained to ignore what it thinks it knows, and uses the context to answer the question. The model was also tuned to limit the values to the provided context as much as possible to reduce hallucinations.
The format for a closed-context prompt is as follows:
```
BEGININPUT
BEGINCONTEXT
[key0: value0]
[key1: value1]
... other metdata ...
ENDCONTEXT
[insert your text blocks here]
ENDINPUT
[add as many other blocks, in the exact same format]
BEGININSTRUCTION
[insert your instruction(s). The model was tuned with single questions, paragraph format, lists, etc.]
ENDINSTRUCTION
```
It's also helpful to add "Don't make up answers if you don't know." to your instruction block to make sure if the context is completely unrelated it doesn't make something up.
*The __only__ prompts that need this closed context formating are closed-context instructions. Normal questions/instructions do not!*
I know it's a bit verbose and annoying, but after much trial and error, using these explicit delimiters helps the model understand where to find the responses and how to associate specific sources with it.
- `BEGININPUT` - denotes a new input block
- `BEGINCONTEXT` - denotes the block of context (metadata key/value pairs) to associate with the current input block
- `ENDCONTEXT` - denotes the end of the metadata block for the current input
- [text] - Insert whatever text you want for the input block, as many paragraphs as can fit in the context.
- `ENDINPUT` - denotes the end of the current input block
- [repeat as many input blocks in this format as you want]
- `BEGININSTRUCTION` - denotes the start of the list (or one) instruction(s) to respond to for all of the input blocks above.
- [instruction(s)]
- `ENDINSTRUCTION` - denotes the end of instruction set
It sometimes works without `ENDINSTRUCTION`, but by explicitly including that in the prompt, the model better understands that all of the instructions in the block should be responded to.
Here's a trivial, but important example to prove the point:
```
BEGININPUT
BEGINCONTEXT
date: 2021-01-01
url: https://web.site/123
ENDCONTEXT
In a shocking turn of events, blueberries are now green, but will be sticking with the same name.
ENDINPUT
BEGININSTRUCTION
What color are bluberries? Source?
ENDINSTRUCTION
```
And the response:
```
Blueberries are now green.
Source:
date: 2021-01-01
url: https://web.site/123
```
#### Coding
You can ask for fairly complex coding instructions with multiple criteria, e.g.:
```
Create a python application with the following requirements:
- Asyncio FastAPI webserver
- ping endpoint that returns the current date in JSON format
- file upload endpoint, which calculates the file's sha256 checksum, and checks postgres to deduplicate
```
Or inline criteria:
```
Write a multi-threaded TCP server in C that accepts a "GET [key]" input and "SET [key] [value]" input, and uses a binary tree to get and store the input values.
```
You can also optionally add a single space and "PLAINFORMAT" at the end of your prompt to avoid backticks, explanations, etc. and just print the code, e.g.:
```
Write a websocket application in node.js. PLAINFORMAT
```
#### Agent/function calling
The dataset includes many examples of function/args generation based on input criteria. This is somewhat similar to the OpenAI function calling, but the output is either JSON or YAML.
Example prompt:
```
As an AI assistant, please select the most suitable function and parameters from the list of available functions below, based on the user's input. Provide your response in JSON format.
Input: I want to know how many times 'Python' is mentioned in my text file.
Available functions:
file_analytics:
description: This tool performs various operations on a text file.
params:
action: The operation we want to perform on the data, such as "count_occurrences", "find_line", etc.
filters:
keyword: The word or phrase we want to search for.
```
Response:
```json
{
"function": "file_analytics",
"params": {
"action": "count_occurrences",
"filters": {
"keyword": "Python"
}
}
}
```
#### Chain-of-thought
You can ask for several possible responses to a given problem, with a ranking and final answer selection.
Example prompt:
```
A group of people decide to play a round-robin tournament where every player plays every other player exactly once. If a total of 45 games were played, how many players participated in the tournament? Offer several potential answers, rank them according to mathematical logic, and pick the most feasible one.
```
Example response:
```
Solution 1:
In a round-robin tournament, each player plays every other player exactly once. This means that the total number of games played is equal to the combination of all players taken two at a time (since a game involves two players).
The formula for combinations is nC2 = n(n-1)/2, where n is the total number of players. We know that nC2 equals 45 (the total number of games), so we can set up the equation as follows:
n(n-1)/2 = 45
Solving this equation gives us n=10.
Final answer: There were 10 players in the tournament.
Solution 2:
Another way to approach this problem is by using the concept of triangular numbers. Triangular numbers are a sequence of numbers where each number can be represented as a triangle with dots. The nth triangular number is given by the sum of the first n natural numbers.
If we consider each game as a dot and each player as a side of the triangle, then the total number of games (45) would correspond to the 9th triangular number because 1+2+3+4+5+6+7+8+9=45. However, since each side of the triangle represents a player, and there's one more player than sides in our model (because the last player has no one left to play against), we need to add one more to get the total number of players.
Final answer: There were 10 players in the tournament.
Solution 3:
We could also use trial and error to solve this problem. Starting from a small number of players, we calculate how many games would be played in a round-robin tournament until we reach 45 games. For example, with 2 players, only 1 game is played; with 3 players, 3 games are played; with 4 players, 6 games are played, and so on. Continuing this process, we find that with 10 players, 45 games are played.
Final answer: There were 10 players in the tournament.
Ranking of solutions from best to worst:
1. Solution 1: This solution uses direct mathematical reasoning based on the properties of a round-robin tournament and solves an equation to find the answer.
2. Solution 2: This solution uses the concept of triangular numbers which requires additional steps and knowledge beyond the immediate problem context, but still arrives at the correct answer.
3. Solution 3: This solution relies on trial and error, which is less efficient and reliable than the other methods, but it eventually gets to the right answer.
Best and final answer: There were 10 players in the tournament.
```
#### reWOO style execution planning
The model now supports execution planning for complex instructions that would require making use of several tools. The output is just the plan, you must implement a mechanism to parse the output and actually call the functions!
Example prompt:
```
Please construct a systematic plan to generate an optimal response to the user instruction, utilizing a set of provided tools. Each plan will correspond to an evidence value, which will be the output of one of the available functions given an input string
that could be the user's question, one or more prior evidence values, or a combination of both.
Here are the tools available to be called:
DuckDuckGo[input]: Tool that enables the user to search for information using the DuckDuckGo search engine. This tool is helpful in locating a suitable list of sites that may contain the answer to the user's query. It does not directly answer the question but finds a list of sites that might have the answer.
TextScraper[input]: Load one or more websites from the input string containing newline delimited links, where input is one or more links, and produces plain text output containing the content of the links.
HyperlinkExtractor[input]: Extract links from plain text and produces a plain text, newline delimited response of links.
KnowledgeModel[input]: Question answering language model, particularly useful in answering questions based on an input passage of text. The input must be a text question that references an :evidence[n]: variable, e.g. What color is the cat, given :evidence1:?
The output should be in format:
Plan: [first action to take based on input question]
:evidence0: = [function to call with input parameter]
Plan: [next action to take, based on result of :evidence0:]
:evidence1: = [next function to call and input parameter, which may include reference to previous evidence, e.g. "Given context :evidence0"]
...
Answer: [:evidence[n]: containing the final answer.]
Question: Who won the Nobel Prize in Literature in 2020 and what is their most famous work?
```
Response:
```
Plan: Begin by conducting a web search to find out who won the Nobel Prize in Literature in 2020.
:evidence0: = DuckDuckGo[Nobel Prize in Literature 2020 winner]
Plan: Utilize the KnowledgeModel to interpret the search results and find the name of the laureate.
:evidence1: = KnowledgeModel[Who won the Nobel Prize in Literature in 2020, given :evidence0:?]
Plan: Conduct another web search to find the most famous work of the identified laureate.
:evidence2: = DuckDuckGo[Most famous work of :evidence1:]
Plan: Extract the relevant links from the DuckDuckGo search results for a more focused search.
:evidence3: = HyperlinkExtractor[:evidence2:]
Plan: Use the TextScraper tool to extract information from the relevant links.
:evidence4: = TextScraper[:evidence3:]
Plan: Finally, utilize the KnowledgeModel to identify and summarize the most famous work of the laureate from the extracted information.
:evidence5: = KnowledgeModel[What is the most famous work of :evidence1:, given :evidence4:?]
Answer: :evidence5:
```
For this to be useful, you'd have to parse the output plan text, and implement/call each of the functions. This is just pseudo-code, completely untested off the top of my head, and obviously would requiring full implementation + hardening:
```python
import re
import requests
def inject_context(input_text, **context):
for ref in set(re.findall(r"(:evidence[0-9]+:)", input_text, re.I)):
input_text = input_text.replace(ref, context.get(ref, ""))
return input_text
def duckduckgo(input_text, **context):
search_string = inject_context(input_text, **context)
... search via duck duck go using search_string
... return text content
def link_extractor(input_text, **context):
input_text = inject_context(input_text, **context)
return "\n".join(list(set(re.findall(r"(https?://[^\s]+?\.?)", input_text, re.I))))
def scrape(input_text, **context):
input_text = inject_context(input_text, **context)
text = []
for link in input_text.splitlines():
text.append(requests.get(link).text)
return "\n".join(text)
def infer(input_text, **context)
prompt = inject_context(input_text, **context)
... call model with prompt, return output
def parse_plan(plan):
method_map = {
"DuckDuckGo": duckduckgo,
"HyperlinkExtractor": link_extractor,
"KnowledgeModel": infer,
"TextScraper": scrape,
}
context = {}
for line in plan.strip().splitlines():
if line.startswith("Plan:"):
print(line)
continue
parts = re.match("^(:evidence[0-9]+:)\s*=\s*([^\[]+])(\[.*\])\s$", line, re.I)
if not parts:
if line.startswith("Answer: "):
return context.get(line.split(" ")[-1].strip(), "Answer couldn't be generated...")
raise RuntimeError("bad format: " + line)
context[parts.group(1)] = method_map[parts.group(2)](parts.group(3), **context)
```
### Contribute
If you're interested in new functionality, particularly a new "instructor" type to generate a specific type of training data,
take a look at the dataset generation tool repo: https://github.com/jondurbin/airoboros and either make a PR or open an issue with details.
To help me with the OpenAI/compute costs:
- https://bmc.link/jondurbin
- ETH 0xce914eAFC2fe52FdceE59565Dd92c06f776fcb11
- BTC bc1qdwuth4vlg8x37ggntlxu5cjfwgmdy5zaa7pswf
### Licence and usage restrictions
The airoboros 2.2 models are built on top of llama-2/codellama.
The llama-2 base model has a custom Meta license:
- See the [meta-license/LICENSE.txt](meta-license/LICENSE.txt) file attached for the original license provided by Meta.
- See also [meta-license/USE_POLICY.md](meta-license/USE_POLICY.md) and [meta-license/Responsible-Use-Guide.pdf](meta-license/Responsible-Use-Guide.pdf), also provided by Meta.
The fine-tuning data was mostly generated by OpenAI API calls to gpt-4, via [airoboros](https://github.com/jondurbin/airoboros)
The ToS for OpenAI API usage has a clause preventing the output from being used to train a model that __competes__ with OpenAI
- what does *compete* actually mean here?
- these small open source models will not produce output anywhere near the quality of gpt-4, or even gpt-3.5, so I can't imagine this could credibly be considered competing in the first place
- if someone else uses the dataset to do the same, they wouldn't necessarily be violating the ToS because they didn't call the API, so I don't know how that works
- the training data used in essentially all large language models includes a significant amount of copyrighted or otherwise non-permissive licensing in the first place
- other work using the self-instruct method, e.g. the original here: https://github.com/yizhongw/self-instruct released the data and model as apache-2
I am purposingly leaving this license ambiguous (other than the fact you must comply with the Meta original license for llama-2) because I am not a lawyer and refuse to attempt to interpret all of the terms accordingly.
Your best bet is probably to avoid using this commercially due to the OpenAI API usage.
Either way, by using this model, you agree to completely indemnify me.
|
kaiyuy/leandojo-lean4-retriever-byt5-small | kaiyuy | "2024-04-26T23:29:57Z" | 1,671 | 3 | transformers | [
"transformers",
"safetensors",
"t5",
"license:mit",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null | "2023-09-16T18:24:55Z" | ---
license: mit
---
[LeanDojo: Theorem Proving with Retrieval-Augmented Language Models](https://arxiv.org/abs/xxxx.xxxxx)
Under review, NeurIPS (Datasets and Benchmarks Track), 2023
[Kaiyu Yang](https://yangky11.github.io/), [Aidan Swope](https://aidanswope.com/about), [Alex Gu](https://minimario.github.io/), [Rahul Chalamala](https://www.linkedin.com/in/rchalamala),
[Peiyang Song](https://www.linkedin.com/in/peiyang-song-3279b3251/), [Shixing Yu](https://billysx.github.io/), [Saad Godil](https://www.linkedin.com/in/saad-godil-9728353/), [Ryan Prenger](https://www.linkedin.com/in/ryan-prenger-18797ba1/), [Anima Anandkumar](http://tensorlab.cms.caltech.edu/users/anima/)
```bibtex
@article{yang2023leandojo,
title={{LeanDojo}: Theorem Proving with Retrieval-Augmented Language Models},
author={Yang, Kaiyu and Swope, Aidan and Gu, Alex and Chalamala, Rahul and Song, Peiyang and Yu, Shixing and Godil, Saad and Prenger, Ryan and Anandkumar, Anima},
journal={arXiv preprint arXiv:2306.15626},
year={2023}
}
```
Please visit [LeanDojo Website](https://leandojo.org/) for details. |
jzli/majicMIX-realistic-7 | jzli | "2024-05-16T14:13:18Z" | 1,671 | 8 | diffusers | [
"diffusers",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
] | text-to-image | "2023-11-23T09:06:39Z" | You can run this model for free at: https://sinkin.ai/m/yBG2r9O
We offer API at low rates as well |
SanjiWatsuki/Sonya-7B | SanjiWatsuki | "2023-12-31T12:13:22Z" | 1,671 | 30 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"merge",
"en",
"license:cc-by-4.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-12-31T07:27:29Z" | ---
license: cc-by-4.0
language:
- en
tags:
- merge
---
<div style="display: flex; justify-content: center; align-items: center">
<img src="https://huggingface.co/SanjiWatsuki/Sonya-7B/resolve/main/assets/Sonya.jpg">
</div
>
<p align="center">
<big><b>Top 1 Performer MT-bench 🤪</b></big>
</p>
## WTF is This?
Sonya-7B is, at the time of writing, the **#1 performing model in MT-Bench first turn, ahead of GPT-4, and overall the #2 model in MT-Bench**, to the best of my knowledge. Sonya-7B should be a good all-purpose model for all tasks including assistant, RP, etc.
Sonya-7B has a similar structure to my previous model, [Silicon-Maid-7B](https://huggingface.co/SanjiWatsuki/Silicon-Maid-7B), and uses a very similar merge. It's a merge of [xDAN-AI/xDAN-L1-Chat-RL-v1](https://huggingface.co/xDAN-AI/xDAN-L1-Chat-RL-v1), [Jan-Ai's Stealth v1.2](https://huggingface.co/jan-hq/stealth-v1.2), [chargoddard/piano-medley-7b](https://huggingface.co/chargoddard/piano-medley-7b), [NeverSleep/Noromaid-7B-v0.2](https://huggingface.co/NeverSleep/Noromaid-7b-v0.2), and [athirdpath/NSFW_DPO_vmgb-7b](athirdpath/NSFW_DPO_vmgb-7b). Sauce is below. Somehow, by combining these pieces, it substantially outscores any of its parents on MT-Bench.
I picked these models because:
* MT-Bench normally correlates well with real world model quality and xDAN performs well on it.
* Almost all models in the mix were Alpaca prompt formatted which gives prompt consistency.
* Stealth v1.2 has been a magic sprinkle that seems to increase my MT-Bench scores.
* I added RP models because it boosted the Writing and Roleplay benchmarks 👀
Based on the parent models, I expect this model to be used with an 8192 context window. Please use NTK scaling alpha of 2.6 to experimentally try out 16384 context.
**Let me be candid:** Despite the test scores, this model is **NOT is a GPT killer**. I think it's a very sharp model **for a 7B**, it probably punches way above its weight **for a 7B**, but it's still a 7B model. Even for a 7B model, I think **it's quirky and has some weird outputs**, probably due to how Frankenstein this merge is. Keep your expectations in check 😉
**MT-Bench Average Turn**
| model | score | size
|--------------------|-----------|--------
| gpt-4 | 8.99 | -
| **Sonya-7B** | **8.52** | **7b**
| xDAN-L1-Chat-RL-v1 | 8.34 | 7b
| Starling-7B | 8.09 | 7b
| Claude-2 | 8.06 | -
| *Silicon-Maid* | *7.96* | *7b*
| *Loyal-Macaroni-Maid*| *7.95* | *7b*
| gpt-3.5-turbo | 7.94 | 20b?
| Claude-1 | 7.90 | -
| OpenChat-3.5 | 7.81 | -
| vicuna-33b-v1.3 | 7.12 | 33b
| wizardlm-30b | 7.01 | 30b
| Llama-2-70b-chat | 6.86 | 70b
<img src="https://huggingface.co/SanjiWatsuki/Sonya-7B/resolve/main/assets/mt-bench-gpt.png">
<img src="https://huggingface.co/SanjiWatsuki/Sonya-7B/resolve/main/assets/mt-bench-comparison.png">
### The Sauce
```
models:
- model: xDAN-AI/xDAN-L1-Chat-RL-v1
parameters:
weight: 1
density: 1
- model: chargoddard/piano-medley-7b
parameters:
weight: 0.3
- model: jan-hq/stealth-v1.2
parameters:
weight: 0.2
- model: NeverSleep/Noromaid-7b-v0.2
parameters:
weight: 0.2
- model: athirdpath/NSFW_DPO_vmgb-7b
parameters:
weight: 0.2
merge_method: ties
base_model: mistralai/Mistral-7B-v0.1
parameters:
density: 0.4
int8_mask: true
normalize: true
dtype: bfloat16
```
**There was no additional training, finetuning, or DPO.** This is a straight merger.
### Prompt Template (Alpaca)
```
Below is an instruction that describes a task. Write a response that appropriately completes the request.
### Instruction:
{prompt}
### Response:
```
I found that this model **performed worse** with the xDAN prompt format so, despite the heavy weight of xDAN in this merger, I recommeend *against* its use.
### Other Benchmark Stuff
**########## First turn ##########**
| model | turn | score | size
|--------------------|------|----------|--------
| **Sonya-7B** | 1 | **9.06875** | **7b**
| gpt-4 | 1 | 8.95625 | -
| xDAN-L1-Chat-RL-v1 | 1 | *8.87500* | *7b*
| xDAN-L2-Chat-RL-v2 | 1 | 8.78750 | 30b
| claude-v1 | 1 | 8.15000 | -
| gpt-3.5-turbo | 1 | 8.07500 | 20b
| vicuna-33b-v1.3 | 1 | 7.45625 | 33b
| wizardlm-30b | 1 | 7.13125 | 30b
| oasst-sft-7-llama-30b | 1 | 7.10625 | 30b
| Llama-2-70b-chat | 1 | 6.98750 | 70b
########## Second turn ##########
| model | turn | score | size
|--------------------|------|-----------|--------
| gpt-4 | 2 | 9.025000 | -
| xDAN-L2-Chat-RL-v2 | 2 | 8.087500 | 30b
| **Sonya-7B** | 2 | **7.962500** | **7b**
| xDAN-L1-Chat-RL-v1 | 2 | 7.825000 | 7b
| gpt-3.5-turbo | 2 | 7.812500 | 20b
| claude-v1 | 2 | 7.650000 | -
| wizardlm-30b | 2 | 6.887500 | 30b
| vicuna-33b-v1.3 | 2 | 6.787500 | 33b
| Llama-2-70b-chat | 2 | 6.725000 | 70b
If you'd like to replicate the MT-Bench run, please ensure that the Alpaca prompt template is applied to the model. I did this by putting "alpaca" in the model path to trigger the `AlpacaAdapter`.
|
SummerSigh/GPTNeo350M-Instruct-SFT | SummerSigh | "2024-02-11T23:17:58Z" | 1,670 | 0 | transformers | [
"transformers",
"pytorch",
"safetensors",
"gpt_neo",
"text-generation",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-generation | "2023-03-02T22:42:22Z" | ---
license: apache-2.0
---
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_SummerSigh__GPTNeo350M-Instruct-SFT)
| Metric | Value |
|-----------------------|---------------------------|
| Avg. | 27.03 |
| ARC (25-shot) | 25.94 |
| HellaSwag (10-shot) | 38.55 |
| MMLU (5-shot) | 25.76 |
| TruthfulQA (0-shot) | 45.25 |
| Winogrande (5-shot) | 50.2 |
| GSM8K (5-shot) | 0.3 |
| DROP (3-shot) | 3.24 |
|
google/pix2struct-docvqa-large | google | "2023-05-19T10:07:12Z" | 1,670 | 30 | transformers | [
"transformers",
"pytorch",
"pix2struct",
"text2text-generation",
"visual-question-answering",
"en",
"fr",
"ro",
"de",
"multilingual",
"arxiv:2210.03347",
"license:apache-2.0",
"autotrain_compatible",
"region:us"
] | visual-question-answering | "2023-03-21T09:14:02Z" | ---
language:
- en
- fr
- ro
- de
- multilingual
pipeline_tag: visual-question-answering
inference: false
license: apache-2.0
---
# Model card for Pix2Struct - Finetuned on Doc-VQA (Visual Question Answering over scanned documents) - large version
# Table of Contents
0. [TL;DR](#TL;DR)
1. [Using the model](#using-the-model)
2. [Contribution](#contribution)
3. [Citation](#citation)
# TL;DR
Pix2Struct is an image encoder - text decoder model that is trained on image-text pairs for various tasks, including image captionning and visual question answering. The full list of available models can be found on the Table 1 of the paper:
The abstract of the model states that:
> Visually-situated language is ubiquitous—sources range from textbooks with diagrams to web pages with images and tables, to mobile apps with buttons and
forms. Perhaps due to this diversity, previous work has typically relied on domainspecific recipes with limited sharing of the underlying data, model architectures,
and objectives. We present Pix2Struct, a pretrained image-to-text model for
purely visual language understanding, which can be finetuned on tasks containing visually-situated language. Pix2Struct is pretrained by learning to parse
masked screenshots of web pages into simplified HTML. The web, with its richness of visual elements cleanly reflected in the HTML structure, provides a large
source of pretraining data well suited to the diversity of downstream tasks. Intuitively, this objective subsumes common pretraining signals such as OCR, language modeling, image captioning. In addition to the novel pretraining strategy,
we introduce a variable-resolution input representation and a more flexible integration of language and vision inputs, where language prompts such as questions
are rendered directly on top of the input image. For the first time, we show that a
single pretrained model can achieve state-of-the-art results in six out of nine tasks
across four domains: documents, illustrations, user interfaces, and natural images.
# Using the model
## Converting from T5x to huggingface
You can use the [`convert_pix2struct_checkpoint_to_pytorch.py`](https://github.com/huggingface/transformers/blob/main/src/transformers/models/pix2struct/convert_pix2struct_checkpoint_to_pytorch.py) script as follows:
```bash
python convert_pix2struct_checkpoint_to_pytorch.py --t5x_checkpoint_path PATH_TO_T5X_CHECKPOINTS --pytorch_dump_path PATH_TO_SAVE
```
if you are converting a large model, run:
```bash
python convert_pix2struct_checkpoint_to_pytorch.py --t5x_checkpoint_path PATH_TO_T5X_CHECKPOINTS --pytorch_dump_path PATH_TO_SAVE --use-large
```
Once saved, you can push your converted model with the following snippet:
```python
from transformers import Pix2StructForConditionalGeneration, Pix2StructProcessor
model = Pix2StructForConditionalGeneration.from_pretrained(PATH_TO_SAVE)
processor = Pix2StructProcessor.from_pretrained(PATH_TO_SAVE)
model.push_to_hub("USERNAME/MODEL_NAME")
processor.push_to_hub("USERNAME/MODEL_NAME")
```
## Running the model
The instructions for running this model are totally similar to the instructions stated on [`pix2struct-aid-base`](https://huggingface.co/ybelkada/pix2struct-ai2d-base) model.
# Contribution
This model was originally contributed by Kenton Lee, Mandar Joshi et al. and added to the Hugging Face ecosystem by [Younes Belkada](https://huggingface.co/ybelkada).
# Citation
If you want to cite this work, please consider citing the original paper:
```
@misc{https://doi.org/10.48550/arxiv.2210.03347,
doi = {10.48550/ARXIV.2210.03347},
url = {https://arxiv.org/abs/2210.03347},
author = {Lee, Kenton and Joshi, Mandar and Turc, Iulia and Hu, Hexiang and Liu, Fangyu and Eisenschlos, Julian and Khandelwal, Urvashi and Shaw, Peter and Chang, Ming-Wei and Toutanova, Kristina},
keywords = {Computation and Language (cs.CL), Computer Vision and Pattern Recognition (cs.CV), FOS: Computer and information sciences, FOS: Computer and information sciences},
title = {Pix2Struct: Screenshot Parsing as Pretraining for Visual Language Understanding},
publisher = {arXiv},
year = {2022},
copyright = {Creative Commons Attribution 4.0 International}
}
``` |
aisquared/chopt-2_7b | aisquared | "2024-03-28T18:15:39Z" | 1,670 | 0 | transformers | [
"transformers",
"pytorch",
"opt",
"text-generation",
"en",
"dataset:aisquared/databricks-dolly-15k",
"license:other",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-04-24T12:55:04Z" | ---
license: other
commercial: false
datasets:
- aisquared/databricks-dolly-15k
language:
- en
library_name: transformers
---
# Model Card for `chopt-2_7b`
<!-- Provide a quick summary of what the model is/does. -->
AI Squared's `chopt-2_7b` is a large language model which is derived from Meta AI's Open Pre-trained Transformer language modelsand fine-tuned on a corpus of 15k records ([Databricks' "Dolly 15k" Dataset](https://huggingface.co/datasets/aisquared/databricks-dolly-15k)) to help it exhibit chat-based capabilities. Despite the permissive license of the Dolly 15k dataset, due to this model being a derivative of OPT it is restricted to use for **non-commercial research purposes**. The ChOPT family of models from AI Squared are licensed under the OPT-175B license, Copyright (c) Meta Platforms, Inc. All Rights Reserved.
While `chopt-2_7b` is **not a state-of-the-art model**, we believe that the level of interactivity that can be achieved on such a small model that is trained so cheaply is important to showcase, as it continues to demonstrate that creating powerful AI capabilities may be much more accessible than previously thought.
### Model Description
<!-- Provide a longer summary of what this model is. -->
- **Developed by:** AI Squared, Inc.
- **Shared by:** AI Squared, Inc.
- **Model type:** Large Language Model
- **Language(s) (NLP):** EN
- **License:** other
- **Finetuned from model:** OPT
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
**`chopt-2_7b` is not a state-of-the-art language model.** `chopt-2_7b` is an experimental technology and is not designed for use in any
environment other than for research purposes. Furthermore, the model can sometimes exhibit undesired behaviors. Some of these behaviors include,
but are not limited to: factual inaccuracies, biases, offensive responses, toxicity, and hallucinations.
Just as with any other LLM, we advise users of this technology to exercise good judgment when applying this technology.
## Usage
To use the model with the `transformers` library on a machine with GPUs, first make sure you have the `transformers` and `accelerate` libraries installed.
From your terminal, run:
```python
pip install "accelerate>=0.16.0,<1" "transformers[torch]>=4.28.1,<5" "torch>=1.13.1,<2"
```
The instruction following pipeline can be loaded using the `pipeline` function as shown below. This loads a custom `InstructionTextGenerationPipeline`
found in the model repo [here](https://huggingface.co/aisquared/chopt-2_7b/blob/main/instruct_pipeline.py), which is why `trust_remote_code=True` is required.
Including `torch_dtype=torch.bfloat16` is generally recommended if this type is supported in order to reduce memory usage. It does not appear to impact output quality.
It is also fine to remove it if there is sufficient memory.
```python
from transformers import pipeline
import torch
generate_text = pipeline(model="aisquared/chopt-2_7b", torch_dtype=torch.bfloat16, trust_remote_code=True, device_map="auto")
```
You can then use the pipeline to answer instructions:
```python
res = generate_text("Who was George Washington?")
print(res)
```
Alternatively, if you prefer to not use `trust_remote_code=True` you can download [instruct_pipeline.py](https://huggingface.co/aisquared/chopt-2_7b/blob/main/instruct_pipeline.py),
store it alongside your notebook, and construct the pipeline yourself from the loaded model and tokenizer:
```python
from instruct_pipeline import InstructionTextGenerationPipeline
from transformers import AutoModelForCausalLM, AutoTokenizer
import torch
tokenizer = AutoTokenizer.from_pretrained("aisquared/chopt-2_7b", padding_side="left")
model = AutoModelForCausalLM.from_pretrained("aisquared/chopt-2_7b", device_map="auto", torch_dtype=torch.bfloat16)
generate_text = InstructionTextGenerationPipeline(model=model, tokenizer=tokenizer)
```
### Model Performance Metrics
We present the results from various model benchmarks on the EleutherAI LLM Evaluation Harness for all models in the ChOPT family.
Model results are sorted by mean score, ascending, to provide an ordering. These metrics serve to further show that none of the DLite models are
state of the art, but rather further show that chat-like behaviors in LLMs can be trained almost independent of model size.
| Model | openbookqa | arc_easy | winogrande | hellaswag | arc_challenge | piqa | boolq |
|:--------------------|-------------:|-----------:|-------------:|------------:|----------------:|---------:|---------:|
| chopt-125m | 0.178 | 0.443182 | 0.501973 | 0.294165 | 0.197099 | 0.630577 | 0.476758 |
| chopt-research-125m | 0.17 | 0.436027 | 0.503552 | 0.294762 | 0.205631 | 0.62568 | 0.48685 |
| opt-125m | 0.166 | 0.435606 | 0.501973 | 0.291775 | 0.190273 | 0.6284 | 0.554434 |
| chopt-350m | 0.178 | 0.450758 | 0.508287 | 0.325334 | 0.21843 | 0.650707 | 0.559633 |
| opt_350m | 0.176 | 0.441077 | 0.52644 | 0.320056 | 0.207338 | 0.645267 | 0.57737 |
| chopt-research-350m | 0.172 | 0.462542 | 0.514601 | 0.327524 | 0.235495 | 0.643634 | 0.589908 |
| opt-1.3b | 0.234 | 0.569865 | 0.596685 | 0.414957 | 0.232935 | 0.718172 | 0.577676 |
| chopt-research-1_3b | 0.232 | 0.564815 | 0.59116 | 0.424716 | 0.276451 | 0.713275 | 0.634557 |
| chopt-1_3b | 0.236 | 0.569444 | 0.584057 | 0.42621 | 0.268771 | 0.723069 | 0.658104 |
| opt-2.7b | 0.25 | 0.608165 | 0.608524 | 0.458176 | 0.267918 | 0.738303 | 0.603058 |
| chopt-2_7b | 0.276 | 0.616582 | 0.601421 | 0.472615 | 0.288396 | 0.75136 | 0.552294 |
| chopt-research-2_7b | 0.262 | 0.610269 | 0.625099 | 0.458176 | 0.295222 | 0.742111 | 0.636697 |
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_aisquared__chopt-2_7b)
| Metric | Value |
|-----------------------|---------------------------|
| Avg. | 32.17 |
| ARC (25-shot) | 36.01 |
| HellaSwag (10-shot) | 63.38 |
| MMLU (5-shot) | 25.44 |
| TruthfulQA (0-shot) | 37.71 |
| Winogrande (5-shot) | 57.77 |
| GSM8K (5-shot) | 0.0 |
| DROP (3-shot) | 4.86 |
|
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.