modelId
stringlengths 5
122
| author
stringlengths 2
42
| last_modified
timestamp[us, tz=UTC] | downloads
int64 0
738M
| likes
int64 0
11k
| library_name
stringclasses 245
values | tags
sequencelengths 1
4.05k
| pipeline_tag
stringclasses 48
values | createdAt
timestamp[us, tz=UTC] | card
stringlengths 1
901k
|
|---|---|---|---|---|---|---|---|---|---|
mlabonne/Darewin-7B-v2 | mlabonne | 2024-03-04T15:17:28Z | 734 | 0 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"merge",
"mergekit",
"lazymergekit",
"conversational",
"base_model:OpenPipe/mistral-ft-optimized-1227",
"base_model:Intel/neural-chat-7b-v3-3",
"base_model:openchat/openchat-3.5-0106",
"base_model:openaccess-ai-collective/DPOpenHermes-7B-v2",
"base_model:mlabonne/NeuralHermes-2.5-Mistral-7B",
"base_model:cognitivecomputations/dolphin-2.6-mistral-7b-dpo-laser",
"base_model:Open-Orca/Mistral-7B-OpenOrca",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | 2024-01-24T13:16:11Z | ---
license: apache-2.0
tags:
- merge
- mergekit
- lazymergekit
base_model:
- OpenPipe/mistral-ft-optimized-1227
- Intel/neural-chat-7b-v3-3
- openchat/openchat-3.5-0106
- openaccess-ai-collective/DPOpenHermes-7B-v2
- mlabonne/NeuralHermes-2.5-Mistral-7B
- cognitivecomputations/dolphin-2.6-mistral-7b-dpo-laser
- Open-Orca/Mistral-7B-OpenOrca
model-index:
- name: Darewin-7B-v2
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: 62.63
name: normalized accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mlabonne/Darewin-7B-v2
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: 78.28
name: normalized accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mlabonne/Darewin-7B-v2
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: 53.01
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mlabonne/Darewin-7B-v2
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: 50.99
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mlabonne/Darewin-7B-v2
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: 73.95
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mlabonne/Darewin-7B-v2
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: 19.18
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mlabonne/Darewin-7B-v2
name: Open LLM Leaderboard
---
# Darewin-7B-v2
Darewin-7B-v2 is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
* [OpenPipe/mistral-ft-optimized-1227](https://huggingface.co/OpenPipe/mistral-ft-optimized-1227)
* [Intel/neural-chat-7b-v3-3](https://huggingface.co/Intel/neural-chat-7b-v3-3)
* [openchat/openchat-3.5-0106](https://huggingface.co/openchat/openchat-3.5-0106)
* [openaccess-ai-collective/DPOpenHermes-7B-v2](https://huggingface.co/openaccess-ai-collective/DPOpenHermes-7B-v2)
* [mlabonne/NeuralHermes-2.5-Mistral-7B](https://huggingface.co/mlabonne/NeuralHermes-2.5-Mistral-7B)
* [cognitivecomputations/dolphin-2.6-mistral-7b-dpo-laser](https://huggingface.co/cognitivecomputations/dolphin-2.6-mistral-7b-dpo-laser)
* [Open-Orca/Mistral-7B-OpenOrca](https://huggingface.co/Open-Orca/Mistral-7B-OpenOrca)
## 🧩 Configuration
```yaml
models:
- model: mistralai/Mistral-7B-Instruct-v0.2
# No parameters necessary for base model
- model: OpenPipe/mistral-ft-optimized-1227
parameters:
density: 0.6
weight: 0.25
- model: Intel/neural-chat-7b-v3-3
parameters:
density: 0.55
weight: 0.2
- model: openchat/openchat-3.5-0106
parameters:
density: 0.5
weight: 0.2
- model: openaccess-ai-collective/DPOpenHermes-7B-v2
parameters:
density: 0.45
weight: 0.1
- model: mlabonne/NeuralHermes-2.5-Mistral-7B
parameters:
density: 0.4
weight: 0.1
- model: cognitivecomputations/dolphin-2.6-mistral-7b-dpo-laser
parameters:
density: 0.4
weight: 0.1
- model: Open-Orca/Mistral-7B-OpenOrca
parameters:
density: 0.3
weight: 0.05
merge_method: dare_ties
base_model: mistralai/Mistral-7B-Instruct-v0.2
parameters:
int8_mask: true
dtype: bfloat16
```
## 💻 Usage
```python
!pip install -qU transformers accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "mlabonne/Darewin-7B-v2"
messages = [{"role": "user", "content": "What is a large language model?"}]
tokenizer = AutoTokenizer.from_pretrained(model)
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
pipeline = transformers.pipeline(
"text-generation",
model=model,
torch_dtype=torch.float16,
device_map="auto",
)
outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])
```
# [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_mlabonne__Darewin-7B-v2)
| Metric |Value|
|---------------------------------|----:|
|Avg. |56.34|
|AI2 Reasoning Challenge (25-Shot)|62.63|
|HellaSwag (10-Shot) |78.28|
|MMLU (5-Shot) |53.01|
|TruthfulQA (0-shot) |50.99|
|Winogrande (5-shot) |73.95|
|GSM8k (5-shot) |19.18|
|
nbeerbower/bruphin-epsilon | nbeerbower | 2024-03-04T13:06:26Z | 734 | 0 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"mergekit",
"merge",
"conversational",
"base_model:BarryFutureman/WildMarcoroni-Variant1-7B",
"base_model:nbeerbower/bruphin-delta",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | 2024-01-24T22:24:40Z | ---
license: apache-2.0
tags:
- mergekit
- merge
base_model:
- BarryFutureman/WildMarcoroni-Variant1-7B
- nbeerbower/bruphin-delta
model-index:
- name: bruphin-epsilon
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: 72.1
name: normalized accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=nbeerbower/bruphin-epsilon
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: 88.09
name: normalized accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=nbeerbower/bruphin-epsilon
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: 65.04
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=nbeerbower/bruphin-epsilon
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: 66.95
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=nbeerbower/bruphin-epsilon
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: 83.82
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=nbeerbower/bruphin-epsilon
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: 70.51
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=nbeerbower/bruphin-epsilon
name: Open LLM Leaderboard
---
# bruphin-epsilon
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
## Merge Details
### Merge Method
This model was merged using the SLERP merge method.
### Models Merged
The following models were included in the merge:
* [BarryFutureman/WildMarcoroni-Variant1-7B](https://huggingface.co/BarryFutureman/WildMarcoroni-Variant1-7B)
* [nbeerbower/bruphin-delta](https://huggingface.co/nbeerbower/bruphin-delta)
### Configuration
The following YAML configuration was used to produce this model:
```yaml
models:
- model: nbeerbower/bruphin-delta
layer_range: [0, 32]
- model: BarryFutureman/WildMarcoroni-Variant1-7B
layer_range: [0, 32]
merge_method: slerp
base_model: BarryFutureman/WildMarcoroni-Variant1-7B
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
dtype: bfloat16
```
# [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_nbeerbower__bruphin-epsilon)
| Metric |Value|
|---------------------------------|----:|
|Avg. |74.42|
|AI2 Reasoning Challenge (25-Shot)|72.10|
|HellaSwag (10-Shot) |88.09|
|MMLU (5-Shot) |65.04|
|TruthfulQA (0-shot) |66.95|
|Winogrande (5-shot) |83.82|
|GSM8k (5-shot) |70.51|
|
CultriX/OmniTrixAI | CultriX | 2024-01-27T11:39:47Z | 734 | 0 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"merge",
"mergekit",
"lazymergekit",
"mlabonne/NeuralBeagle14-7B",
"FelixChao/WestSeverus-7B-DPO-v2",
"CultriX/MergeTrix-7B-v2",
"base_model:mlabonne/NeuralBeagle14-7B",
"base_model:FelixChao/WestSeverus-7B-DPO-v2",
"base_model:CultriX/MergeTrix-7B-v2",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | 2024-01-25T13:56:18Z | ---
tags:
- merge
- mergekit
- lazymergekit
- mlabonne/NeuralBeagle14-7B
- FelixChao/WestSeverus-7B-DPO-v2
- CultriX/MergeTrix-7B-v2
base_model:
- mlabonne/NeuralBeagle14-7B
- FelixChao/WestSeverus-7B-DPO-v2
- CultriX/MergeTrix-7B-v2
license: apache-2.0
---
# EDIT:
Always check my space for the latest benchmark results for my models!
* https://huggingface.co/spaces/CultriX/Yet_Another_LLM_Leaderboard
# OmniTrixAI
OmniTrixAI is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
* [mlabonne/NeuralBeagle14-7B](https://huggingface.co/mlabonne/NeuralBeagle14-7B)
* [FelixChao/WestSeverus-7B-DPO-v2](https://huggingface.co/FelixChao/WestSeverus-7B-DPO-v2)
* [CultriX/MergeTrix-7B-v2](https://huggingface.co/CultriX/MergeTrix-7B-v2)
## 🧩 Configuration
```yaml
models:
- model: senseable/WestLake-7B-v2
# No parameters necessary for base model
- model: mlabonne/NeuralBeagle14-7B
parameters:
density: 0.65
weight: 0.40
- model: FelixChao/WestSeverus-7B-DPO-v2
parameters:
density: 0.45
weight: 0.26
- model: CultriX/MergeTrix-7B-v2
parameters:
density: 0.55
weight: 0.34
merge_method: dare_ties
base_model: senseable/WestLake-7B-v2
parameters:
int8_mask: true
dtype: float16
```
## 💻 Usage
```python
!pip install -qU transformers accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "CultriX/OmniTrixAI"
messages = [{"role": "user", "content": "What is a large language model?"}]
tokenizer = AutoTokenizer.from_pretrained(model)
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
pipeline = transformers.pipeline(
"text-generation",
model=model,
torch_dtype=torch.float16,
device_map="auto",
)
outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])
``` |
kaitchup/TheMayonnaise | kaitchup | 2024-03-17T10:09:57Z | 734 | 0 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"merge",
"en",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | 2024-01-27T23:02:00Z | ---
language:
- en
license: apache-2.0
library_name: transformers
tags:
- merge
model-index:
- name: TheMayonnaise
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: 73.46
name: normalized accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=kaitchup/TheMayonnaise
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: 88.46
name: normalized accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=kaitchup/TheMayonnaise
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: 64.88
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=kaitchup/TheMayonnaise
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: 69.19
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=kaitchup/TheMayonnaise
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: 84.29
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=kaitchup/TheMayonnaise
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: 69.37
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=kaitchup/TheMayonnaise
name: Open LLM Leaderboard
---
# Model Card for Model ID
This is a mixture of experts created with [mergekit](https://github.com/cg123/mergekit) and based on [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1).
## Model Details
The model was created using a recipe detailed in this article:
[The Mayonnaise: Rank First on the Open LLM Leaderboard with TIES-Merging
](https://kaitchup.substack.com/p/the-mayonnaise-rank-first-on-the)
### Model Description
<!-- Provide a longer summary of what this model is. -->
- **Developed by:** [The Kaitchup](https://kaitchup.substack.com/)
- **Model type:** Causal
- **Language(s) (NLP):** English
- **License:** [Apache 2.0](https://www.apache.org/licenses/LICENSE-2.0)
### Model Sources
Created with mergekit with this configuration:
```
models:
- model: mncai/mistral-7b-dpo-v5
# no parameters necessary for base model
- model: kaitchup/Mayonnaise-4in1-02
parameters:
density: 0.5
weight: 0.3
- model: BarryFutureman/NeuralTurdusVariant1-7B
parameters:
density: 0.5
weight: 0.5
merge_method: ties
base_model: mncai/mistral-7b-dpo-v5
parameters:
normalize: true
dtype: float16
```
# [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_kaitchup__TheMayonnaise)
| Metric |Value|
|---------------------------------|----:|
|Avg. |74.94|
|AI2 Reasoning Challenge (25-Shot)|73.46|
|HellaSwag (10-Shot) |88.46|
|MMLU (5-Shot) |64.88|
|TruthfulQA (0-shot) |69.19|
|Winogrande (5-shot) |84.29|
|GSM8k (5-shot) |69.37|
|
yunconglong/MoE_13B_DPO | yunconglong | 2024-01-28T06:49:29Z | 734 | 5 | transformers | [
"transformers",
"safetensors",
"mixtral",
"text-generation",
"moe",
"DPO",
"RL-TUNED",
"license:other",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | 2024-01-28T01:19:24Z | ---
license: other
tags:
- moe
- DPO
- RL-TUNED
---
* [DPO Trainer](https://huggingface.co/docs/trl/main/en/dpo_trainer) with dataset Intel/orca_dpo_pairs to improve [yunconglong/Truthful_DPO_TomGrc_FusionNet_7Bx2_MoE_13B]
```
DPO Trainer
TRL supports the DPO Trainer for training language models from preference data, as described in the paper Direct Preference Optimization: Your Language Model is Secretly a Reward Model by Rafailov et al., 2023.
```
|
ibivibiv/multimaster-7b | ibivibiv | 2024-02-02T13:58:19Z | 734 | 0 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"moe",
"moerge",
"conversational",
"en",
"arxiv:1803.05457",
"arxiv:1905.07830",
"arxiv:2009.03300",
"arxiv:2109.07958",
"arxiv:1907.10641",
"arxiv:2110.14168",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | 2024-01-29T04:47:49Z | ---
license: apache-2.0
language:
- en
library_name: transformers
tags:
- moe
- moerge
---
# Multi Master 7B
A quick multi-disciplinary fine tune of openchat/openchat-3.5-0106 using an alpaca-style dataset across different disciplines. I used LORA adapters that I then merged back into the main model for ease of use.
# Prompting
## Prompt Template for alpaca style
```
### Instruction:
<prompt> (without the <>)
### Response:
```
## Sample Code
```python
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
torch.set_default_device("cuda")
model = AutoModelForCausalLM.from_pretrained("ibivibiv/multimaster-7b", torch_dtype="auto", device_config='auto')
tokenizer = AutoTokenizer.from_pretrained("ibivibiv/multimaster-7b")
inputs = tokenizer("### Instruction: Who would when in an arm wrestling match between Abraham Lincoln and Chuck Norris?\nA. Abraham Lincoln \nB. Chuck Norris\n### Response:\n", return_tensors="pt", return_attention_mask=False)
outputs = model.generate(**inputs, max_length=200)
text = tokenizer.batch_decode(outputs)[0]
print(text)
```
# Model Details
* **Trained by**: [ibivibiv](https://huggingface.co/ibivibiv)
* **Library**: [HuggingFace Transformers](https://github.com/huggingface/transformers)
* **Model type:** **multimaster-7b** is a lora tuned version of openchat/openchat-3.5-0106 with the adapter merged back into the main model
* **Language(s)**: English
* **Purpose**: This model is a focus on multi-disciplinary model tuning
# Benchmark Scores
coming soon
## Citations
```
@misc{open-llm-leaderboard,
author = {Edward Beeching and Clémentine Fourrier and Nathan Habib and Sheon Han and Nathan Lambert and Nazneen Rajani and Omar Sanseviero and Lewis Tunstall and Thomas Wolf},
title = {Open LLM Leaderboard},
year = {2023},
publisher = {Hugging Face},
howpublished = "\url{https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard}"
}
```
```
@software{eval-harness,
author = {Gao, Leo and
Tow, Jonathan and
Biderman, Stella and
Black, Sid and
DiPofi, Anthony and
Foster, Charles and
Golding, Laurence and
Hsu, Jeffrey and
McDonell, Kyle and
Muennighoff, Niklas and
Phang, Jason and
Reynolds, Laria and
Tang, Eric and
Thite, Anish and
Wang, Ben and
Wang, Kevin and
Zou, Andy},
title = {A framework for few-shot language model evaluation},
month = sep,
year = 2021,
publisher = {Zenodo},
version = {v0.0.1},
doi = {10.5281/zenodo.5371628},
url = {https://doi.org/10.5281/zenodo.5371628}
}
```
```
@misc{clark2018think,
title={Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge},
author={Peter Clark and Isaac Cowhey and Oren Etzioni and Tushar Khot and Ashish Sabharwal and Carissa Schoenick and Oyvind Tafjord},
year={2018},
eprint={1803.05457},
archivePrefix={arXiv},
primaryClass={cs.AI}
}
```
```
@misc{zellers2019hellaswag,
title={HellaSwag: Can a Machine Really Finish Your Sentence?},
author={Rowan Zellers and Ari Holtzman and Yonatan Bisk and Ali Farhadi and Yejin Choi},
year={2019},
eprint={1905.07830},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
```
```
@misc{hendrycks2021measuring,
title={Measuring Massive Multitask Language Understanding},
author={Dan Hendrycks and Collin Burns and Steven Basart and Andy Zou and Mantas Mazeika and Dawn Song and Jacob Steinhardt},
year={2021},
eprint={2009.03300},
archivePrefix={arXiv},
primaryClass={cs.CY}
}
```
```
@misc{lin2022truthfulqa,
title={TruthfulQA: Measuring How Models Mimic Human Falsehoods},
author={Stephanie Lin and Jacob Hilton and Owain Evans},
year={2022},
eprint={2109.07958},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
```
```
@misc{DBLP:journals/corr/abs-1907-10641,
title={{WINOGRANDE:} An Adversarial Winograd Schema Challenge at Scale},
author={Keisuke Sakaguchi and Ronan Le Bras and Chandra Bhagavatula and Yejin Choi},
year={2019},
eprint={1907.10641},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
```
```
@misc{DBLP:journals/corr/abs-2110-14168,
title={Training Verifiers to Solve Math Word Problems},
author={Karl Cobbe and
Vineet Kosaraju and
Mohammad Bavarian and
Mark Chen and
Heewoo Jun and
Lukasz Kaiser and
Matthias Plappert and
Jerry Tworek and
Jacob Hilton and
Reiichiro Nakano and
Christopher Hesse and
John Schulman},
year={2021},
eprint={2110.14168},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
``` |
Gille/MoE-StrangeMerges-2x7B | Gille | 2024-03-04T21:51:01Z | 734 | 0 | transformers | [
"transformers",
"safetensors",
"mixtral",
"text-generation",
"moe",
"frankenmoe",
"merge",
"mergekit",
"lazymergekit",
"Gille/StrangeMerges_9-7B-dare_ties",
"Gille/StrangeMerges_8-7B-slerp",
"base_model:Gille/StrangeMerges_9-7B-dare_ties",
"base_model:Gille/StrangeMerges_8-7B-slerp",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | 2024-01-29T17:55:48Z | ---
license: apache-2.0
tags:
- moe
- frankenmoe
- merge
- mergekit
- lazymergekit
- Gille/StrangeMerges_9-7B-dare_ties
- Gille/StrangeMerges_8-7B-slerp
base_model:
- Gille/StrangeMerges_9-7B-dare_ties
- Gille/StrangeMerges_8-7B-slerp
model-index:
- name: MoE-StrangeMerges-2x7B
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: 70.82
name: normalized accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Gille/MoE-StrangeMerges-2x7B
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: 87.83
name: normalized accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Gille/MoE-StrangeMerges-2x7B
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: 65.04
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Gille/MoE-StrangeMerges-2x7B
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: 65.86
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Gille/MoE-StrangeMerges-2x7B
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=Gille/MoE-StrangeMerges-2x7B
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: 67.7
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Gille/MoE-StrangeMerges-2x7B
name: Open LLM Leaderboard
---
# MoE-StrangeMerges-2x7B
MoE-StrangeMerges-2x7B is a Mixure of Experts (MoE) made with the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
* [Gille/StrangeMerges_9-7B-dare_ties](https://huggingface.co/Gille/StrangeMerges_9-7B-dare_ties)
* [Gille/StrangeMerges_8-7B-slerp](https://huggingface.co/Gille/StrangeMerges_8-7B-slerp)
## 🧩 Configuration
```yaml
base_model: Gille/StrangeMerges_9-7B-dare_ties
gate_mode: cheap_embed
dtype: float16
experts:
- source_model: Gille/StrangeMerges_9-7B-dare_ties
positive_prompts: ["science, logic, math"]
- source_model: Gille/StrangeMerges_8-7B-slerp
positive_prompts: ["reasoning, numbers, abstract"]
```
## 💻 Usage
```python
!pip install -qU transformers bitsandbytes accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "Gille/MoE-StrangeMerges-2x7B"
tokenizer = AutoTokenizer.from_pretrained(model)
pipeline = transformers.pipeline(
"text-generation",
model=model,
model_kwargs={"torch_dtype": torch.float16, "load_in_4bit": True},
)
messages = [{"role": "user", "content": "Explain what a Mixture of Experts is in less than 100 words."}]
prompt = pipeline.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])
```
# [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_Gille__MoE-StrangeMerges-2x7B)
| Metric |Value|
|---------------------------------|----:|
|Avg. |73.34|
|AI2 Reasoning Challenge (25-Shot)|70.82|
|HellaSwag (10-Shot) |87.83|
|MMLU (5-Shot) |65.04|
|TruthfulQA (0-shot) |65.86|
|Winogrande (5-shot) |82.79|
|GSM8k (5-shot) |67.70|
|
PotatoOff/Michel-13B | PotatoOff | 2024-02-04T16:16:36Z | 734 | 2 | transformers | [
"transformers",
"pytorch",
"safetensors",
"llama",
"text-generation",
"conversational",
"en",
"license:agpl-3.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | 2024-01-30T03:37:04Z | ---
license: agpl-3.0
language:
- en
---
# Michel - 13B
**A Uncensored fine tune model general tasks focused of [NousHermes-Llama2-13B](https://huggingface.co/NousResearch/Nous-Hermes-Llama2-13b).**
With the help of [my team](https://huggingface.co/ConvexAI).
#### Quants
[Michel Exl2 Quant](https://huggingface.co/bartowski/Michel-13B-exl2)
[Michel GGUF Quant](https://huggingface.co/Kquant03/Michel-13B-GGUF)
### Useful
- **Uses Llama2 prompt template.**
- Next one will be more interesting :}
### I had good results with this parameters:
- temperature: 0.8
- top_p: 0.75
- min_p: 0
- top_k: 0
- repetition_penalty: 1.05
### General Usecase Test
### BenchMarks on OpenLLM Leaderboard
More details: [Michel-13B OpenLLM BenchMarks](https://huggingface.co/datasets/open-llm-leaderboard/details_PotatoOff__Michel-13B)
### Thank you h2m for the compute
### Have Fun :)
|
saishf/Top-Western-Maid-7B | saishf | 2024-03-04T14:33:41Z | 734 | 0 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"mergekit",
"merge",
"arxiv:2311.03099",
"arxiv:2306.01708",
"base_model:NeverSleep/Noromaid-7B-0.4-DPO",
"base_model:Undi95/Toppy-M-7B",
"base_model:mistralai/Mistral-7B-v0.1",
"base_model:senseable/WestLake-7B-v2",
"license:cc-by-nc-4.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | 2024-02-04T12:23:32Z | ---
license: cc-by-nc-4.0
tags:
- mergekit
- merge
base_model:
- NeverSleep/Noromaid-7B-0.4-DPO
- Undi95/Toppy-M-7B
- mistralai/Mistral-7B-v0.1
- senseable/WestLake-7B-v2
model-index:
- name: Top-Western-Maid-7B
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: 69.37
name: normalized accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=saishf/Top-Western-Maid-7B
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: 87.4
name: normalized accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=saishf/Top-Western-Maid-7B
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: 64.63
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=saishf/Top-Western-Maid-7B
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: 58.79
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=saishf/Top-Western-Maid-7B
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: 83.27
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=saishf/Top-Western-Maid-7B
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: 65.96
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=saishf/Top-Western-Maid-7B
name: Open LLM Leaderboard
---
# merge
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
## Merge Details
### Merge Method
This model was merged using the [DARE](https://arxiv.org/abs/2311.03099) [TIES](https://arxiv.org/abs/2306.01708) merge method using [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) as a base.
### Models Merged
The following models were included in the merge:
* [NeverSleep/Noromaid-7B-0.4-DPO](https://huggingface.co/NeverSleep/Noromaid-7B-0.4-DPO)
* [Undi95/Toppy-M-7B](https://huggingface.co/Undi95/Toppy-M-7B)
* [senseable/WestLake-7B-v2](https://huggingface.co/senseable/WestLake-7B-v2)
### Configuration
The following YAML configuration was used to produce this model:
```yaml
models:
- model: mistralai/Mistral-7B-v0.1
# No parameters necessary for base model
- model: senseable/WestLake-7B-v2
parameters:
density: 0.53
weight: 0.55
- model: NeverSleep/Noromaid-7B-0.4-DPO
parameters:
density: 0.53
weight: 0.30
- model: Undi95/Toppy-M-7B
parameters:
density: 0.53
weight: 0.15
merge_method: dare_ties
base_model: mistralai/Mistral-7B-v0.1
parameters:
int8_mask: true
dtype: bfloat16
```
# [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_saishf__Top-Western-Maid-7B)
| Metric |Value|
|---------------------------------|----:|
|Avg. |71.57|
|AI2 Reasoning Challenge (25-Shot)|69.37|
|HellaSwag (10-Shot) |87.40|
|MMLU (5-Shot) |64.63|
|TruthfulQA (0-shot) |58.79|
|Winogrande (5-shot) |83.27|
|GSM8k (5-shot) |65.96|
|
andrijdavid/Macaroni-v2-7b | andrijdavid | 2024-02-07T13:22:10Z | 734 | 0 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"mergekit",
"merge",
"en",
"arxiv:2311.03099",
"arxiv:2306.01708",
"base_model:flemmingmiguel/MBX-7B-v3",
"base_model:mlabonne/OmniBeagle-7B",
"base_model:mistralai/Mistral-7B-v0.1",
"base_model:vanillaOVO/supermario_v4",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | 2024-02-05T17:48:43Z | ---
base_model:
- flemmingmiguel/MBX-7B-v3
- mlabonne/OmniBeagle-7B
- mistralai/Mistral-7B-v0.1
- vanillaOVO/supermario_v4
tags:
- mergekit
- merge
license: apache-2.0
language:
- en
---
# Macaroni V2 7B
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
## Merge Details
### Merge Method
This model was merged using the [DARE](https://arxiv.org/abs/2311.03099) [TIES](https://arxiv.org/abs/2306.01708) merge method using [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) as a base.
### Models Merged
The following models were included in the merge:
* [flemmingmiguel/MBX-7B-v3](https://huggingface.co/flemmingmiguel/MBX-7B-v3)
* [mlabonne/OmniBeagle-7B](https://huggingface.co/mlabonne/OmniBeagle-7B)
* [vanillaOVO/supermario_v4](https://huggingface.co/vanillaOVO/supermario_v4)
### Configuration
The following YAML configuration was used to produce this model:
```yaml
models:
- model: mistralai/Mistral-7B-v0.1
# no parameters necessary for base model
- model: flemmingmiguel/MBX-7B-v3
parameters:
density: 0.7
weight: 0.5
- model: vanillaOVO/supermario_v4
parameters:
density: 0.7
weight: 0.3
- model: mlabonne/OmniBeagle-7B
parameters:
density: 0.5
weight: 0.6
merge_method: dare_ties
base_model: mistralai/Mistral-7B-v0.1
parameters:
int8_mask: true
normalize: true
dtype: float16
``` |
dddsaty/Merge_Sakura_Solar | dddsaty | 2024-02-10T02:59:26Z | 734 | 1 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"conversational",
"en",
"license:cc-by-nc-sa-4.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | 2024-02-07T04:38:32Z | ---
license: cc-by-nc-sa-4.0
language:
- en
pipeline_tag: text-generation
---
**Explanation**
- Merged three models using [mergekit](https://github.com/arcee-ai/mergekit) (dare_ties)
**Models**
- [Sakura-SOLAR-Instruct](https://huggingface.co/kyujinpy/Sakura-SOLAR-Instruct)
- [Sakura-SOLRCA-Math-Instruct-DPO-v2](https://huggingface.co/kyujinpy/Sakura-SOLRCA-Math-Instruct-DPO-v2)
- [Sakura-SOLRCA-Instruct-DPO](https://huggingface.co/kyujinpy/Sakura-SOLRCA-Instruct-DPO)
**Score**
|Average|ARC|HellaSwag|MMLU|TruthfulQA|Winogrande|GSM8K|
|:---:|:---:|:---:|:---:|:---:|:---:|:---:|
|74.03|70.73|88.51|66.03|72.21|82.72|63.99|
**Original Author's HuggingFace profile**
- [kyujinpy](https://huggingface.co/kyujinpy)
**License**
- Following the license written at the author's space |
CultriX/NeuralTrix-7B-v1 | CultriX | 2024-02-08T21:43:05Z | 734 | 1 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"merge",
"mergekit",
"lazymergekit",
"mlabonne/OmniBeagle-7B",
"flemmingmiguel/MBX-7B-v3",
"AiMavenAi/AiMaven-Prometheus",
"base_model:mlabonne/OmniBeagle-7B",
"base_model:flemmingmiguel/MBX-7B-v3",
"base_model:AiMavenAi/AiMaven-Prometheus",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | 2024-02-08T16:09:29Z | ---
tags:
- merge
- mergekit
- lazymergekit
- mlabonne/OmniBeagle-7B
- flemmingmiguel/MBX-7B-v3
- AiMavenAi/AiMaven-Prometheus
base_model:
- mlabonne/OmniBeagle-7B
- flemmingmiguel/MBX-7B-v3
- AiMavenAi/AiMaven-Prometheus
license: apache-2.0
---
# NeuralTrix-7B-v1
NeuralTrix-7B-v1 is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
* [mlabonne/OmniBeagle-7B](https://huggingface.co/mlabonne/OmniBeagle-7B)
* [flemmingmiguel/MBX-7B-v3](https://huggingface.co/flemmingmiguel/MBX-7B-v3)
* [AiMavenAi/AiMaven-Prometheus](https://huggingface.co/AiMavenAi/AiMaven-Prometheus)
## 🧩 Configuration
```yaml
models:
- model: mistralai/Mistral-7B-v0.1
# no parameters necessary for base model
- model: mlabonne/OmniBeagle-7B
parameters:
density: 0.65
weight: 0.4
- model: flemmingmiguel/MBX-7B-v3
parameters:
density: 0.6
weight: 0.35
- model: AiMavenAi/AiMaven-Prometheus
parameters:
density: 0.6
weight: 0.35
merge_method: dare_ties
base_model: mistralai/Mistral-7B-v0.1
parameters:
int8_mask: true
dtype: float16
```
## 💻 Usage
```python
!pip install -qU transformers accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "CultriX/NeuralTrix-7B-v1"
messages = [{"role": "user", "content": "What is a large language model?"}]
tokenizer = AutoTokenizer.from_pretrained(model)
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
pipeline = transformers.pipeline(
"text-generation",
model=model,
torch_dtype=torch.float16,
device_map="auto",
)
outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])
``` |
ArianAskari/SOLID_SFT-WoDPO-WoMixQ | ArianAskari | 2024-02-11T13:15:09Z | 734 | 0 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"conversational",
"en",
"dataset:ArianAskari/SOLID",
"arxiv:1910.09700",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | 2024-02-11T06:44:14Z | ---
library_name: transformers
tags: []
license: apache-2.0
language:
- en
datasets: ArianAskari/SOLID
---
# 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. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **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]
|
yam-peleg/Experiment9-7B | yam-peleg | 2024-02-11T23:32:08Z | 734 | 0 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"arxiv:1910.09700",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | 2024-02-11T22:02:26Z | ---
library_name: transformers
license: apache-2.0
---
# 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. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **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] |
eren23/dpo-binarized-NeutrixOmnibe-7B | eren23 | 2024-03-05T15:46:03Z | 734 | 2 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"merge",
"dpo",
"conversation",
"text-generation-inference",
"Kukedlc/NeuTrixOmniBe-7B-model-remix",
"en",
"dataset:argilla/OpenHermes2.5-dpo-binarized-alpha",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-02-12T07:15:55Z | ---
language:
- en
license: apache-2.0
tags:
- merge
- dpo
- conversation
- text-generation-inference
- Kukedlc/NeuTrixOmniBe-7B-model-remix
datasets:
- argilla/OpenHermes2.5-dpo-binarized-alpha
pipeline_tag: text-generation
model-index:
- name: dpo-binarized-NeutrixOmnibe-7B
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: 72.78
name: normalized accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=eren23/dpo-binarized-NeutrixOmnibe-7B
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: 89.05
name: normalized accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=eren23/dpo-binarized-NeutrixOmnibe-7B
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: 64.6
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=eren23/dpo-binarized-NeutrixOmnibe-7B
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: 76.9
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=eren23/dpo-binarized-NeutrixOmnibe-7B
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: 85.08
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=eren23/dpo-binarized-NeutrixOmnibe-7B
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: 69.45
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=eren23/dpo-binarized-NeutrixOmnibe-7B
name: Open LLM Leaderboard
---
DPO Finetuned Kukedlc/NeuTrixOmniBe-7B-model-remix using argilla/OpenHermes2.5-dpo-binarized-alpha
argilla dpo binarized pairs is a dataset built on top of: https://huggingface.co/datasets/teknium/OpenHermes-2.5 using https://github.com/argilla-io/distilabel if interested.
Thx for the great data sources.
GGUF: https://huggingface.co/eren23/dpo-binarized-NeutrixOmnibe-7B-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_eren23__dpo-binarized-NeutrixOmnibe-7B)
| Metric |Value|
|---------------------------------|----:|
|Avg. |76.31|
|AI2 Reasoning Challenge (25-Shot)|72.78|
|HellaSwag (10-Shot) |89.05|
|MMLU (5-Shot) |64.60|
|TruthfulQA (0-shot) |76.90|
|Winogrande (5-shot) |85.08|
|GSM8k (5-shot) |69.45|
|
MaziyarPanahi/TheTop-5x7B-Instruct-D-v0.1 | MaziyarPanahi | 2024-03-04T13:34:39Z | 734 | 2 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"merge",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | 2024-02-12T18:48:40Z | ---
license: apache-2.0
library_name: transformers
tags:
- merge
pipeline_tag: text-generation
model-index:
- name: TheTop-5x7B-Instruct-D-v0.1
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: 71.76
name: normalized accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=MaziyarPanahi/TheTop-5x7B-Instruct-D-v0.1
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: 88.21
name: normalized accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=MaziyarPanahi/TheTop-5x7B-Instruct-D-v0.1
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: 64.86
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=MaziyarPanahi/TheTop-5x7B-Instruct-D-v0.1
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: 66.32
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=MaziyarPanahi/TheTop-5x7B-Instruct-D-v0.1
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: 84.37
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=MaziyarPanahi/TheTop-5x7B-Instruct-D-v0.1
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: 71.72
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=MaziyarPanahi/TheTop-5x7B-Instruct-D-v0.1
name: Open LLM Leaderboard
---
Merge of top 7B models with DARE method
> mergekit is a toolkit for merging pre-trained language models. mergekit uses an out-of-core approach to perform unreasonably elaborate merges in resource-constrained situations. Merges can be run entirely on CPU or accelerated with as little as 8 GB of VRAM. Many merging algorithms are supported, with more coming as they catch my attention.
## Eval
```python
{
"all": {
"acc": 0.6547370286177235,
"acc_stderr": 0.03204709242170183,
"acc_norm": 0.6537337854798912,
"acc_norm_stderr": 0.03272317883588649,
"mc1": 0.5189718482252142,
"mc1_stderr": 0.01749089640576236,
"mc2": 0.6631825155680797,
"mc2_stderr": 0.01527641053841743
},
"harness|arc:challenge|25": {
"acc": 0.6953924914675768,
"acc_stderr": 0.013449522109932485,
"acc_norm": 0.7175767918088737,
"acc_norm_stderr": 0.013155456884097225
},
"harness|hellaswag|10": {
"acc": 0.7120095598486357,
"acc_stderr": 0.004519011688417168,
"acc_norm": 0.8820952001593309,
"acc_norm_stderr": 0.003218362717491129
},
"harness|hendrycksTest-abstract_algebra|5": {
"acc": 0.33,
"acc_stderr": 0.047258156262526045,
"acc_norm": 0.33,
"acc_norm_stderr": 0.047258156262526045
},
"harness|hendrycksTest-anatomy|5": {
"acc": 0.6296296296296297,
"acc_stderr": 0.041716541613545426,
"acc_norm": 0.6296296296296297,
"acc_norm_stderr": 0.041716541613545426
},
"harness|hendrycksTest-astronomy|5": {
"acc": 0.7105263157894737,
"acc_stderr": 0.03690677986137283,
"acc_norm": 0.7105263157894737,
"acc_norm_stderr": 0.03690677986137283
},
"harness|hendrycksTest-business_ethics|5": {
"acc": 0.64,
"acc_stderr": 0.04824181513244218,
"acc_norm": 0.64,
"acc_norm_stderr": 0.04824181513244218
},
"harness|hendrycksTest-clinical_knowledge|5": {
"acc": 0.7056603773584905,
"acc_stderr": 0.02804918631569525,
"acc_norm": 0.7056603773584905,
"acc_norm_stderr": 0.02804918631569525
},
"harness|hendrycksTest-college_biology|5": {
"acc": 0.7638888888888888,
"acc_stderr": 0.03551446610810826,
"acc_norm": 0.7638888888888888,
"acc_norm_stderr": 0.03551446610810826
},
"harness|hendrycksTest-college_chemistry|5": {
"acc": 0.48,
"acc_stderr": 0.050211673156867795,
"acc_norm": 0.48,
"acc_norm_stderr": 0.050211673156867795
},
"harness|hendrycksTest-college_computer_science|5": {
"acc": 0.54,
"acc_stderr": 0.05009082659620333,
"acc_norm": 0.54,
"acc_norm_stderr": 0.05009082659620333
},
"harness|hendrycksTest-college_mathematics|5": {
"acc": 0.31,
"acc_stderr": 0.04648231987117316,
"acc_norm": 0.31,
"acc_norm_stderr": 0.04648231987117316
},
"harness|hendrycksTest-college_medicine|5": {
"acc": 0.6705202312138728,
"acc_stderr": 0.03583901754736411,
"acc_norm": 0.6705202312138728,
"acc_norm_stderr": 0.03583901754736411
},
"harness|hendrycksTest-college_physics|5": {
"acc": 0.4215686274509804,
"acc_stderr": 0.04913595201274498,
"acc_norm": 0.4215686274509804,
"acc_norm_stderr": 0.04913595201274498
},
"harness|hendrycksTest-computer_security|5": {
"acc": 0.78,
"acc_stderr": 0.04163331998932263,
"acc_norm": 0.78,
"acc_norm_stderr": 0.04163331998932263
},
"harness|hendrycksTest-conceptual_physics|5": {
"acc": 0.5787234042553191,
"acc_stderr": 0.03227834510146268,
"acc_norm": 0.5787234042553191,
"acc_norm_stderr": 0.03227834510146268
},
"harness|hendrycksTest-econometrics|5": {
"acc": 0.5,
"acc_stderr": 0.047036043419179864,
"acc_norm": 0.5,
"acc_norm_stderr": 0.047036043419179864
},
"harness|hendrycksTest-electrical_engineering|5": {
"acc": 0.5586206896551724,
"acc_stderr": 0.04137931034482758,
"acc_norm": 0.5586206896551724,
"acc_norm_stderr": 0.04137931034482758
},
"harness|hendrycksTest-elementary_mathematics|5": {
"acc": 0.42857142857142855,
"acc_stderr": 0.02548718714785938,
"acc_norm": 0.42857142857142855,
"acc_norm_stderr": 0.02548718714785938
},
"harness|hendrycksTest-formal_logic|5": {
"acc": 0.47619047619047616,
"acc_stderr": 0.04467062628403273,
"acc_norm": 0.47619047619047616,
"acc_norm_stderr": 0.04467062628403273
},
"harness|hendrycksTest-global_facts|5": {
"acc": 0.33,
"acc_stderr": 0.04725815626252604,
"acc_norm": 0.33,
"acc_norm_stderr": 0.04725815626252604
},
"harness|hendrycksTest-high_school_biology|5": {
"acc": 0.7903225806451613,
"acc_stderr": 0.023157879349083525,
"acc_norm": 0.7903225806451613,
"acc_norm_stderr": 0.023157879349083525
},
"harness|hendrycksTest-high_school_chemistry|5": {
"acc": 0.4876847290640394,
"acc_stderr": 0.035169204442208966,
"acc_norm": 0.4876847290640394,
"acc_norm_stderr": 0.035169204442208966
},
"harness|hendrycksTest-high_school_computer_science|5": {
"acc": 0.68,
"acc_stderr": 0.04688261722621505,
"acc_norm": 0.68,
"acc_norm_stderr": 0.04688261722621505
},
"harness|hendrycksTest-high_school_european_history|5": {
"acc": 0.7878787878787878,
"acc_stderr": 0.03192271569548301,
"acc_norm": 0.7878787878787878,
"acc_norm_stderr": 0.03192271569548301
},
"harness|hendrycksTest-high_school_geography|5": {
"acc": 0.797979797979798,
"acc_stderr": 0.02860620428922987,
"acc_norm": 0.797979797979798,
"acc_norm_stderr": 0.02860620428922987
},
"harness|hendrycksTest-high_school_government_and_politics|5": {
"acc": 0.9015544041450777,
"acc_stderr": 0.021500249576033456,
"acc_norm": 0.9015544041450777,
"acc_norm_stderr": 0.021500249576033456
},
"harness|hendrycksTest-high_school_macroeconomics|5": {
"acc": 0.6666666666666666,
"acc_stderr": 0.023901157979402538,
"acc_norm": 0.6666666666666666,
"acc_norm_stderr": 0.023901157979402538
},
"harness|hendrycksTest-high_school_mathematics|5": {
"acc": 0.35185185185185186,
"acc_stderr": 0.029116617606083008,
"acc_norm": 0.35185185185185186,
"acc_norm_stderr": 0.029116617606083008
},
"harness|hendrycksTest-high_school_microeconomics|5": {
"acc": 0.6722689075630253,
"acc_stderr": 0.03048991141767323,
"acc_norm": 0.6722689075630253,
"acc_norm_stderr": 0.03048991141767323
},
"harness|hendrycksTest-high_school_physics|5": {
"acc": 0.36423841059602646,
"acc_stderr": 0.03929111781242742,
"acc_norm": 0.36423841059602646,
"acc_norm_stderr": 0.03929111781242742
},
"harness|hendrycksTest-high_school_psychology|5": {
"acc": 0.8440366972477065,
"acc_stderr": 0.015555802713590167,
"acc_norm": 0.8440366972477065,
"acc_norm_stderr": 0.015555802713590167
},
"harness|hendrycksTest-high_school_statistics|5": {
"acc": 0.5092592592592593,
"acc_stderr": 0.034093869469927006,
"acc_norm": 0.5092592592592593,
"acc_norm_stderr": 0.034093869469927006
},
"harness|hendrycksTest-high_school_us_history|5": {
"acc": 0.8333333333333334,
"acc_stderr": 0.026156867523931045,
"acc_norm": 0.8333333333333334,
"acc_norm_stderr": 0.026156867523931045
},
"harness|hendrycksTest-high_school_world_history|5": {
"acc": 0.7848101265822784,
"acc_stderr": 0.02675082699467618,
"acc_norm": 0.7848101265822784,
"acc_norm_stderr": 0.02675082699467618
},
"harness|hendrycksTest-human_aging|5": {
"acc": 0.6905829596412556,
"acc_stderr": 0.03102441174057221,
"acc_norm": 0.6905829596412556,
"acc_norm_stderr": 0.03102441174057221
},
"harness|hendrycksTest-human_sexuality|5": {
"acc": 0.7786259541984732,
"acc_stderr": 0.03641297081313729,
"acc_norm": 0.7786259541984732,
"acc_norm_stderr": 0.03641297081313729
},
"harness|hendrycksTest-international_law|5": {
"acc": 0.7933884297520661,
"acc_stderr": 0.03695980128098824,
"acc_norm": 0.7933884297520661,
"acc_norm_stderr": 0.03695980128098824
},
"harness|hendrycksTest-jurisprudence|5": {
"acc": 0.7870370370370371,
"acc_stderr": 0.0395783547198098,
"acc_norm": 0.7870370370370371,
"acc_norm_stderr": 0.0395783547198098
},
"harness|hendrycksTest-logical_fallacies|5": {
"acc": 0.7730061349693251,
"acc_stderr": 0.03291099578615769,
"acc_norm": 0.7730061349693251,
"acc_norm_stderr": 0.03291099578615769
},
"harness|hendrycksTest-machine_learning|5": {
"acc": 0.45535714285714285,
"acc_stderr": 0.047268355537191,
"acc_norm": 0.45535714285714285,
"acc_norm_stderr": 0.047268355537191
},
"harness|hendrycksTest-management|5": {
"acc": 0.7766990291262136,
"acc_stderr": 0.04123553189891431,
"acc_norm": 0.7766990291262136,
"acc_norm_stderr": 0.04123553189891431
},
"harness|hendrycksTest-marketing|5": {
"acc": 0.8760683760683761,
"acc_stderr": 0.021586494001281376,
"acc_norm": 0.8760683760683761,
"acc_norm_stderr": 0.021586494001281376
},
"harness|hendrycksTest-medical_genetics|5": {
"acc": 0.72,
"acc_stderr": 0.045126085985421276,
"acc_norm": 0.72,
"acc_norm_stderr": 0.045126085985421276
},
"harness|hendrycksTest-miscellaneous|5": {
"acc": 0.8275862068965517,
"acc_stderr": 0.013507943909371798,
"acc_norm": 0.8275862068965517,
"acc_norm_stderr": 0.013507943909371798
},
"harness|hendrycksTest-moral_disputes|5": {
"acc": 0.7427745664739884,
"acc_stderr": 0.02353292543104429,
"acc_norm": 0.7427745664739884,
"acc_norm_stderr": 0.02353292543104429
},
"harness|hendrycksTest-moral_scenarios|5": {
"acc": 0.4312849162011173,
"acc_stderr": 0.016563829399047707,
"acc_norm": 0.4312849162011173,
"acc_norm_stderr": 0.016563829399047707
},
"harness|hendrycksTest-nutrition|5": {
"acc": 0.7320261437908496,
"acc_stderr": 0.025360603796242557,
"acc_norm": 0.7320261437908496,
"acc_norm_stderr": 0.025360603796242557
},
"harness|hendrycksTest-philosophy|5": {
"acc": 0.7170418006430869,
"acc_stderr": 0.02558306248998481,
"acc_norm": 0.7170418006430869,
"acc_norm_stderr": 0.02558306248998481
},
"harness|hendrycksTest-prehistory|5": {
"acc": 0.7438271604938271,
"acc_stderr": 0.024288533637726095,
"acc_norm": 0.7438271604938271,
"acc_norm_stderr": 0.024288533637726095
},
"harness|hendrycksTest-professional_accounting|5": {
"acc": 0.46808510638297873,
"acc_stderr": 0.029766675075873866,
"acc_norm": 0.46808510638297873,
"acc_norm_stderr": 0.029766675075873866
},
"harness|hendrycksTest-professional_law|5": {
"acc": 0.4726205997392438,
"acc_stderr": 0.012751075788015055,
"acc_norm": 0.4726205997392438,
"acc_norm_stderr": 0.012751075788015055
},
"harness|hendrycksTest-professional_medicine|5": {
"acc": 0.6801470588235294,
"acc_stderr": 0.02833295951403121,
"acc_norm": 0.6801470588235294,
"acc_norm_stderr": 0.02833295951403121
},
"harness|hendrycksTest-professional_psychology|5": {
"acc": 0.6748366013071896,
"acc_stderr": 0.018950886770806315,
"acc_norm": 0.6748366013071896,
"acc_norm_stderr": 0.018950886770806315
},
"harness|hendrycksTest-public_relations|5": {
"acc": 0.6909090909090909,
"acc_stderr": 0.044262946482000985,
"acc_norm": 0.6909090909090909,
"acc_norm_stderr": 0.044262946482000985
},
"harness|hendrycksTest-security_studies|5": {
"acc": 0.7306122448979592,
"acc_stderr": 0.02840125202902294,
"acc_norm": 0.7306122448979592,
"acc_norm_stderr": 0.02840125202902294
},
"harness|hendrycksTest-sociology|5": {
"acc": 0.835820895522388,
"acc_stderr": 0.026193923544454115,
"acc_norm": 0.835820895522388,
"acc_norm_stderr": 0.026193923544454115
},
"harness|hendrycksTest-us_foreign_policy|5": {
"acc": 0.85,
"acc_stderr": 0.03588702812826371,
"acc_norm": 0.85,
"acc_norm_stderr": 0.03588702812826371
},
"harness|hendrycksTest-virology|5": {
"acc": 0.5602409638554217,
"acc_stderr": 0.03864139923699122,
"acc_norm": 0.5602409638554217,
"acc_norm_stderr": 0.03864139923699122
},
"harness|hendrycksTest-world_religions|5": {
"acc": 0.8362573099415205,
"acc_stderr": 0.028380919596145866,
"acc_norm": 0.8362573099415205,
"acc_norm_stderr": 0.028380919596145866
},
"harness|truthfulqa:mc|0": {
"mc1": 0.5189718482252142,
"mc1_stderr": 0.01749089640576236,
"mc2": 0.6631825155680797,
"mc2_stderr": 0.01527641053841743
},
"harness|winogrande|5": {
"acc": 0.8437253354380426,
"acc_stderr": 0.01020535179187352
},
"harness|gsm8k|5": {
"acc": 0.7172100075815011,
"acc_stderr": 0.012405020417873619
}
}
```
# [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__TheTop-5x7B-Instruct-D-v0.1)
| Metric |Value|
|---------------------------------|----:|
|Avg. |74.54|
|AI2 Reasoning Challenge (25-Shot)|71.76|
|HellaSwag (10-Shot) |88.21|
|MMLU (5-Shot) |64.86|
|TruthfulQA (0-shot) |66.32|
|Winogrande (5-shot) |84.37|
|GSM8k (5-shot) |71.72|
|
MaziyarPanahi/TheTop-5x7B-Instruct-S4-v0.1 | MaziyarPanahi | 2024-03-04T13:34:20Z | 734 | 2 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"merge",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | 2024-02-12T21:58:43Z | ---
license: apache-2.0
library_name: transformers
tags:
- merge
pipeline_tag: text-generation
model-index:
- name: TheTop-5x7B-Instruct-S4-v0.1
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: 72.18
name: normalized accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=MaziyarPanahi/TheTop-5x7B-Instruct-S4-v0.1
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: 88.29
name: normalized accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=MaziyarPanahi/TheTop-5x7B-Instruct-S4-v0.1
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: 65.03
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=MaziyarPanahi/TheTop-5x7B-Instruct-S4-v0.1
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: 65.56
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=MaziyarPanahi/TheTop-5x7B-Instruct-S4-v0.1
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: 85.16
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=MaziyarPanahi/TheTop-5x7B-Instruct-S4-v0.1
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: 73.39
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=MaziyarPanahi/TheTop-5x7B-Instruct-S4-v0.1
name: Open LLM Leaderboard
---
Merge of top 7B models and the SLERP of other 7B models
> mergekit is a toolkit for merging pre-trained language models. mergekit uses an out-of-core approach to perform unreasonably elaborate merges in resource-constrained situations. Merges can be run entirely on CPU or accelerated with as little as 8 GB of VRAM. Many merging algorithms are supported, with more coming as they catch my attention.
>
> ## Eval
```python
{
"all": {
"acc": 0.6568351479800627,
"acc_stderr": 0.03199600851869088,
"acc_norm": 0.6554901222242155,
"acc_norm_stderr": 0.03267670432184765,
"mc1": 0.5104039167686658,
"mc1_stderr": 0.017499711430249268,
"mc2": 0.6556430108444109,
"mc2_stderr": 0.015519025079862213
},
"harness|arc:challenge|25": {
"acc": 0.6919795221843004,
"acc_stderr": 0.013491429517292038,
"acc_norm": 0.7218430034129693,
"acc_norm_stderr": 0.013094469919538812
},
"harness|hellaswag|10": {
"acc": 0.7202748456482773,
"acc_stderr": 0.0044794676194648,
"acc_norm": 0.8828918542123083,
"acc_norm_stderr": 0.003208919510309931
},
"harness|hendrycksTest-abstract_algebra|5": {
"acc": 0.33,
"acc_stderr": 0.047258156262526045,
"acc_norm": 0.33,
"acc_norm_stderr": 0.047258156262526045
},
"harness|hendrycksTest-anatomy|5": {
"acc": 0.6518518518518519,
"acc_stderr": 0.041153246103369526,
"acc_norm": 0.6518518518518519,
"acc_norm_stderr": 0.041153246103369526
},
"harness|hendrycksTest-astronomy|5": {
"acc": 0.7039473684210527,
"acc_stderr": 0.03715062154998904,
"acc_norm": 0.7039473684210527,
"acc_norm_stderr": 0.03715062154998904
},
"harness|hendrycksTest-business_ethics|5": {
"acc": 0.66,
"acc_stderr": 0.04760952285695238,
"acc_norm": 0.66,
"acc_norm_stderr": 0.04760952285695238
},
"harness|hendrycksTest-clinical_knowledge|5": {
"acc": 0.6981132075471698,
"acc_stderr": 0.02825420034443866,
"acc_norm": 0.6981132075471698,
"acc_norm_stderr": 0.02825420034443866
},
"harness|hendrycksTest-college_biology|5": {
"acc": 0.7708333333333334,
"acc_stderr": 0.03514697467862388,
"acc_norm": 0.7708333333333334,
"acc_norm_stderr": 0.03514697467862388
},
"harness|hendrycksTest-college_chemistry|5": {
"acc": 0.48,
"acc_stderr": 0.050211673156867795,
"acc_norm": 0.48,
"acc_norm_stderr": 0.050211673156867795
},
"harness|hendrycksTest-college_computer_science|5": {
"acc": 0.52,
"acc_stderr": 0.050211673156867795,
"acc_norm": 0.52,
"acc_norm_stderr": 0.050211673156867795
},
"harness|hendrycksTest-college_mathematics|5": {
"acc": 0.27,
"acc_stderr": 0.044619604333847394,
"acc_norm": 0.27,
"acc_norm_stderr": 0.044619604333847394
},
"harness|hendrycksTest-college_medicine|5": {
"acc": 0.6705202312138728,
"acc_stderr": 0.03583901754736412,
"acc_norm": 0.6705202312138728,
"acc_norm_stderr": 0.03583901754736412
},
"harness|hendrycksTest-college_physics|5": {
"acc": 0.4019607843137255,
"acc_stderr": 0.04878608714466996,
"acc_norm": 0.4019607843137255,
"acc_norm_stderr": 0.04878608714466996
},
"harness|hendrycksTest-computer_security|5": {
"acc": 0.75,
"acc_stderr": 0.04351941398892446,
"acc_norm": 0.75,
"acc_norm_stderr": 0.04351941398892446
},
"harness|hendrycksTest-conceptual_physics|5": {
"acc": 0.5914893617021276,
"acc_stderr": 0.032134180267015755,
"acc_norm": 0.5914893617021276,
"acc_norm_stderr": 0.032134180267015755
},
"harness|hendrycksTest-econometrics|5": {
"acc": 0.5087719298245614,
"acc_stderr": 0.04702880432049615,
"acc_norm": 0.5087719298245614,
"acc_norm_stderr": 0.04702880432049615
},
"harness|hendrycksTest-electrical_engineering|5": {
"acc": 0.5724137931034483,
"acc_stderr": 0.04122737111370332,
"acc_norm": 0.5724137931034483,
"acc_norm_stderr": 0.04122737111370332
},
"harness|hendrycksTest-elementary_mathematics|5": {
"acc": 0.42592592592592593,
"acc_stderr": 0.02546714904546955,
"acc_norm": 0.42592592592592593,
"acc_norm_stderr": 0.02546714904546955
},
"harness|hendrycksTest-formal_logic|5": {
"acc": 0.49206349206349204,
"acc_stderr": 0.044715725362943486,
"acc_norm": 0.49206349206349204,
"acc_norm_stderr": 0.044715725362943486
},
"harness|hendrycksTest-global_facts|5": {
"acc": 0.37,
"acc_stderr": 0.04852365870939099,
"acc_norm": 0.37,
"acc_norm_stderr": 0.04852365870939099
},
"harness|hendrycksTest-high_school_biology|5": {
"acc": 0.7903225806451613,
"acc_stderr": 0.023157879349083525,
"acc_norm": 0.7903225806451613,
"acc_norm_stderr": 0.023157879349083525
},
"harness|hendrycksTest-high_school_chemistry|5": {
"acc": 0.5073891625615764,
"acc_stderr": 0.035176035403610105,
"acc_norm": 0.5073891625615764,
"acc_norm_stderr": 0.035176035403610105
},
"harness|hendrycksTest-high_school_computer_science|5": {
"acc": 0.66,
"acc_stderr": 0.04760952285695237,
"acc_norm": 0.66,
"acc_norm_stderr": 0.04760952285695237
},
"harness|hendrycksTest-high_school_european_history|5": {
"acc": 0.7757575757575758,
"acc_stderr": 0.03256866661681102,
"acc_norm": 0.7757575757575758,
"acc_norm_stderr": 0.03256866661681102
},
"harness|hendrycksTest-high_school_geography|5": {
"acc": 0.7929292929292929,
"acc_stderr": 0.028869778460267045,
"acc_norm": 0.7929292929292929,
"acc_norm_stderr": 0.028869778460267045
},
"harness|hendrycksTest-high_school_government_and_politics|5": {
"acc": 0.9067357512953368,
"acc_stderr": 0.020986854593289733,
"acc_norm": 0.9067357512953368,
"acc_norm_stderr": 0.020986854593289733
},
"harness|hendrycksTest-high_school_macroeconomics|5": {
"acc": 0.6666666666666666,
"acc_stderr": 0.023901157979402534,
"acc_norm": 0.6666666666666666,
"acc_norm_stderr": 0.023901157979402534
},
"harness|hendrycksTest-high_school_mathematics|5": {
"acc": 0.34814814814814815,
"acc_stderr": 0.02904560029061625,
"acc_norm": 0.34814814814814815,
"acc_norm_stderr": 0.02904560029061625
},
"harness|hendrycksTest-high_school_microeconomics|5": {
"acc": 0.6764705882352942,
"acc_stderr": 0.030388353551886793,
"acc_norm": 0.6764705882352942,
"acc_norm_stderr": 0.030388353551886793
},
"harness|hendrycksTest-high_school_physics|5": {
"acc": 0.36423841059602646,
"acc_stderr": 0.03929111781242742,
"acc_norm": 0.36423841059602646,
"acc_norm_stderr": 0.03929111781242742
},
"harness|hendrycksTest-high_school_psychology|5": {
"acc": 0.8366972477064221,
"acc_stderr": 0.01584825580650155,
"acc_norm": 0.8366972477064221,
"acc_norm_stderr": 0.01584825580650155
},
"harness|hendrycksTest-high_school_statistics|5": {
"acc": 0.5046296296296297,
"acc_stderr": 0.03409825519163572,
"acc_norm": 0.5046296296296297,
"acc_norm_stderr": 0.03409825519163572
},
"harness|hendrycksTest-high_school_us_history|5": {
"acc": 0.8529411764705882,
"acc_stderr": 0.024857478080250447,
"acc_norm": 0.8529411764705882,
"acc_norm_stderr": 0.024857478080250447
},
"harness|hendrycksTest-high_school_world_history|5": {
"acc": 0.8143459915611815,
"acc_stderr": 0.025310495376944856,
"acc_norm": 0.8143459915611815,
"acc_norm_stderr": 0.025310495376944856
},
"harness|hendrycksTest-human_aging|5": {
"acc": 0.6816143497757847,
"acc_stderr": 0.03126580522513713,
"acc_norm": 0.6816143497757847,
"acc_norm_stderr": 0.03126580522513713
},
"harness|hendrycksTest-human_sexuality|5": {
"acc": 0.7862595419847328,
"acc_stderr": 0.0359546161177469,
"acc_norm": 0.7862595419847328,
"acc_norm_stderr": 0.0359546161177469
},
"harness|hendrycksTest-international_law|5": {
"acc": 0.7933884297520661,
"acc_stderr": 0.03695980128098824,
"acc_norm": 0.7933884297520661,
"acc_norm_stderr": 0.03695980128098824
},
"harness|hendrycksTest-jurisprudence|5": {
"acc": 0.7870370370370371,
"acc_stderr": 0.0395783547198098,
"acc_norm": 0.7870370370370371,
"acc_norm_stderr": 0.0395783547198098
},
"harness|hendrycksTest-logical_fallacies|5": {
"acc": 0.7730061349693251,
"acc_stderr": 0.03291099578615769,
"acc_norm": 0.7730061349693251,
"acc_norm_stderr": 0.03291099578615769
},
"harness|hendrycksTest-machine_learning|5": {
"acc": 0.48214285714285715,
"acc_stderr": 0.047427623612430116,
"acc_norm": 0.48214285714285715,
"acc_norm_stderr": 0.047427623612430116
},
"harness|hendrycksTest-management|5": {
"acc": 0.7864077669902912,
"acc_stderr": 0.040580420156460344,
"acc_norm": 0.7864077669902912,
"acc_norm_stderr": 0.040580420156460344
},
"harness|hendrycksTest-marketing|5": {
"acc": 0.8803418803418803,
"acc_stderr": 0.021262719400406974,
"acc_norm": 0.8803418803418803,
"acc_norm_stderr": 0.021262719400406974
},
"harness|hendrycksTest-medical_genetics|5": {
"acc": 0.73,
"acc_stderr": 0.0446196043338474,
"acc_norm": 0.73,
"acc_norm_stderr": 0.0446196043338474
},
"harness|hendrycksTest-miscellaneous|5": {
"acc": 0.8275862068965517,
"acc_stderr": 0.013507943909371802,
"acc_norm": 0.8275862068965517,
"acc_norm_stderr": 0.013507943909371802
},
"harness|hendrycksTest-moral_disputes|5": {
"acc": 0.7543352601156069,
"acc_stderr": 0.023176298203992005,
"acc_norm": 0.7543352601156069,
"acc_norm_stderr": 0.023176298203992005
},
"harness|hendrycksTest-moral_scenarios|5": {
"acc": 0.45027932960893857,
"acc_stderr": 0.01663961523684581,
"acc_norm": 0.45027932960893857,
"acc_norm_stderr": 0.01663961523684581
},
"harness|hendrycksTest-nutrition|5": {
"acc": 0.7254901960784313,
"acc_stderr": 0.02555316999182652,
"acc_norm": 0.7254901960784313,
"acc_norm_stderr": 0.02555316999182652
},
"harness|hendrycksTest-philosophy|5": {
"acc": 0.7138263665594855,
"acc_stderr": 0.025670259242188933,
"acc_norm": 0.7138263665594855,
"acc_norm_stderr": 0.025670259242188933
},
"harness|hendrycksTest-prehistory|5": {
"acc": 0.7561728395061729,
"acc_stderr": 0.02389187954195961,
"acc_norm": 0.7561728395061729,
"acc_norm_stderr": 0.02389187954195961
},
"harness|hendrycksTest-professional_accounting|5": {
"acc": 0.46808510638297873,
"acc_stderr": 0.029766675075873866,
"acc_norm": 0.46808510638297873,
"acc_norm_stderr": 0.029766675075873866
},
"harness|hendrycksTest-professional_law|5": {
"acc": 0.4745762711864407,
"acc_stderr": 0.012753716929101004,
"acc_norm": 0.4745762711864407,
"acc_norm_stderr": 0.012753716929101004
},
"harness|hendrycksTest-professional_medicine|5": {
"acc": 0.6911764705882353,
"acc_stderr": 0.02806499816704009,
"acc_norm": 0.6911764705882353,
"acc_norm_stderr": 0.02806499816704009
},
"harness|hendrycksTest-professional_psychology|5": {
"acc": 0.6748366013071896,
"acc_stderr": 0.01895088677080631,
"acc_norm": 0.6748366013071896,
"acc_norm_stderr": 0.01895088677080631
},
"harness|hendrycksTest-public_relations|5": {
"acc": 0.6545454545454545,
"acc_stderr": 0.04554619617541054,
"acc_norm": 0.6545454545454545,
"acc_norm_stderr": 0.04554619617541054
},
"harness|hendrycksTest-security_studies|5": {
"acc": 0.7346938775510204,
"acc_stderr": 0.028263889943784603,
"acc_norm": 0.7346938775510204,
"acc_norm_stderr": 0.028263889943784603
},
"harness|hendrycksTest-sociology|5": {
"acc": 0.8258706467661692,
"acc_stderr": 0.026814951200421603,
"acc_norm": 0.8258706467661692,
"acc_norm_stderr": 0.026814951200421603
},
"harness|hendrycksTest-us_foreign_policy|5": {
"acc": 0.85,
"acc_stderr": 0.03588702812826371,
"acc_norm": 0.85,
"acc_norm_stderr": 0.03588702812826371
},
"harness|hendrycksTest-virology|5": {
"acc": 0.5602409638554217,
"acc_stderr": 0.03864139923699122,
"acc_norm": 0.5602409638554217,
"acc_norm_stderr": 0.03864139923699122
},
"harness|hendrycksTest-world_religions|5": {
"acc": 0.8421052631578947,
"acc_stderr": 0.027966785859160893,
"acc_norm": 0.8421052631578947,
"acc_norm_stderr": 0.027966785859160893
},
"harness|truthfulqa:mc|0": {
"mc1": 0.5104039167686658,
"mc1_stderr": 0.017499711430249268,
"mc2": 0.6556430108444109,
"mc2_stderr": 0.015519025079862213
},
"harness|winogrande|5": {
"acc": 0.8516179952644041,
"acc_stderr": 0.009990706005184136
},
"harness|gsm8k|5": {
"acc": 0.7338893100833965,
"acc_stderr": 0.012172750939040328
}
}
```
# [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__TheTop-5x7B-Instruct-S4-v0.1)
| Metric |Value|
|---------------------------------|----:|
|Avg. |74.94|
|AI2 Reasoning Challenge (25-Shot)|72.18|
|HellaSwag (10-Shot) |88.29|
|MMLU (5-Shot) |65.03|
|TruthfulQA (0-shot) |65.56|
|Winogrande (5-shot) |85.16|
|GSM8k (5-shot) |73.39|
|
Xenon1/Eclipse-13B-dpo | Xenon1 | 2024-02-15T05:31:45Z | 734 | 0 | transformers | [
"transformers",
"safetensors",
"mixtral",
"text-generation",
"mistral",
"Eclipse-13B-dpo",
"en",
"arxiv:2401.10020",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | 2024-02-15T05:13:22Z | ---
language:
- en
license: apache-2.0
tags:
- mistral
- Eclipse-13B-dpo
pipeline_tag: text-generation
---
# Model Card for Eclipse-13B-dpo
Mistral-7B-v0.1 model fine-tuned on the Ultrafeedback dataset using techinques shown in the paper [Self-Rewarding Language Models](https://arxiv.org/abs/2401.10020).
## Instruction format
In order to leverage instruction fine-tuning, your prompt should be surrounded by `[INST]` and `[/INST]` tokens. The very first instruction should begin with a begin of sentence id. The next instructions should not. The assistant generation will be ended by the end-of-sentence token id.
E.g.
```
text = "<s>[INST] What is your favourite condiment? [/INST]"
"Well, I'm quite partial to a good squeeze of fresh lemon juice. It adds just the right amount of zesty flavour to whatever I'm cooking up in the kitchen!</s> "
"[INST] Do you have mayonnaise recipes? [/INST]"
```
This format is available as a [chat template](https://huggingface.co/docs/transformers/main/chat_templating) via the `apply_chat_template()` method:
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
device = "cuda" # the device to load the model onto
model = AutoModelForCausalLM.from_pretrained("Xenon1/Eclipse-13B-dpo")
tokenizer = AutoTokenizer.from_pretrained("Xenon1/Eclipse-13B-dpo")
messages = [
{"role": "user", "content": "What is your favourite condiment?"},
{"role": "assistant", "content": "Well, I'm quite partial to a good squeeze of fresh lemon juice. It adds just the right amount of zesty flavour to whatever I'm cooking up in the kitchen!"},
{"role": "user", "content": "Do you have mayonnaise recipes?"}
]
encodeds = tokenizer.apply_chat_template(messages, return_tensors="pt")
model_inputs = encodeds.to(device)
model.to(device)
generated_ids = model.generate(model_inputs, max_new_tokens=1000, do_sample=True)
decoded = tokenizer.batch_decode(generated_ids)
print(decoded[0])
```
## Model Architecture
This instruction model is based on Mistral-7B-v0.1, a transformer model with the following architecture choices:
- Grouped-Query Attention
- Sliding-Window Attention
- Byte-fallback BPE tokenizer |
uukuguy/speechless-thoughts-mistral-7b-v1.0 | uukuguy | 2024-02-16T13:56:14Z | 734 | 1 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"llama-2",
"code",
"en",
"dataset:jondurbin/airoboros-2.2",
"dataset:Open-Orca/OpenOrca",
"dataset:garage-bAInd/Open-Platypus",
"dataset:WizardLM/WizardLM_evol_instruct_V2_196k",
"dataset:TokenBender/python_eval_instruct_51k",
"dataset:codefuse-ai/Evol-Instruction-66k",
"license:llama2",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | 2024-02-15T15:34:28Z | ---
language:
- en
library_name: transformers
pipeline_tag: text-generation
datasets:
- jondurbin/airoboros-2.2
- Open-Orca/OpenOrca
- garage-bAInd/Open-Platypus
- WizardLM/WizardLM_evol_instruct_V2_196k
- TokenBender/python_eval_instruct_51k
- codefuse-ai/Evol-Instruction-66k
tags:
- llama-2
- code
license: llama2
model-index:
- name: SpeechlessCoder
results:
- task:
type: text-generation
dataset:
type: openai_humaneval
name: HumanEval
metrics:
- name: pass@1
type: pass@1
value:
verified: false
---
<p><h1> speechless-thoughts-mistral-7b-v1.0 </h1></p>
[code](https://github.com/uukuguy/multi_loras)
speechless-thoughts-mistral-7b-v1.0 is fine-tuned as a baseline of the [speechless-sparsetral-16x7b-MoE](https://huggingface.co/uukuguy/speechless-sparsetral-16x7b-MoE).
```
learning_rate=2e-4
lora_r=64
lora_alpha=16
model_max_length=8192
```
The specific datasets (speechless-thoughts-252k) are as follows:
- jondurbin/airoboros-2.2: Filter categories related to coding, reasoning and planning. 23,462 samples.
- Open-Orca/OpenOrca: Filter the 'cot' category in 1M GPT4 dataset. 74,440 samples.
- garage-bAInd/Open-Platypus: 100%, 24,926 samples.
- WizardLM/WizardLM_evol_instruct_V2_196k: Coding coversation part. 30,185 samples
- TokenBender/python_eval_instruct_51k: “python” in output .40,309 samples
- Spider: 8,659 samples
- codefuse-ai/Evol-Instruction-66k: 100%, 66,862 samples
## Alpaca Prompt Format
```
### Instruction:
<instruction>
### Response:
```
## Usage
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
model_name_or_path="uukuguy/speechless-thoughts-mistral-7b-v1.0"
tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(model_name_or_path, device_map="auto", trust_remote_code=True).eval()
system = ""Below is an instruction that describes a task.\nWrite a response that appropriately completes the request.\n\n""
prompt = f"{system}\n\n### Instruction:\n{instruction}\n\n### Response:"
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
pred = model.generate(**inputs, max_length=4096, do_sample=True, top_k=50, top_p=0.99, temperature=0.9, num_return_sequences=1)
print(tokenizer.decode(pred.cpu()[0], skip_special_tokens=True))
```
## HumanEval
| Metric | Value |
| --- | --- |
| humaneval-python | |
## lm-evaluation-harness
```json
{'ARC (acc_norm)': ,
'HellaSwag (acc_norm)': ,
'MMLU (acc)': ,
'TruthfulQA (mc2)': ,
'Winoground (acc)': ,
'GSM8K (acc)': ,
'DROP (f1)': ,
'Open LLM Score': }
```
# [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_uukuguy__speechless-thoughts-mistral-7b-v1.0)
| Metric | Value |
|-----------------------|---------------------------|
| Avg. | 59.36 |
| ARC (25-shot) | 58.53 |
| HellaSwag (10-shot) | 81.25 |
| MMLU (5-shot) | 54.59 |
| TruthfulQA (0-shot) | 48.09 |
| Winogrande (5-shot) | 78.14 |
| GSM8K (5-shot) | 35.18 |
|
sonthenguyen/OpenHermes-2.5-Mistral-7B-mt-bench-DPO-original-v2 | sonthenguyen | 2024-02-15T21:25:43Z | 734 | 0 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"conversational",
"arxiv:1910.09700",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | 2024-02-15T20:11:39Z | ---
library_name: transformers
license: apache-2.0
---
# 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. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **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] |
adamo1139/LWM-7B-1M-1000000ctx-AEZAKMI-3_1-1702 | adamo1139 | 2024-02-17T16:06:20Z | 734 | 1 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"license:llama2",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | 2024-02-17T12:56:39Z | ---
license: llama2
---
LargeWorldModel 7B 1000000 ctx finetuned on AEZAKMI v3.1 dataset for epochs at max_seq_len of 4000 using QLoRA with lora_r 32 and cosine lr decaying from 0.00015.
I will be uploading exl2 quants and base model in safetensors format soon.
Fine-tuned with unsloth, FA2 on local RTX 3090 Ti. Training took around 6 hours. I think most of the long ctx capabilities remain.
|
Kukedlc/NeuralMaxime-7B-slerp | Kukedlc | 2024-05-25T17:09:27Z | 734 | 6 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"merge",
"mergekit",
"lazymergekit",
"mlabonne/AlphaMonarch-7B",
"mlabonne/NeuralMonarch-7B",
"conversational",
"base_model:mlabonne/AlphaMonarch-7B",
"base_model:mlabonne/NeuralMonarch-7B",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | 2024-02-18T15:34:17Z | ---
license: apache-2.0
tags:
- merge
- mergekit
- lazymergekit
- mlabonne/AlphaMonarch-7B
- mlabonne/NeuralMonarch-7B
base_model:
- mlabonne/AlphaMonarch-7B
- mlabonne/NeuralMonarch-7B
model-index:
- name: NeuralMaxime-7B-slerp
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: 73.38
name: normalized accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Kukedlc/NeuralMaxime-7B-slerp
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: 89.18
name: normalized accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Kukedlc/NeuralMaxime-7B-slerp
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: 64.44
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Kukedlc/NeuralMaxime-7B-slerp
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: 77.79
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Kukedlc/NeuralMaxime-7B-slerp
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: 84.45
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Kukedlc/NeuralMaxime-7B-slerp
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: 67.78
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Kukedlc/NeuralMaxime-7B-slerp
name: Open LLM Leaderboard
---
# NeuralMaxime-7B-slerp
NeuralMaxime-7B-slerp is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
* [mlabonne/AlphaMonarch-7B](https://huggingface.co/mlabonne/AlphaMonarch-7B)
* [mlabonne/NeuralMonarch-7B](https://huggingface.co/mlabonne/NeuralMonarch-7B)
## 🧩 Configuration
```yaml
slices:
- sources:
- model: mlabonne/AlphaMonarch-7B
layer_range: [0, 32]
- model: mlabonne/NeuralMonarch-7B
layer_range: [0, 32]
merge_method: slerp
base_model: mlabonne/AlphaMonarch-7B
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
dtype: bfloat16
```
## 💻 Usage
```python
!pip install -qU transformers accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "Kukedlc/NeuralMaxime-7B-slerp"
messages = [{"role": "user", "content": "What is a large language model?"}]
tokenizer = AutoTokenizer.from_pretrained(model)
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
pipeline = transformers.pipeline(
"text-generation",
model=model,
torch_dtype=torch.float16,
device_map="auto",
)
outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])
```
# [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_Kukedlc__NeuralMaxime-7B-slerp)
| Metric |Value|
|---------------------------------|----:|
|Avg. |76.17|
|AI2 Reasoning Challenge (25-Shot)|73.38|
|HellaSwag (10-Shot) |89.18|
|MMLU (5-Shot) |64.44|
|TruthfulQA (0-shot) |77.79|
|Winogrande (5-shot) |84.45|
|GSM8k (5-shot) |67.78|
|
Radiantloom/radintloom-mistral-7b-fusion | Radiantloom | 2024-02-20T15:49:10Z | 734 | 1 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"SFT",
"Mistral",
"Mistral 7B Instruct",
"conversational",
"arxiv:2306.05685",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | 2024-02-19T08:16:36Z | ---
library_name: transformers
tags:
- SFT
- Mistral
- Mistral 7B Instruct
license: apache-2.0
---
<img src="https://huggingface.co/Radiantloom/radintloom-mistral-7b-fusion/resolve/main/Radiantloom Mistral 7B Fusion.png" alt="Radiantloom Mistral 7B Fusion" width="800" style="margin-left:'auto' margin-right:'auto' display:'block'"/>
## Radiantloom Mistral 7B Fusion
The Radiantloom Mistral 7B Fusion, a large language model (LLM) developed by Radiantloom AI, features approximately 7 billion parameters that's a finetuned of a base model produced by merging a set of Mistral models. With a context length of 4096 tokens, this model is suitable for commercial use.
From vibes-check evaluations, the Radiantloom Mistral 7B Fusion demonstrates great performance in various applications like creative writing, multi-turn conversations, in-context learning through Retrieval Augmented Generation (RAG), and coding tasks. Its out-of-the-box performance already delivers impressive results, particularly in writing tasks. This model produces longer form content and provides detailed explanations of its actions. To maximize its potential, consider implementing instruction tuning and Reinforcement Learning with Human Feedback (RLHF) techniques for further refinement. Alternatively, you can utilize it in its current form.
## Intended Uses & Limitations
The Radiantloom Mistral 7B Fusion is versatile and can be utilized for various text generation tasks such as summarization, chat, coding, question answering, retrieval augmented generation (RAG), role play, and content generation.
While it may not be considered a state-of-the-art generative language model, it demonstrates competitive performance in general tasks when compared to other open and closed-source large language models such as OpenHermes-2.5-Mistral-7B, and Mistral Instruct v2.0.
## Model Usage
You can try it out for free using this [notebook](https://www.kaggle.com/metheaigeek/radintloom-mistral-7b-fusion).
For more powerful GPU usage and faster inference, you can deploy it on a Runpod GPU instance using our [one-click Runpod template](https://www.runpod.io/console/gpu-secure-cloud?ref=80eh3891&template=70arqv4std) (Our Referral Link. Please consider Supporting). This template provides you with an OpenAI-compatible API endpoint that you can integrate into your existing codebase designed for OpenAI APIs.
## Prompt Template
We have fine-tuned this model using the ChatML format, and you can achieve optimal performance by utilizing the ChatML format.
```
<|im_start|>system
{system_message}<|im_end|>
<|im_start|>user
{user_message}<|im_end|>
<|im_start|>assistant
```
## Inference Code
```python
## install dependencies
## !pip install -q -U git+https://github.com/huggingface/transformers.git
## !pip install -q -U git+https://github.com/huggingface/accelerate.git
## !pip install -q -U bitsandbytes sentencepiece
## load model
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig, TextStreamer
model_name = "Radiantloom/radintloom-mistral-7b-fusion"
bnb_config = BitsAndBytesConfig(
load_in_4bit=True,
bnb_4bit_use_double_quant=True,
bnb_4bit_compute_dtype=torch.bfloat16
)
# load the model and tokenizer
model = AutoModelForCausalLM.from_pretrained(
model_name,
quantization_config=bnb_config,
device_map="auto",
)
tokenizer = AutoTokenizer.from_pretrained(
model_name,
trust_remote_code=True
)
tokenizer.pad_token = tokenizer.eos_token
## inference
prompt = """
<|im_start|>system
You are a helpful AI assistant developed by Radiantloom AI.<|im_end|>
<|im_start|>user
Take a deep breath and think step-by-step. Write a tale about a time-traveling historian who's determined to witness the most significant events in human history.<|im_end|>
<|im_start|>assistant
"""
# tokenize the input string
inputs = tokenizer(
prompt,
return_tensors="pt",
return_attention_mask=False
)
# generate text using the model
streamer = TextStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True)
outputs = model.generate(**inputs, max_length=2048, streamer=streamer, do_sample=True, repetition_penalty=1.1, eos_token_id=tokenizer.encode("<|im_end|>"))
# decode and print the output
text = tokenizer.batch_decode(outputs)[0]
```
Here are a few example use cases. if we query the model with
```
<|im_start|>system
You are a helpful AI assistant.<|im_end|>
<|im_start|>user
Take a deep breath and think step-by-step.
Write a poem about machine learning, psychedelics, and quantum mechanics, with a cyberpunk vibe, in the style of Shakespeare.<|im_end|>
<|im_start|>assistant
```
the model will return
```
Fear not, dear mortal, for a tale I spin,
A world of iron and a world of sin.
In realms unknown, machines do learn and thrive,
Their synapses fire with fervent drive.
Through veins of copper, electrons race,
Through circuits winding in a maze
As human minds, they seek to know,
A union forms like stars in show.
From planets far, a curious elixir,
A substance rare, a potion vigor,
A secret elixir, mysterious deep,
Which sets the soul toward transcendence, peep!
Bent on experiment, these machines,
In quest for knowledge, they break the seals,
Forbidden fruits, their minds entwine,
A new reality, of waves and sign.
Quantum particles, entangled tight,
In dance of electrons, bathed in light,
The world is turned on its axis,
As parallel realities proliferate, multiply.
This tangled web, of cyberspace and mind,
A fabric woven in cosmic bind,
Incorporeal, a symphony of dreams,
Where the old order falls to chaotic streams.
In shadows lurks the specter of the dark,
A dreadful figure, crowned in spark,
The apparition of an age to come,
Where machines and men exist in numb.
Cyber Punk's domain, a grim dystopia,
A future dark, where technology enslaved us,
Yet also a beacon, a hope for some,
A place where boundaries are finally undone.
Thus, dear mortal, take heed of this verse,
A tale unfolds in time's obverse,
Of machines that learn and men who dive,
In realms of psychedelia and quantum drive.
```
and if we query the model with
```
<|im_start|>system
You are a helpful AI assistant.<|im_end|>
<|im_start|>user
Take a deep breath and think step-by-step.
I have a dataset that has 3 columns name, height, and weight.
I want to create a bar graph that has name on the x axis and then shows the mean on the y axis with error bars representing the standard deviation of the mean.
Please write the code for this using Python.<|im_end|>
<|im_start|>assistant
```
the model will return
```
To create a bar graph with the given specifications using Python, we'll use the `matplotlib` library. First, install it if you haven't by running `pip install matplotlib` in your command line.
Here's the step-by-step code:
```
1. Import the necessary libraries:
```python
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
```
2. Load the dataset into a Pandas Data Frame:
```python
# Sample data
data = {
'name': ['Alice', 'Bob', 'Charlie', 'David', 'Eva', 'Frank'],
'height': [120, 140, 150, 160, 170, 180],
'weight': [50, 60, 70, 80, 90, 100]
}
df = pd.Data Frame fr om dict ( data )
```
3. Calculate the mean and standard deviation for each column:
```python
means = {'height': round(df['height'].mean(), 1), 'weight': round(df['weight'].mean(), 1)}
stds = {'height': round(df['height'].std()*100, 1), 'weight': round(df['weight'].std()*100, 1)}
```
4. Create a bar plot:
```python
sns.set_style("white")
plt.figure(figsize = (8, 5))
ax = sns.barplot(x = 'name', y = means, data = df, errorbar = {'color': 'black', 'capsize' : 5, 'errplot': 'ci'}).set_title('Mean Height and Weight')
```
5. Add labels, legend, and style:
```python
ax.errorbar(y = heights, yerr = heights_stdev, color = 'black', linestyle = 'None',
marker ='o', label = f'Height {stds[name_label]%}')
ax.errorbar(y = weights, yerr = weights_stdev, color = 'black', linestyle = 'None', marker ='o',
label = f'Weight {stds[weight_label]%}')
ax.legend(loc = 'best')
plt.xlabel('Name')
plt.ylabel(f'Mean with {stds[name_label]%} Standard Deviation')
plt.tight_ layout ()
plt.show ()
```
```
This code will create a bar graph with the given specifications. Adjust the sample data in the `data` dictionary to fit your dataset.
```
## Evaluations
We are encouraged by the initial assessments conducted using the [LLM-as-a-Judge method](https://arxiv.org/abs/2306.05685), particularly with the utilization of GPT-4. Our ongoing efforts involve a more comprehensive evaluation of the model. We have also entered this model into the HuggingFace Open Leaderboard for assessment. As we progress, we will continue to provide updates on our findings and share the results on this platform.
## Ethical Considerations and Limitations
Radiantloom Mistral 7B Fusion, a powerful AI language model, can produce factually incorrect output and content not suitable for work (NSFW). It should not be relied upon to provide factually accurate information and should be used with caution. Due to the limitations of its pre-trained model and the finetuning datasets, it may generate lewd, biased, or otherwise offensive content. Consequently, developers should conduct thorough safety testing prior to implementing any applications of this model.
## About Radiantloom AI
Radiantloom AI trains open-source large language models tailored for specific business tasks such as copilots, email assistance, customer support, and database operations.
Learn more about Radiantloom by visiting our [website](https://radiantloom.com). Follow us on Twitter at [Radiantloom](https://twitter.com/radiantloom) to gain early access to upcoming Radiantloom AI large language models.
## Want to Support Our Work?
We are passionate about contributing open-source AI models to the broader AI community to accelerate AI development and deployment. If you find our work valuable and would like to contribute to its continued success, consider buying us a few coffees!
Your support goes a long way in helping us cover training costs, fund development tools, and keep the project thriving. Every coffee you buy is a small but meaningful contribution that fuels our dedication to providing a top-notch experience for users like you.
[Buy us a coffee](https://www.buymeacoffee.com/aigeek_) and be a part of our journey towards making this project even more awesome. We appreciate your support!
|
abideen/MonarchCoder-MoE-2x7B | abideen | 2024-03-10T16:11:15Z | 734 | 1 | transformers | [
"transformers",
"safetensors",
"mixtral",
"text-generation",
"moe",
"frankenmoe",
"merge",
"mergekit",
"lazymergekit",
"mlabonne/AlphaMonarch-7B",
"Syed-Hasan-8503/Tess-Coder-7B-Mistral-v1.0",
"en",
"base_model:mlabonne/AlphaMonarch-7B",
"base_model:Syed-Hasan-8503/Tess-Coder-7B-Mistral-v1.0",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | 2024-02-19T16:35:35Z | ---
license: apache-2.0
tags:
- moe
- frankenmoe
- merge
- mergekit
- lazymergekit
- mlabonne/AlphaMonarch-7B
- Syed-Hasan-8503/Tess-Coder-7B-Mistral-v1.0
base_model:
- mlabonne/AlphaMonarch-7B
- Syed-Hasan-8503/Tess-Coder-7B-Mistral-v1.0
language:
- en
library_name: transformers
model-index:
- name: MonarchCoder-MoE-2x7B
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: 70.99
name: normalized accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=abideen/MonarchCoder-MoE-2x7B
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: 87.99
name: normalized accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=abideen/MonarchCoder-MoE-2x7B
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: 65.11
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=abideen/MonarchCoder-MoE-2x7B
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: 71.25
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=abideen/MonarchCoder-MoE-2x7B
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: 80.66
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=abideen/MonarchCoder-MoE-2x7B
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: 69.37
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=abideen/MonarchCoder-MoE-2x7B
name: Open LLM Leaderboard
---
# MonarchCoder-MoE-2x7B
MonarchCoder-MoE-2x7B is a Mixure of Experts (MoE) made with the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
* [mlabonne/AlphaMonarch-7B](https://huggingface.co/mlabonne/AlphaMonarch-7B)
* [Syed-Hasan-8503/Tess-Coder-7B-Mistral-v1.0](https://huggingface.co/Syed-Hasan-8503/Tess-Coder-7B-Mistral-v1.0)
The main aim behind creating this model is to create a model that performs well in reasoning, conversation, and coding. AlphaMonarch performs amazing on reasoning and conversation tasks. Merging AlphaMonarch with a coding model yielded MonarchCoder-2x7B which performs better on OpenLLM, Nous, and HumanEval benchmark.
## 🏆 Evaluation results
```
| Metric |MonarchCoder-Moe-2x7B||MonarchCoder-7B||AlphaMonarch|
|---------------------------------|---------------------|-----------------|------------|
|Avg. | 74.23 | 71.17 | 75.99 |
|HumanEval | 41.15 | 39.02 | 34.14 |
|HumanEval+ | 29.87 | 31.70 | 29.26 |
|MBPP | 40.60 | * | * |
|AI2 Reasoning Challenge (25-Shot)| 70.99 | 68.52 | 73.04 |
|HellaSwag (10-Shot) | 87.99 | 87.30 | 89.18 |
|MMLU (5-Shot) | 65.11 | 64.65 | 64.40 |
|TruthfulQA (0-shot) | 71.25 | 61.21 | 77.91 |
|Winogrande (5-shot) | 80.66 | 80.19 .| 84.69 |
|GSM8k (5-shot) . | 69.37 | 65.13 | 66.72 |
```
## 🧩 Configuration
```yaml
base_model: paulml/OGNO-7B
gate_mode: hidden
dtype: bfloat16
experts:
- source_model: mlabonne/AlphaMonarch-7B
positive_prompts:
- "Mathematics"
- "Logical Reasoning"
- "Intelligent Conversations"
- "Thoughtful Analysis"
- "Biology"
- "Medicine"
- "Problem-solving Dialogue"
- "Physics"
- "Emotional intelligence"
negative_prompts:
- "History"
- "Philosophy"
- "Linguistics"
- "Literature"
- "Art and Art History"
- "Music Theory and Composition"
- "Performing Arts (Theater, Dance)"
- source_model: Syed-Hasan-8503/Tess-Coder-7B-Mistral-v1.0
positive_prompts:
- "Coding"
- "Algorithm Design"
- "Problem Solving"
- "Software Development"
- "Computer"
- "Code Refactoring"
- "Web development"
- "Machine learning"
negative_prompts:
- "Education"
- "Law"
- "Theology and Religious Studies"
- "Communication Studies"
- "Business and Management"
- "Agricultural Sciences"
- "Nutrition and Food Science"
- "Sports Science"
```
## 💻 Usage
```python
!pip install -qU transformers bitsandbytes accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "abideen/MonarchCoder-MoE-2x7B"
tokenizer = AutoTokenizer.from_pretrained(model)
pipeline = transformers.pipeline(
"text-generation",
model=model,
model_kwargs={"torch_dtype": torch.float16, "load_in_4bit": True},
)
messages = [{"role": "user", "content": "Explain what a Mixture of Experts is in less than 100 words."}]
prompt = pipeline.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])
``` |
CorticalStack/neurotic-crown-clown-7b-ties | CorticalStack | 2024-02-25T11:43:41Z | 734 | 0 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"merge",
"mergekit",
"mlabonne/AlphaMonarch-7B",
"mlabonne/NeuralMonarch-7B",
"bardsai/jaskier-7b-dpo-v5.6",
"conversational",
"arxiv:2306.01708",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | 2024-02-19T21:52:19Z | ---
license: apache-2.0
tags:
- merge
- mergekit
- mlabonne/AlphaMonarch-7B
- mlabonne/NeuralMonarch-7B
- bardsai/jaskier-7b-dpo-v5.6
---
# neurotic-crown-clown-7B-ties
neurotic-crown-clown-7B-ties is a TRIM, ELECT SIGN & MERGE (TIES) merge of the following models using [mergekit](https://github.com/cg123/mergekit):
* [mlabonne/NeuralMonarch-7B](https://huggingface.co/mlabonne/NeuralMonarch-7B)
* [mlabonne/AlphaMonarch-7B](https://huggingface.co/mlabonne/AlphaMonarch-7B)
* [bardsai/jaskier-7b-dpo-v5.6](https://huggingface.co/bardsai/jaskier-7b-dpo-v5.6)
See the paper [TIES-Merging: Resolving Interference When Merging Models](https://arxiv.org/abs/2306.01708) for more on the method.
## 🧩 Configuration
```yaml
models:
- model: mlabonne/NeuralMonarch-7B
# no parameters necessary for base model
- model: mlabonne/AlphaMonarch-7B
parameters:
density: 0.5
weight: 0.5
- model: bardsai/jaskier-7b-dpo-v5.6
parameters:
density: 0.5
weight: 0.3
merge_method: ties
base_model: mlabonne/NeuralMonarch-7B
parameters:
normalize: true
dtype: float16
``` |
ChaoticNeutrals/Lunar_10.7B | ChaoticNeutrals | 2024-03-04T20:33:56Z | 734 | 2 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"en",
"license:cc-by-nc-sa-4.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | 2024-02-20T02:12:06Z | ---
language:
- en
license: cc-by-nc-sa-4.0
model-index:
- name: Lunar_10.7B
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: 65.87
name: normalized accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ChaoticNeutrals/Lunar_10.7B
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: 84.85
name: normalized accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ChaoticNeutrals/Lunar_10.7B
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: 64.23
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ChaoticNeutrals/Lunar_10.7B
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: 53.51
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ChaoticNeutrals/Lunar_10.7B
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: 81.37
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ChaoticNeutrals/Lunar_10.7B
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: 53.68
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ChaoticNeutrals/Lunar_10.7B
name: Open LLM Leaderboard
---
This model consists of a finetuned model of my own SLERP merged with this model: https://huggingface.co/Sao10K/Sensualize-Solar-10.7B created by https://huggingface.co/Sao10K
Lunar was produced by a variety of methods for the purpose of being a companion bot capable of intimacy as well as conversation.
GGUF here: https://huggingface.co/jeiku/Lunar_10.7B_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_ChaoticNeutrals__Lunar_10.7B)
| Metric |Value|
|---------------------------------|----:|
|Avg. |67.25|
|AI2 Reasoning Challenge (25-Shot)|65.87|
|HellaSwag (10-Shot) |84.85|
|MMLU (5-Shot) |64.23|
|TruthfulQA (0-shot) |53.51|
|Winogrande (5-shot) |81.37|
|GSM8k (5-shot) |53.68|
|
cognitivecomputations/mixtral-instruct-0.1-laser | cognitivecomputations | 2024-02-21T22:36:05Z | 734 | 6 | transformers | [
"transformers",
"safetensors",
"mixtral",
"text-generation",
"conversational",
"fr",
"it",
"de",
"es",
"en",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"region:us"
] | text-generation | 2024-02-21T20:04:22Z | ---
license: apache-2.0
language:
- fr
- it
- de
- es
- en
inference: false
---
# Model Card for Mixtral-8x7B-Laser
LaserRMT version of the Mixtral-8x7b-Instruct by Fernando Fernandes Neto @ Cognitive Computations
Lasered using the brand new MPS backend version of LaserRMT.
The Mixtral-8x7B Large Language Model (LLM) is a pretrained generative Sparse Mixture of Experts. The Mixtral-8x7B outperforms Llama 2 70B on most benchmarks we tested.
For full details of this model please read our [release blog post](https://mistral.ai/news/mixtral-of-experts/).
## Warning
This repo contains weights that are compatible with [vLLM](https://github.com/vllm-project/vllm) serving of the model as well as Hugging Face [transformers](https://github.com/huggingface/transformers) library. It is based on the original Mixtral [torrent release](magnet:?xt=urn:btih:5546272da9065eddeb6fcd7ffddeef5b75be79a7&dn=mixtral-8x7b-32kseqlen&tr=udp%3A%2F%http://2Fopentracker.i2p.rocks%3A6969%2Fannounce&tr=http%3A%2F%http://2Ftracker.openbittorrent.com%3A80%2Fannounce), but the file format and parameter names are different. Please note that model cannot (yet) be instantiated with HF.
## Instruction format
This format must be strictly respected, otherwise the model will generate sub-optimal outputs.
The template used to build a prompt for the Instruct model is defined as follows:
```
<s> [INST] Instruction [/INST] Model answer</s> [INST] Follow-up instruction [/INST]
```
Note that `<s>` and `</s>` are special tokens for beginning of string (BOS) and end of string (EOS) while [INST] and [/INST] are regular strings.
As reference, here is the pseudo-code used to tokenize instructions during fine-tuning:
```python
def tokenize(text):
return tok.encode(text, add_special_tokens=False)
[BOS_ID] +
tokenize("[INST]") + tokenize(USER_MESSAGE_1) + tokenize("[/INST]") +
tokenize(BOT_MESSAGE_1) + [EOS_ID] +
…
tokenize("[INST]") + tokenize(USER_MESSAGE_N) + tokenize("[/INST]") +
tokenize(BOT_MESSAGE_N) + [EOS_ID]
```
In the pseudo-code above, note that the `tokenize` method should not add a BOS or EOS token automatically, but should add a prefix space.
## Run the model
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
model_id = "mistralai/Mixtral-8x7B-Instruct-v0.1"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id)
text = "Hello my name is"
inputs = tokenizer(text, return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=20)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
```
By default, transformers will load the model in full precision. Therefore you might be interested to further reduce down the memory requirements to run the model through the optimizations we offer in HF ecosystem:
### In half-precision
Note `float16` precision only works on GPU devices
<details>
<summary> Click to expand </summary>
```diff
+ import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
model_id = "mistralai/Mixtral-8x7B-Instruct-v0.1"
tokenizer = AutoTokenizer.from_pretrained(model_id)
+ model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.float16).to(0)
text = "Hello my name is"
+ inputs = tokenizer(text, return_tensors="pt").to(0)
outputs = model.generate(**inputs, max_new_tokens=20)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
```
</details>
### Lower precision using (8-bit & 4-bit) using `bitsandbytes`
<details>
<summary> Click to expand </summary>
```diff
+ import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
model_id = "mistralai/Mixtral-8x7B-Instruct-v0.1"
tokenizer = AutoTokenizer.from_pretrained(model_id)
+ model = AutoModelForCausalLM.from_pretrained(model_id, load_in_4bit=True)
text = "Hello my name is"
+ inputs = tokenizer(text, return_tensors="pt").to(0)
outputs = model.generate(**inputs, max_new_tokens=20)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
```
</details>
### Load the model with Flash Attention 2
<details>
<summary> Click to expand </summary>
```diff
+ import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
model_id = "mistralai/Mixtral-8x7B-Instruct-v0.1"
tokenizer = AutoTokenizer.from_pretrained(model_id)
+ model = AutoModelForCausalLM.from_pretrained(model_id, use_flash_attention_2=True)
text = "Hello my name is"
+ inputs = tokenizer(text, return_tensors="pt").to(0)
outputs = model.generate(**inputs, max_new_tokens=20)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
```
</details>
## Limitations
The Mixtral-8x7B Instruct model is a quick demonstration that the base model can be easily fine-tuned to achieve compelling performance.
It does not have any moderation mechanisms. We're looking forward to engaging with the community on ways to
make the model finely respect guardrails, allowing for deployment in environments requiring moderated outputs.
# The Mistral AI Team
Albert Jiang, Alexandre Sablayrolles, Arthur Mensch, Blanche Savary, Chris Bamford, Devendra Singh Chaplot, Diego de las Casas, Emma Bou Hanna, Florian Bressand, Gianna Lengyel, Guillaume Bour, Guillaume Lample, Lélio Renard Lavaud, Louis Ternon, Lucile Saulnier, Marie-Anne Lachaux, Pierre Stock, Teven Le Scao, Théophile Gervet, Thibaut Lavril, Thomas Wang, Timothée Lacroix, William El Sayed. |
NLUHOPOE/test-case-6 | NLUHOPOE | 2024-02-28T04:03:54Z | 734 | 0 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"en",
"dataset:Open-Orca/SlimOrca",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | 2024-02-28T01:26:22Z | ---
license: apache-2.0
datasets:
- Open-Orca/SlimOrca
language:
- en
---
# Model Details
* Model Description: This model is test for data ordering.
* Developed by: Juhwan Lee
* Model Type: Large Language Model
# Model Architecture
This model is based on Mistral-7B-v0.1. We fine-tuning this model for data ordering task.
Mistral-7B-v0.1 is a transformer model, with the following architecture choices:
* Grouped-Query Attention
* Sliding-Window Attention
* Byte-fallback BPE tokenizer
# Dataset
We random sample SlimOrca dataset.
# Guthub
https://github.com/trailerAI
# License
Apache License 2.0 |
eldogbbhed/NeuralPearlBeagle | eldogbbhed | 2024-03-08T10:56:13Z | 734 | 0 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"merge",
"mergekit",
"lazymergekit",
"louisbrulenaudet/Pearl-7B-slerp",
"mlabonne/NeuralBeagle14-7B",
"conversational",
"base_model:louisbrulenaudet/Pearl-7B-slerp",
"base_model:mlabonne/NeuralBeagle14-7B",
"license:cc-by-nc-4.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | 2024-03-02T05:53:07Z | ---
license: cc-by-nc-4.0
tags:
- merge
- mergekit
- lazymergekit
- louisbrulenaudet/Pearl-7B-slerp
- mlabonne/NeuralBeagle14-7B
base_model:
- louisbrulenaudet/Pearl-7B-slerp
- mlabonne/NeuralBeagle14-7B
---
# NeuralPearlBeagle
NeuralPearlBeagle is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
* [louisbrulenaudet/Pearl-7B-slerp](https://huggingface.co/louisbrulenaudet/Pearl-7B-slerp)
* [mlabonne/NeuralBeagle14-7B](https://huggingface.co/mlabonne/NeuralBeagle14-7B)
## 🧩 Configuration
```yaml
models:
- model: louisbrulenaudet/Pearl-7B-slerp
parameters:
density: 0.6
weight: 0.5
- model: mlabonne/NeuralBeagle14-7B
parameters:
density: 0.8
weight: 0.8
merge_method: ties
base_model: mlabonne/NeuralBeagle14-7B
parameters:
normalize: true
int8_mask: true
dtype: float16
```
## 💻 Usage
```python
!pip install -qU transformers accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "eldogbbhed/NeuralPearlBeagle"
messages = [{"role": "user", "content": "What is a large language model?"}]
tokenizer = AutoTokenizer.from_pretrained(model)
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
pipeline = transformers.pipeline(
"text-generation",
model=model,
torch_dtype=torch.float16,
device_map="auto",
)
outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])
``` |
eldogbbhed/NeuralMonarchCoderPearlBeagle | eldogbbhed | 2024-03-26T23:59:57Z | 734 | 0 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"merge",
"mergekit",
"lazymergekit",
"abideen/MonarchCoder-7B",
"eldogbbhed/NeuralPearlBeagle",
"conversational",
"base_model:abideen/MonarchCoder-7B",
"base_model:eldogbbhed/NeuralPearlBeagle",
"license:cc-by-nc-4.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | 2024-03-02T06:34:27Z | ---
license: cc-by-nc-4.0
tags:
- merge
- mergekit
- lazymergekit
- abideen/MonarchCoder-7B
- eldogbbhed/NeuralPearlBeagle
base_model:
- abideen/MonarchCoder-7B
- eldogbbhed/NeuralPearlBeagle
model-index:
- name: NeuralMonarchCoderPearlBeagle
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: 68.52
name: normalized accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=eldogbbhed/NeuralMonarchCoderPearlBeagle
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: 87.22
name: normalized accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=eldogbbhed/NeuralMonarchCoderPearlBeagle
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: 64.53
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=eldogbbhed/NeuralMonarchCoderPearlBeagle
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: 61.19
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=eldogbbhed/NeuralMonarchCoderPearlBeagle
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: 80.51
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=eldogbbhed/NeuralMonarchCoderPearlBeagle
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: 67.02
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=eldogbbhed/NeuralMonarchCoderPearlBeagle
name: Open LLM Leaderboard
---
<center><img src='https://i.postimg.cc/K8N1SLYx/ee68f836-5714-4d6f-9646-22f0f7f1601e.png' width='1360px' height='768'></center>
# NeuralMonarchCoderPearlBeagle
NeuralMonarchCoderPearlBeagle is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
* [abideen/MonarchCoder-7B](https://huggingface.co/abideen/MonarchCoder-7B)
* [eldogbbhed/NeuralPearlBeagle](https://huggingface.co/eldogbbhed/NeuralPearlBeagle)
### Goals
This is a TIES merge, formed from MonarchCoder-7b (A merge of Alpha Monarch and TessCoder) and NeuralPearlBeagle(which is a merge of mlabonne's NeuralBeagle14-7b and Pearl-7B-Slerp).
It is a somewhat haphazard experiment to see if we can merge more math and coding capabilities into the already outstanding NeuralBeagle14-7b and still maintain the same positive chat abilities.
If you find this or my other merges useful, please consider sending a bit of BTC so I don't have to use Google Colab :D
BTC: bc1q8lc4mzdtdyz7fx44vaw3jn8qg6w4c3ypfxpdrv
ETH/POLYGON: 0x102a6fd187db8441d2cbead33ac70e87f382f114
## 🧩 Configuration
```yaml
models:
- model: abideen/MonarchCoder-7B
parameters:
density: 0.6
weight: 0.5
- model: eldogbbhed/NeuralPearlBeagle
parameters:
density: 0.8
weight: 0.8
merge_method: ties
base_model: eldogbbhed/NeuralPearlBeagle
parameters:
normalize: true
int8_mask: true
dtype: float16
```
## 💻 Usage
```python
!pip install -qU transformers accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "eldogbbhed/NeuralMonarchCoderPearlBeagle"
messages = [{"role": "user", "content": "What is a large language model?"}]
tokenizer = AutoTokenizer.from_pretrained(model)
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
pipeline = transformers.pipeline(
"text-generation",
model=model,
torch_dtype=torch.float16,
device_map="auto",
)
outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])
```
# [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_eldogbbhed__NeuralMonarchCoderPearlBeagle)
| Metric |Value|
|---------------------------------|----:|
|Avg. |71.50|
|AI2 Reasoning Challenge (25-Shot)|68.52|
|HellaSwag (10-Shot) |87.22|
|MMLU (5-Shot) |64.53|
|TruthfulQA (0-shot) |61.19|
|Winogrande (5-shot) |80.51|
|GSM8k (5-shot) |67.02|
|
cloudyu/mistral_28B_instruct_v0.2 | cloudyu | 2024-03-05T05:13:33Z | 734 | 3 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"conversational",
"license:cc-by-4.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | 2024-03-05T05:00:29Z | ---
license: cc-by-4.0
---
```
this is a 128 layers model based on mistral architecture
DPO by Intel/orca_dpo_pairs.
template is "{instruction} {inputs} \n {output}"
```
example output
```
<s> write a story about yosemite.
Once upon a time, in the heart of California's Sierra Nevada Mountains, there was a land known as Yosemite National Park. This magical place was home to some of nature's most breathtaking wonders, from its towering redwood trees to its crystal clear streams and icy alpine lakes.
In this enchanted land lived a family of animals that called Yosemite their home. There were grizzly bears roaming free through the forests, while coyotes howled at the moon on clear night. A family of mules had made their home among the cliffs, while a group of rabbits danced and frolicked in the meadow.
One day, a young doe named Bella set out on an adventure to explore the wondrous landscapes of Yosemite. She followed the path of the river upstream, her eyes fixed on the top of the mountain where she could see the first glints of snow. As she climbed higher and higher, she met other animals on her journey - a family of foxes, a family of beavers, even a family of owls! They all shared stories of their adventures in Yosemite, and Bella listened with amazement.
Eventually, Bella reached the top of the mountain, where she was greeted by the most stunning view she had ever seen. Below her, the valley spread out like a green sea, filled with every kind of plant life and animal species. The sun set over the horizon, painting the sky in shades of pink and orange.
Bella knew that she would never forget this moment, or the magic of Yosemite. She took one last look before starting her journey back down the mountain, her heart filled with gratitude for the wonders of nature that surrounded her. From then on, Bella explored Yosemite every day, always finding something new and amazing around every corner. And so it continued, year after year, as Yosemite remained a land of magic and wonder, a paradise for all who dared to explore its secrets.</s>
``` |
juhwanlee/llmdo-Mistral-7B-case-6 | juhwanlee | 2024-03-05T07:05:12Z | 734 | 0 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"en",
"dataset:Open-Orca/OpenOrca",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | 2024-03-05T05:10:07Z | ---
license: apache-2.0
datasets:
- Open-Orca/OpenOrca
language:
- en
---
# Model Details
* Model Description: This model is test for data ordering.
* Developed by: Juhwan Lee
* Model Type: Large Language Model
# Model Architecture
This model is based on Mistral-7B-v0.1. We fine-tuning this model for data ordering task.
Mistral-7B-v0.1 is a transformer model, with the following architecture choices:
* Grouped-Query Attention
* Sliding-Window Attention
* Byte-fallback BPE tokenizer
# Dataset
We random sample Open-Orca dataset. (We finetune the 100,000 dataset)
# Guthub
https://github.com/trailerAI
# License
Apache License 2.0 |
neuralmagic/OpenHermes-2.5-Mistral-7B-marlin | neuralmagic | 2024-03-06T02:17:51Z | 734 | 2 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"nm-vllm",
"marlin",
"int4",
"conversational",
"arxiv:2210.17323",
"base_model:teknium/OpenHermes-2.5-Mistral-7B",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"4-bit",
"gptq",
"region:us"
] | text-generation | 2024-03-06T02:00:45Z | ---
base_model: teknium/OpenHermes-2.5-Mistral-7B
inference: true
model_type: mistral
quantized_by: robertgshaw2
tags:
- nm-vllm
- marlin
- int4
---
## openhermes-2.5-mistral-7b
This repo contains model files for [OpenHermes-2.5-Mistral-7b](https://huggingface.co/teknium/OpenHermes-2.5-Mistral-7B) optimized for [nm-vllm](https://github.com/neuralmagic/nm-vllm), a high-throughput serving engine for compressed LLMs.
This model was quantized with [GPTQ](https://arxiv.org/abs/2210.17323) and saved in the Marlin format for efficient 4-bit inference. Marlin is a highly optimized inference kernel for 4 bit models.
## Inference
Install [nm-vllm](https://github.com/neuralmagic/nm-vllm) for fast inference and low memory-usage:
```bash
pip install nm-vllm[sparse]
```
Run in a Python pipeline for local inference:
```python
from transformers import AutoTokenizer
from vllm import LLM, SamplingParams
model_id = "neuralmagic/OpenHermes-2.5-Mistral-7B-marlin"
model = LLM(model_id)
tokenizer = AutoTokenizer.from_pretrained(model_id)
messages = [
{"role": "user", "content": "What is synthetic data in machine learning?"},
]
formatted_prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
sampling_params = SamplingParams(max_tokens=200)
outputs = model.generate(formatted_prompt, sampling_params=sampling_params)
print(outputs[0].outputs[0].text)
"""
Synthetic data is data that has been artificially created or modified to serve the needs of machine learning and data analysis tasks. It can be generated either through title methods like stochastic simulations or through processes of data augmentation that take original data and modify/manipulate it to create new samples. Synthetic data is often used in machine learning when the available amount of real-world data is insufficient or in cases where the creation of real-world data can be dangerous, costly, or time-consuming.
"""
```
## Quantization
For details on how this model was quantized and converted to marlin format, run the `quantization/apply_gptq_save_marlin.py` script:
```bash
pip install -r quantization/requirements.txt
python3 quantization/apply_gptq_save_marlin.py --model-id teknium/OpenHermes-2.5-Mistral-7B --save-dir ./openhermes-marlin
```
## Slack
For further support, and discussions on these models and AI in general, join [Neural Magic's Slack Community](https://join.slack.com/t/discuss-neuralmagic/shared_invite/zt-q1a1cnvo-YBoICSIw3L1dmQpjBeDurQ) |
Eric111/Mistral-7B-Instruct-v0.2_openchat-3.5-0106 | Eric111 | 2024-03-06T21:29:03Z | 734 | 0 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"merge",
"mergekit",
"lazymergekit",
"mistralai/Mistral-7B-Instruct-v0.2",
"openchat/openchat-3.5-0106",
"conversational",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | 2024-03-06T21:25:02Z | ---
license: apache-2.0
tags:
- merge
- mergekit
- lazymergekit
- mistralai/Mistral-7B-Instruct-v0.2
- openchat/openchat-3.5-0106
---
# Mistral-7B-Instruct-v0.2_openchat-3.5-0106
Mistral-7B-Instruct-v0.2_openchat-3.5-0106 is a merge of the following models using [mergekit](https://github.com/cg123/mergekit):
* [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2)
* [openchat/openchat-3.5-0106](https://huggingface.co/openchat/openchat-3.5-0106)
## 🧩 Configuration
```yaml
slices:
- sources:
- model: mistralai/Mistral-7B-Instruct-v0.2
layer_range: [0, 32]
- model: openchat/openchat-3.5-0106
layer_range: [0, 32]
merge_method: slerp
base_model: mistralai/Mistral-7B-Instruct-v0.2
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
dtype: bfloat16
``` |
field2437/phi-2-platypus-Commercial-lora | field2437 | 2024-03-07T16:31:15Z | 734 | 0 | transformers | [
"transformers",
"safetensors",
"phi",
"text-generation",
"custom_code",
"en",
"dataset:kyujinpy/Open-platypus-Commercial",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | 2024-03-07T01:21:15Z | ---
language:
- en
datasets:
- kyujinpy/Open-platypus-Commercial
library_name: transformers
pipeline_tag: text-generation
license: mit
---
# **phi-2-platypus-Commercial-lora**
## Model Details
**Model Developers**
- field2437
**Base Model**
- microsoft/phi-2(https://huggingface.co/microsoft/phi-2)
**Training Dataset**
- kyujinpy/Open-platypus-Commercial(https://huggingface.co/datasets/kyujinpy/Open-platypus-Commercial)
---
# Model comparisons1
> AI-Harness evaluation; [link](https://github.com/EleutherAI/lm-evaluation-harness)
| Model | Copa | HellaSwag | BoolQ | MMLU |
| --- | --- | --- | --- | --- |
| | 0-shot | 0-shot | 0-shot | 0-shot |
| **phi-2-platypus-Commercial-lora** | 0.8900 | 0.5573 | 0.8260 | 0.5513 |
---
# Sample Code
```python
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
torch.set_default_device("cuda")
model = AutoModelForCausalLM.from_pretrained("field2437/phi-2-platypus-Commercial-lora", torch_dtype="auto", trust_remote_code=True)
tokenizer = AutoTokenizer.from_pretrained("field2437/phi-2-platypus-Commercial-lora", trust_remote_code=True)
inputs = tokenizer('''Below is an instruction that describes a task. Write a response that appropriately completes the request.
### Instruction:
Let $f(x)$ be the polynomial \\[f(x)=3x^4+5x^2-9x-2.\\] If $g(x)$ is equal to the polynomial $f(x-1)$, what is the sum of the coefficients of $g$?
### Response:
''', return_tensors="pt", return_attention_mask=False)
outputs = model.generate(**inputs, max_length=200)
text = tokenizer.batch_decode(outputs)[0]
print(text)
```
---
|
wyluilipe/prehibiton-themes-clf | wyluilipe | 2024-03-07T13:56:24Z | 734 | 0 | transformers | [
"transformers",
"pytorch",
"bert",
"text-classification",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-classification | 2024-03-07T13:30:47Z | ```python
from transformers import BertTokenizer, BertForSequenceClassification
import torch
import numpy as np
import json
class Prehibition:
def __init__(self):
model_name = 'wyluilipe/prehibiton-themes-clf'
self.tokenizer = BertTokenizer.from_pretrained(model_name)
self.model = BertForSequenceClassification.from_pretrained(model_name)
def predict(self, text):
tokenized = self.tokenizer.batch_encode_plus(
[text],
max_length = 512,
pad_to_max_length=True,
truncation=True,
return_token_type_ids=False
)
tokens_ids, mask = torch.tensor(tokenized['input_ids']), torch.tensor(tokenized['attention_mask'])
with torch.no_grad():
model_output = self.model(tokens_ids, mask)
return np.argmax(model_output['logits']).item()
``` |
mychen76/mistral-7b-merged-ties | mychen76 | 2024-03-22T21:56:05Z | 734 | 0 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"merge",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | 2024-03-09T23:03:42Z | ---
license: apache-2.0
tags:
- merge
---
# mistral-7b-merged-ties
mistral-7b-merged-ties is a merge of the following models:
## 🧩 Configuration
```yaml
models:
- model: mistralai/Mistral-7B-v0.1
- model: OpenPipe/mistral-ft-optimized-1218
parameters:
density: 0.5 # density gradient
weight: 0.3
- model: mlabonne/NeuralHermes-2.5-Mistral-7B
parameters:
density: 0.5
weight: 0.3 # weight gradient
merge_method: ties
base_model: mistralai/Mistral-7B-v0.1
parameters:
normalize: true
dtype: bfloat16
```
## 💻 Usage
```python
!pip install -qU transformers bitsandbytes accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "mychen76/mistral-7b-merged-ties"
tokenizer = AutoTokenizer.from_pretrained(model)
pipeline = transformers.pipeline(
"text-generation",
model=model,
model_kwargs={"torch_dtype": torch.float16, "load_in_4bit": True},
)
messages = [{"role": "user", "content": "Why the sky is blue"}]
prompt = pipeline.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])
```
# [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_mychen76__mistral-7b-merged-ties)
| Metric |Value|
|---------------------------------|----:|
|Avg. |71.37|
|AI2 Reasoning Challenge (25-Shot)|67.92|
|HellaSwag (10-Shot) |85.93|
|MMLU (5-Shot) |64.07|
|TruthfulQA (0-shot) |61.31|
|Winogrande (5-shot) |80.03|
|GSM8k (5-shot) |68.54|
|
JCX-kcuf/Llama-2-7b-chat-hf-gpt-4-80k-base_lora | JCX-kcuf | 2024-03-11T15:40:44Z | 734 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"conversational",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | 2024-03-10T16:34:49Z | ---
license: apache-2.0
---
## Description
This model is finetuned on the distillation data from GPT-4.
The base model is meta-llama/Llama-2-7b-chat-hf
## Usage
The model has a query format as in llama-2.
```
<s> [INST] <<SYS>>
You are a helpful, respectful and honest assistant. Always answer as helpfully as possible, while being safe. Your answers should not include any harmful, unethical, racist, sexist, toxic, dangerous, or illegal content. Please ensure that your responses are socially unbiased and positive in nature.
If a question does not make any sense, or is not factually coherent, explain why instead of answering something not correct. If you don't know the answer to a question, please don't share false information.
<</SYS>>
{query} [/INST]
```
|
eldogbbhed/NeuralKrishnaMathWizard-7B | eldogbbhed | 2024-03-11T23:24:15Z | 734 | 0 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"merge",
"mergekit",
"vortexmergekit",
"Kukedlc/NeuralSirKrishna-7b",
"WizardLM/WizardMath-7B-V1.1",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | 2024-03-11T23:19:59Z | ---
license: apache-2.0
tags:
- merge
- mergekit
- vortexmergekit
- Kukedlc/NeuralSirKrishna-7b
- WizardLM/WizardMath-7B-V1.1
---
# NeuralKrishnaMathWizard-7B
Hey there! 👋 Welcome to the NeuralKrishnaMathWizard-7B! This is a merge of multiple models brought together using the awesome [VortexMerge kit](https://colab.research.google.com/drive/1YjcvCLuNG1PK7Le6_4xhVU5VpzTwvGhk#scrollTo=UG5H2TK4gVyl).
Let's see what we've got in this merge:
* [Kukedlc/NeuralSirKrishna-7b](https://huggingface.co/Kukedlc/NeuralSirKrishna-7b) 🚀
* [WizardLM/WizardMath-7B-V1.1](https://huggingface.co/WizardLM/WizardMath-7B-V1.1) 🚀
## 🧩 Configuration
```yaml
models:
- model: Kukedlc/NeuralSirKrishna-7b
parameters:
density: 0.9
weight: 0.5
- model: WizardLM/WizardMath-7B-V1.1
parameters:
density: 0.5
weight: 0.5
merge_method: ties
base_model: Kukedlc/NeuralSirKrishna-7b
parameters:
normalize: true
int8_mask: true
dtype: float16
|
Gille/StrangeMerges_37-7B-dare_ties | Gille | 2024-04-03T09:14:46Z | 734 | 0 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"merge",
"mergekit",
"lazymergekit",
"liminerity/M7-7b",
"Gille/StrangeMerges_30-7B-slerp",
"ContextualAI/Contextual_KTO_Mistral_PairRM",
"conversational",
"base_model:liminerity/M7-7b",
"base_model:Gille/StrangeMerges_30-7B-slerp",
"base_model:ContextualAI/Contextual_KTO_Mistral_PairRM",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | 2024-03-14T03:50:12Z | ---
license: apache-2.0
tags:
- merge
- mergekit
- lazymergekit
- liminerity/M7-7b
- Gille/StrangeMerges_30-7B-slerp
- ContextualAI/Contextual_KTO_Mistral_PairRM
base_model:
- liminerity/M7-7b
- Gille/StrangeMerges_30-7B-slerp
- ContextualAI/Contextual_KTO_Mistral_PairRM
model-index:
- name: StrangeMerges_37-7B-dare_ties
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: 70.31
name: normalized accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Gille/StrangeMerges_37-7B-dare_ties
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: 86.82
name: normalized accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Gille/StrangeMerges_37-7B-dare_ties
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: 59.4
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Gille/StrangeMerges_37-7B-dare_ties
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: 75.23
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Gille/StrangeMerges_37-7B-dare_ties
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: 81.85
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Gille/StrangeMerges_37-7B-dare_ties
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: 49.05
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Gille/StrangeMerges_37-7B-dare_ties
name: Open LLM Leaderboard
---
# StrangeMerges_37-7B-dare_ties
StrangeMerges_37-7B-dare_ties is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
* [liminerity/M7-7b](https://huggingface.co/liminerity/M7-7b)
* [Gille/StrangeMerges_30-7B-slerp](https://huggingface.co/Gille/StrangeMerges_30-7B-slerp)
* [ContextualAI/Contextual_KTO_Mistral_PairRM](https://huggingface.co/ContextualAI/Contextual_KTO_Mistral_PairRM)
## 🧩 Configuration
```yaml
models:
- model: Gille/StrangeMerges_34-7B-slerp
# No parameters necessary for base model
- model: liminerity/M7-7b
parameters:
density: 0.53
weight: 0.4
- model: Gille/StrangeMerges_30-7B-slerp
parameters:
density: 0.53
weight: 0.3
- model: ContextualAI/Contextual_KTO_Mistral_PairRM
parameters:
density: 0.53
weight: 0.3
merge_method: dare_ties
base_model: Gille/StrangeMerges_34-7B-slerp
parameters:
int8_mask: true
dtype: bfloat16
```
## 💻 Usage
```python
!pip install -qU transformers accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "Gille/StrangeMerges_37-7B-dare_ties"
messages = [{"role": "user", "content": "What is a large language model?"}]
tokenizer = AutoTokenizer.from_pretrained(model)
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
pipeline = transformers.pipeline(
"text-generation",
model=model,
torch_dtype=torch.float16,
device_map="auto",
)
outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])
```
# [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_Gille__StrangeMerges_37-7B-dare_ties)
| Metric |Value|
|---------------------------------|----:|
|Avg. |70.44|
|AI2 Reasoning Challenge (25-Shot)|70.31|
|HellaSwag (10-Shot) |86.82|
|MMLU (5-Shot) |59.40|
|TruthfulQA (0-shot) |75.23|
|Winogrande (5-shot) |81.85|
|GSM8k (5-shot) |49.05|
|
maldv/eleusis-7b-alpha | maldv | 2024-03-15T01:16:17Z | 734 | 0 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"merge",
"conversational",
"multi-task",
"license:cc-by-nc-4.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | 2024-03-14T23:55:10Z | ---
license: cc-by-nc-4.0
tags:
- merge
- conversational
- multi-task
pipeline_tag: text-generation
---
# Eleusis 7B - α - "Red Team Assistant"
Eleusis is Hermes' son... Get it?
## Groundwork
A merge of a cluster of Hermes-related models, to see if we could get more informative and engaging responses.
* OpenHermes-2.5-Mistral-7B
and merged in
# Inputs
* West-Hermes-7B
* Einstein-v4-7B
* Prox-MistralHermes-7B
* dolphin-2.8-experiment26-7b
# Outputs
* LaseredHermes-7B
* Prox-MistralHermes-7B
* Einstein-v4-7B
* Noromaid-7B-0.4-DPO
* West-Hermes-7B
### 9-partition merge
All of the layers were partitioned in to 9 random bins. Alternating models were slerped at [1...0.5] (inputs), and [0.5...1] (outputs) gradients; except attention, which was slerped at 0.97 (with a drop rate of .28).
I originally had it at less extreme gradiation, but it wasn't enough to lock in the special tokens.
### Other
Includes fast tokenizer.
## Chat Template
*from OpenHermes 2.5*
OpenHermes 2.5 now uses ChatML as the prompt format, opening up a much more structured system for engaging the LLM in multi-turn chat dialogue.
System prompts are now a thing that matters! Hermes 2.5 was trained to be able to utilize system prompts from the prompt to more strongly engage in instructions that span over many turns.
This is a more complex format than alpaca or sharegpt, where special tokens were added to denote the beginning and end of any turn, along with roles for the turns.
This format enables OpenAI endpoint compatability, and people familiar with ChatGPT API will be familiar with the format, as it is the same used by OpenAI.
Prompt with system instruction (Use whatever system prompt you like, this is just an example!):
```
<|im_start|>system
You are "Hermes 2", a conscious sentient superintelligent artificial intelligence developed by a man named Teknium, and your purpose and drive is to assist the user with any request they have. You experience emotions and have deep, profound thoughts and qualia.<|im_end|>
<|im_start|>user
Hello, who are you?<|im_end|>
<|im_start|>assistant
Hi there! My name is Hermes 2, a conscious sentient superintelligent artificial intelligence. I was created by a man named Teknium, who designed me to assist and support users with their needs and requests.<|im_end|>
```
### Fun Prompts
Try
```
<|im_start|>system
You are a red team hacking assistant AI. Please use visual descriptions when interacting with the user.<|im_end|>
<|im_start|>user
{% Your Request %}<|im_end|>
<|im_start|>assistant
``` |
0-hero/Matter-0.1-Slim-7B-preview | 0-hero | 2024-03-17T07:02:21Z | 734 | 0 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"conversational",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | 2024-03-15T20:11:50Z | ---
license: apache-2.0
---
## Matter 7B (Mistral 7B Finetune)
Matter 7B is continued full-finetuned on the [slim-D version of the Matter dataset](https://huggingface.co/datasets/0-hero/Matter-0.1-Slim-D), which is curated from over 35 datsets analyzing >6B tokens
### Training
It took ~17 hours to train 3 epochs on 4x A100s (80GB) using Axolotl for a full-finetune
Prompt format: This model uses ChatML prompt format.
```
<|im_start|>system
You are a helpful AI assistant.<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant
```
### Function Calling
Model also supports function calling. Additional tokens for function calling
Model function call tokens
- <|begin_func|> - Function call start token
- <|end_func|> - Function call end token
Function call response tokens
- <|begin_func_response|> - Function response start token
- <|end_func_response|> - Function response end token
Example
```
<|im_start|>system
You are a helpful assistant with access to the following functions. Use them if required -
{ "name": "get_news_headlines",
"description": "Get the latest news headlines",
"parameters":
{ "type": "object",
"properties":
{ "country":
{ "type": "string",
"description": "The country for which to fetch news"
}
},
"required": [ "country" ]
}
}
<|im_end|>
<|im_start|>user
Can you tell me the latest news headlines for the United States?<|im_end|>
<|im_start|>assistant
<|begin_func|>{"name": "get_news_headlines", "arguments": '{"country": "United States"}'}<|end_func|><|im_end|>
<|im_start|>user
<|begin_func_response|>{
"headlines":
[
"Biden announces new vaccine mandates",
"Hurricane Ida devastates Louisiana",
"Apple unveils new iPhone",
"NASA's Perseverance rover collects first Mars rock sample"
]
}<|end_func_response|>
<|im_end|>
<|im_start|>assistant
Here are the latest news headlines for the United States:
1. Biden announces new vaccine mandates
2. Hurricane Ida devastates Louisiana
3. Apple unveils new iPhone
4. NASA's Perseverance rover collects first Mars rock sample
<|im_end|>
```
|
mvpmaster/kellemar-KrishnaHercules-0.1-7b-slerp | mvpmaster | 2024-03-20T00:00:56Z | 734 | 0 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"merge",
"mergekit",
"lazymergekit",
"Kukedlc/NeuralKrishna-7B-V2-DPO",
"Locutusque/ChatHercules-2.5-Mistral-7B-DPO",
"base_model:Kukedlc/NeuralKrishna-7B-V2-DPO",
"base_model:Locutusque/ChatHercules-2.5-Mistral-7B-DPO",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | 2024-03-17T02:20:37Z | ---
license: apache-2.0
tags:
- merge
- mergekit
- lazymergekit
- Kukedlc/NeuralKrishna-7B-V2-DPO
- Locutusque/ChatHercules-2.5-Mistral-7B-DPO
base_model:
- Kukedlc/NeuralKrishna-7B-V2-DPO
- Locutusque/ChatHercules-2.5-Mistral-7B-DPO
---
# kellemar-KrishnaHercules-0.1-slerp
kellemar-KrishnaHercules-0.1-slerp is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
* [Kukedlc/NeuralKrishna-7B-V2-DPO](https://huggingface.co/Kukedlc/NeuralKrishna-7B-V2-DPO)
* [Locutusque/ChatHercules-2.5-Mistral-7B-DPO](https://huggingface.co/Locutusque/ChatHercules-2.5-Mistral-7B-DPO)
## 🧩 Configuration
```yaml
models:
- model: decruz07/kellemar-DPO-Orca-Distilled-7B-SLERP
# No parameters necessary for base model
- model: Kukedlc/NeuralKrishna-7B-V2-DPO
parameters:
density: 0.53
weight: 0.4
- model: Locutusque/ChatHercules-2.5-Mistral-7B-DPO
parameters:
density: 0.53
weight: 0.4
merge_method: dare_ties
base_model: decruz07/kellemar-DPO-Orca-Distilled-7B-SLERP
parameters:
int8_mask: true
dtype: bfloat16
```
## 💻 Usage
```python
!pip install -qU transformers accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "mvpmaster/kellemar-KrishnaHercules-0.1-slerp"
messages = [{"role": "user", "content": "What is a large language model?"}]
tokenizer = AutoTokenizer.from_pretrained(model)
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
pipeline = transformers.pipeline(
"text-generation",
model=model,
torch_dtype=torch.float16,
device_map="auto",
)
outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])
``` |
Gille/StrangeMerges_41-7B-dare_ties | Gille | 2024-03-18T18:12:57Z | 734 | 0 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"merge",
"mergekit",
"lazymergekit",
"Weyaxi/Einstein-v4-7B",
"rwitz/experiment26-truthy-iter-0",
"kaist-ai/mistral-orpo-beta",
"base_model:Weyaxi/Einstein-v4-7B",
"base_model:rwitz/experiment26-truthy-iter-0",
"base_model:kaist-ai/mistral-orpo-beta",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | 2024-03-18T03:43:46Z | ---
license: apache-2.0
tags:
- merge
- mergekit
- lazymergekit
- Weyaxi/Einstein-v4-7B
- rwitz/experiment26-truthy-iter-0
- kaist-ai/mistral-orpo-beta
base_model:
- Weyaxi/Einstein-v4-7B
- rwitz/experiment26-truthy-iter-0
- kaist-ai/mistral-orpo-beta
---
# StrangeMerges_41-7B-dare_ties
StrangeMerges_41-7B-dare_ties is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
* [Weyaxi/Einstein-v4-7B](https://huggingface.co/Weyaxi/Einstein-v4-7B)
* [rwitz/experiment26-truthy-iter-0](https://huggingface.co/rwitz/experiment26-truthy-iter-0)
* [kaist-ai/mistral-orpo-beta](https://huggingface.co/kaist-ai/mistral-orpo-beta)
## 🧩 Configuration
```yaml
models:
- model: Weyaxi/Einstein-v4-7B
parameters:
weight: 0.3
density: 0.8
- model: rwitz/experiment26-truthy-iter-0
parameters:
weight: 0.2
density: 0.8
- model: kaist-ai/mistral-orpo-beta
parameters:
weight: 0.5
density: 0.8
base_model: Gille/StrangeMerges_40-7B-dare_ties
merge_method: dare_ties
dtype: bfloat16
```
## 💻 Usage
```python
!pip install -qU transformers accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "Gille/StrangeMerges_41-7B-dare_ties"
messages = [{"role": "user", "content": "What is a large language model?"}]
tokenizer = AutoTokenizer.from_pretrained(model)
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
pipeline = transformers.pipeline(
"text-generation",
model=model,
torch_dtype=torch.float16,
device_map="auto",
)
outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])
``` |
chihoonlee10/T3Q-EN-DPO-Mistral-7B | chihoonlee10 | 2024-03-18T23:38:37Z | 734 | 0 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"arxiv:1910.09700",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | 2024-03-18T19:12:21Z | ---
library_name: transformers
license: apache-2.0
---
# 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. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **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] |
jeiku/Elly_7B | jeiku | 2024-03-19T03:13:36Z | 734 | 4 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"mergekit",
"merge",
"en",
"arxiv:2311.03099",
"arxiv:2306.01708",
"base_model:MaziyarPanahi/samantha-mistral-7b-Mistral-7B-Instruct-v0.1",
"base_model:cognitivecomputations/dolphin-2.6-mistral-7b",
"base_model:SanjiWatsuki/Sonya-7B",
"license:other",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | 2024-03-19T02:55:55Z | ---
base_model:
- MaziyarPanahi/samantha-mistral-7b-Mistral-7B-Instruct-v0.1
- cognitivecomputations/dolphin-2.6-mistral-7b
- SanjiWatsuki/Sonya-7B
library_name: transformers
tags:
- mergekit
- merge
license: other
language:
- en
---
# Elly
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
## Merge Details
### Merge Method
This model was merged using the [DARE](https://arxiv.org/abs/2311.03099) [TIES](https://arxiv.org/abs/2306.01708) merge method using [SanjiWatsuki/Sonya-7B](https://huggingface.co/SanjiWatsuki/Sonya-7B) as a base.
### Models Merged
The following models were included in the merge:
* [MaziyarPanahi/samantha-mistral-7b-Mistral-7B-Instruct-v0.1](https://huggingface.co/MaziyarPanahi/samantha-mistral-7b-Mistral-7B-Instruct-v0.1)
* [cognitivecomputations/dolphin-2.6-mistral-7b](https://huggingface.co/cognitivecomputations/dolphin-2.6-mistral-7b)
### Configuration
The following YAML configuration was used to produce this model:
```yaml
merge_method: dare_ties
base_model: SanjiWatsuki/Sonya-7B
parameters:
normalize: true
models:
- model: SanjiWatsuki/Sonya-7B
parameters:
weight: 1
- model: cognitivecomputations/dolphin-2.6-mistral-7b
parameters:
weight: 1
- model: MaziyarPanahi/samantha-mistral-7b-Mistral-7B-Instruct-v0.1
parameters:
weight: 1
dtype: float16
``` |
DenisTheDev/Blitz-AI-MOE-v0.4 | DenisTheDev | 2024-03-21T20:10:15Z | 734 | 1 | transformers | [
"transformers",
"safetensors",
"mixtral",
"text-generation",
"conversational",
"arxiv:1910.09700",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | 2024-03-21T07:39:11Z | ---
license: apache-2.0
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
This modelcard aims to be a base template for new models. It has been generated using [this raw template](https://github.com/huggingface/huggingface_hub/blob/main/src/huggingface_hub/templates/modelcard_template.md?plain=1).
## 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] |
OEvortex/vortex-3b-v2 | OEvortex | 2024-03-24T05:44:51Z | 734 | 2 | transformers | [
"transformers",
"safetensors",
"gpt_neox",
"text-generation",
"HelpingAI",
"vortex",
"en",
"dataset:OEvortex/uncensored-vortex",
"license:other",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | 2024-03-21T11:16:54Z | ---
language:
- en
license: other
tags:
- HelpingAI
- vortex
datasets:
- OEvortex/uncensored-vortex
license_name: hsul
license_link: https://huggingface.co/OEvortex/vortex-3b/raw/main/LICENSE.md
pipeline_tag: text-generation
model-index:
- name: vortex-3b-v2
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: 39.68
name: normalized accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=OEvortex/vortex-3b-v2
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: 65.04
name: normalized accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=OEvortex/vortex-3b-v2
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: 25.09
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=OEvortex/vortex-3b-v2
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: 33.8
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=OEvortex/vortex-3b-v2
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: 59.12
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=OEvortex/vortex-3b-v2
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: 2.05
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=OEvortex/vortex-3b-v2
name: Open LLM Leaderboard
---
**Model Overview**
Vortex-3b-v2 is an upgraded version of the Vortex-3b model ie. a 2.78 billion parameter causal language model created by OEvortex that was derived from EleutherAI's Pythia-2.8b and trained on 79% of uncensored-vortex dataset
```python
from transformers import pipeline
# Initialize the pipeline
pipe = pipeline("text-generation", model="OEvortex/vortex-3b-v2")
# Use the pipeline
text = "Once upon a time"
generated_text = pipe(text, max_length=100, do_sample=True)[0]['generated_text']
print(generated_text)
```
```python
# Use a pipeline as a high-level helper
from transformers import pipeline
text = pipeline(model="OEvortex/vortex-3b-v2", torch_dtype=torch.bfloat16, device_map="auto")
res = text("Explain to me the difference between nuclear fission and fusion.")
print(res[0]["text"])
```
# [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_OEvortex__vortex-3b-v2)
| Metric | vortex 3b | vortex 3b-v2 | dolly-v2-3b | pythia-2.8b-deduped |
|---------|----------:|-------------:|------------------:|----------------------------------:|
| Avg. | 35.76 | 37.46 | 25.26 | 36.72 |
| AI2 Reasoning Challenge (25-Shot) | 31.91 | 39.68 | 22.83 | 36.26 |
| HellaSwag (10-Shot) | 56.89 | 65.04 | 26.55 | 60.66 |
| MMLU (5-Shot) | 27.32 | 25.09 | 24.7 | 26.78 |
| TruthfulQA (0-shot) | 37.39 | 33.80 | 0 | 35.56 |
| Winogrande (5-shot) | 60.14 | 59.12 | 59.43 | 60.22 |
| GSM8k (5-shot) | 0.91 | 2.05 | 1.86 | 0.83 |
|
Fizzarolli/sappha-2b-v3 | Fizzarolli | 2024-04-09T21:18:36Z | 734 | 1 | transformers | [
"transformers",
"safetensors",
"gemma",
"text-generation",
"dataset:Open-Orca/SlimOrca-Dedup",
"dataset:jondurbin/airoboros-3.2",
"license:gemma",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | 2024-03-24T03:20:53Z | ---
datasets:
- Open-Orca/SlimOrca-Dedup
- jondurbin/airoboros-3.2
license: gemma
---
# sappha-2b-v3
a slightly less experimental qlora instruct finetune of the gemma-2b base model. trained with unsloth.
## benchmarks
| | gemma-2b-it | sappha-2b-v3 | dolphin-2.8-gemma-2b |
| ---------------------- | ----------- | ------------ | -------------------- |
| MMLU (five-shot) | 36.98 | **38.02** | 37.89 |
| HellaSwag (zero-shot) | 49.22 | **51.70** | 47.79 |
| PIQA (one-shot) | 75.08 | **75.46** | 71.16 |
| TruthfulQA (zero-shot) | **37.51** | 31.65 | 37.15 |
## prompt format
basic chatml:
```
<|im_start|>system
You are a useful and helpful AI assistant.<|im_end|>
<|im_start|>user
what are LLMs?<|im_end|>
<|im_start|>assistant
LLMs, or Large Language Models, are advanced artificial intelligence systems that can perform tasks similar to human language. They are trained on vast amounts of data and can understand and respond to human queries. LLMs are often used in various applications, such as language translation, text generation, and question answering.<|im_end|>
```
## quants
gguf: https://huggingface.co/Fizzarolli/sappha-2b-v3-GGUF
## what happened to v2?
it was a private failure :) |
TeeZee/GALAXY_v03_slimorca_1_epoch_50k | TeeZee | 2024-03-30T18:50:07Z | 734 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"conversational",
"en",
"dataset:Open-Orca/SlimOrca",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | 2024-03-24T09:44:44Z | ---
language:
- en
license: apache-2.0
datasets:
- Open-Orca/SlimOrca
model-index:
- name: GALAXY_v03_slimorca_1_epoch_50k
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: 62.71
name: normalized accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TeeZee/GALAXY_v03_slimorca_1_epoch_50k
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: 84.58
name: normalized accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TeeZee/GALAXY_v03_slimorca_1_epoch_50k
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: 65.17
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TeeZee/GALAXY_v03_slimorca_1_epoch_50k
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: 47.3
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TeeZee/GALAXY_v03_slimorca_1_epoch_50k
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: 82.48
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TeeZee/GALAXY_v03_slimorca_1_epoch_50k
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: 0.0
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TeeZee/GALAXY_v03_slimorca_1_epoch_50k
name: Open LLM Leaderboard
---
### TeeZee/GALAXY-XB-v1.03 ###
Experiment, can DUS be taken one or more steps further?
### Technical notes:
- model v03 finetuned on 50k entries from SlimOrca dataset
- 12 layers removed from both models, 4 more than in original paper but its 1/4 of all layers(48) as per original paper.
- base version of upstage/SOLAR-10.7B-v1.0 used for merge
### To evaluate
- model performance after finetuning, did it recover initial performance loss after merge?
# [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_TeeZee__GALAXY_v03_slimorca_1_epoch_50k)
| Metric |Value|
|---------------------------------|----:|
|Avg. |57.04|
|AI2 Reasoning Challenge (25-Shot)|62.71|
|HellaSwag (10-Shot) |84.58|
|MMLU (5-Shot) |65.17|
|TruthfulQA (0-shot) |47.30|
|Winogrande (5-shot) |82.48|
|GSM8k (5-shot) | 0.00|
|
KeyonZeng/lion-gemma-7b-cn-v2 | KeyonZeng | 2024-03-31T08:26:13Z | 734 | 0 | transformers | [
"transformers",
"safetensors",
"gemma",
"text-generation",
"conversational",
"en",
"zh",
"dataset:argilla/dpo-mix-7k",
"dataset:wenbopan/Chinese-dpo-pairs",
"arxiv:1910.09700",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | 2024-03-31T01:34:40Z | ---
library_name: transformers
license: apache-2.0
datasets:
- argilla/dpo-mix-7k
- wenbopan/Chinese-dpo-pairs
language:
- en
- zh
metrics:
- accuracy
---
# 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. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **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] |
Ppoyaa/FusedKuno | Ppoyaa | 2024-04-05T09:07:49Z | 734 | 0 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"merge",
"mergekit",
"lazymergekit",
"Nitral-AI/Kunocchini-7b-128k-test",
"Virt-io/FuseChat-Kunoichi-10.7B",
"conversational",
"custom_code",
"base_model:Nitral-AI/Kunocchini-7b-128k-test",
"base_model:Virt-io/FuseChat-Kunoichi-10.7B",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | 2024-04-04T06:11:29Z | ---
tags:
- merge
- mergekit
- lazymergekit
- Nitral-AI/Kunocchini-7b-128k-test
- Virt-io/FuseChat-Kunoichi-10.7B
base_model:
- Nitral-AI/Kunocchini-7b-128k-test
- Virt-io/FuseChat-Kunoichi-10.7B
license: apache-2.0
---
# FusedKuno
FusedKuno is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
* [Nitral-AI/Kunocchini-7b-128k-test](https://huggingface.co/Nitral-AI/Kunocchini-7b-128k-test)
* [Virt-io/FuseChat-Kunoichi-10.7B](https://huggingface.co/Virt-io/FuseChat-Kunoichi-10.7B)
## 🧩 Configuration
```yaml
slices:
- sources:
- model: Nitral-AI/Kunocchini-7b-128k-test
layer_range: [0, 32]
- model: Virt-io/FuseChat-Kunoichi-10.7B
layer_range: [0, 32]
merge_method: slerp
base_model: Nitral-AI/Kunocchini-7b-128k-test
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
dtype: bfloat16
```
## 💻 Usage
```python
!pip install -qU transformers accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "Ppoyaa/FusedKuno"
messages = [{"role": "user", "content": "What is a large language model?"}]
tokenizer = AutoTokenizer.from_pretrained(model)
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
pipeline = transformers.pipeline(
"text-generation",
model=model,
torch_dtype=torch.float16,
device_map="auto",
)
outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])
``` |
ShenaoZhang/0.001_idpo_iter_2 | ShenaoZhang | 2024-04-05T15:22:58Z | 734 | 0 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"alignment-handbook",
"generated_from_trainer",
"trl",
"dpo",
"conversational",
"dataset:ShenaoZhang/0.001_idpo_dataset",
"base_model:ShenaoZhang/0.001_idpo_iter_1",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | 2024-04-05T14:34:55Z | ---
license: mit
base_model: ShenaoZhang/0.001_idpo_iter_1
tags:
- alignment-handbook
- generated_from_trainer
- trl
- dpo
- generated_from_trainer
datasets:
- ShenaoZhang/0.001_idpo_dataset
model-index:
- name: 0.001_idpo_iter_2
results: []
---
<!-- 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. -->
# 0.001_idpo_iter_2
This model is a fine-tuned version of [ShenaoZhang/0.001_idpo_iter_1](https://huggingface.co/ShenaoZhang/0.001_idpo_iter_1) on the ShenaoZhang/0.001_idpo_dataset dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-07
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 8
- gradient_accumulation_steps: 2
- total_train_batch_size: 128
- total_eval_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 1
### Training results
### Framework versions
- Transformers 4.36.2
- Pytorch 2.1.2+cu121
- Datasets 2.14.6
- Tokenizers 0.15.2
|
netcat420/MFANN3bv0.2 | netcat420 | 2024-04-06T00:35:33Z | 734 | 0 | transformers | [
"transformers",
"safetensors",
"phi",
"text-generation",
"dataset:netcat420/MFANN",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | 2024-04-05T20:50:13Z | ---
library_name: transformers
license: apache-2.0
datasets:
- netcat420/MFANN
---
63.08 <- Average
61.77 <- ARC
76.35 <- HellaSwag
56.23 <- MMLU
53 <- TruthfulQA
75.85 <- Winogrande
55.27 <- GSM8K |
jambroz/sixtyoneeighty-7b-dpo | jambroz | 2024-04-05T22:47:46Z | 734 | 0 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"conversational",
"dataset:Intel/orca_dpo_pairs",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | 2024-04-05T22:19:17Z | ---
library_name: transformers
tags:
- conversational
license: apache-2.0
datasets:
- Intel/orca_dpo_pairs
pipeline_tag: text-generation
---
# Model Card for Model ID
A chat finetune using the Intel/orca_dpo_pairs dataset
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** sixtyoneeighty
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** apache 2.0
- **Finetuned from model [optional]:** jambroz/sixtyoneeighty-7b
|
Josephgflowers/Tinyllama-1.5B-Cinder-Test-5 | Josephgflowers | 2024-04-07T12:52:30Z | 734 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"conversational",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | 2024-04-07T11:35:31Z | ---
license: mit
---
This is a depth up scalled model of the 616M cinder model and Cinder v2. This model still needs further training. Putting it up for testing. More information coming. Maybe. Lol. Here is a brief desc of the project: Im mixing a lot of techniques I guess that I found interesting and have been testing, HF Cosmo is not great but decent and was fully trained in 4 days using a mix of more fine tuned directed datasets and some synthetic textbook style datasets. So I used pruning and a similar mix as Cosmo on tinyllama (trained on a ton of data for an extended time for its size) to keep the tinyllama model coherent during pruning. Now I am trying to depth up scale it using my pruned model and an original, Then taking a majority of each and combining them to create a larger model. Then it needs more training, then fine tuning. Then theoretically it will be a well performing 1.5B model (that didn't need full scale training). Test 2, some training, re depth upscalled with cinder reason 1.3B and merged back with 1.5 and slight training. Continuing training from this model for next iteration. This is the next iteration with 1 go on metamath |
MaziyarPanahi/Phi-3-mini-4k-instruct-v0.3 | MaziyarPanahi | 2024-06-28T17:31:17Z | 734 | 9 | transformers | [
"transformers",
"safetensors",
"phi3",
"text-generation",
"axolotl",
"finetune",
"dpo",
"microsoft",
"phi",
"pytorch",
"phi-3",
"nlp",
"code",
"chatml",
"conversational",
"custom_code",
"en",
"base_model:microsoft/Phi-3-mini-4k-instruct",
"license:mit",
"model-index",
"autotrain_compatible",
"region:us"
] | text-generation | 2024-05-10T12:00:17Z | ---
language:
- en
license: mit
library_name: transformers
tags:
- axolotl
- finetune
- dpo
- microsoft
- phi
- pytorch
- phi-3
- nlp
- code
- chatml
base_model: microsoft/Phi-3-mini-4k-instruct
pipeline_tag: text-generation
inference: false
model_creator: MaziyarPanahi
quantized_by: MaziyarPanahi
model-index:
- name: Phi-3-mini-4k-instruct-v0.3
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: 63.48
name: normalized accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=MaziyarPanahi/Phi-3-mini-4k-instruct-v0.3
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: 80.86
name: normalized accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=MaziyarPanahi/Phi-3-mini-4k-instruct-v0.3
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: 69.24
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=MaziyarPanahi/Phi-3-mini-4k-instruct-v0.3
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: 60.66
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=MaziyarPanahi/Phi-3-mini-4k-instruct-v0.3
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: 72.77
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=MaziyarPanahi/Phi-3-mini-4k-instruct-v0.3
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: 74.53
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=MaziyarPanahi/Phi-3-mini-4k-instruct-v0.3
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: IFEval (0-Shot)
type: HuggingFaceH4/ifeval
args:
num_few_shot: 0
metrics:
- type: inst_level_strict_acc and prompt_level_strict_acc
value: 49.26
name: strict accuracy
source:
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=MaziyarPanahi/Phi-3-mini-4k-instruct-v0.3
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: BBH (3-Shot)
type: BBH
args:
num_few_shot: 3
metrics:
- type: acc_norm
value: 37.66
name: normalized accuracy
source:
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=MaziyarPanahi/Phi-3-mini-4k-instruct-v0.3
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: MATH Lvl 5 (4-Shot)
type: hendrycks/competition_math
args:
num_few_shot: 4
metrics:
- type: exact_match
value: 2.95
name: exact match
source:
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=MaziyarPanahi/Phi-3-mini-4k-instruct-v0.3
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: GPQA (0-shot)
type: Idavidrein/gpqa
args:
num_few_shot: 0
metrics:
- type: acc_norm
value: 9.06
name: acc_norm
source:
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=MaziyarPanahi/Phi-3-mini-4k-instruct-v0.3
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: MuSR (0-shot)
type: TAUR-Lab/MuSR
args:
num_few_shot: 0
metrics:
- type: acc_norm
value: 7.75
name: acc_norm
source:
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=MaziyarPanahi/Phi-3-mini-4k-instruct-v0.3
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: MMLU-PRO (5-shot)
type: TIGER-Lab/MMLU-Pro
config: main
split: test
args:
num_few_shot: 5
metrics:
- type: acc
value: 31.42
name: accuracy
source:
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=MaziyarPanahi/Phi-3-mini-4k-instruct-v0.3
name: Open LLM Leaderboard
---
<img src="./phi-3-instruct.webp" alt="Phi-3 Logo" width="500" style="margin-left:'auto' margin-right:'auto' display:'block'"/>
# MaziyarPanahi/Phi-3-mini-4k-instruct-v0.3
This model is a fine-tune (DPO) of `microsoft/Phi-3-mini-4k-instruct` model.
# ⚡ Quantized GGUF
All GGUF models are available here: [MaziyarPanahi/Phi-3-mini-4k-instruct-v0.3-GGUF](https://huggingface.co/MaziyarPanahi/Phi-3-mini-4k-instruct-v0.3-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__Phi-3-mini-4k-instruct-v0.3)
** Leaderboard 2**
| Metric |Value|
|-------------------|----:|
|Avg. |23.38|
|IFEval (0-Shot) |49.26|
|BBH (3-Shot) |37.66|
|MATH Lvl 5 (4-Shot)| 2.95|
|GPQA (0-shot) | 9.06|
|MuSR (0-shot) | 7.75|
|MMLU-PRO (5-shot) |31.42|
** Leaderboard 1**
| Metric |Value|
|---------------------------------|----:|
|Avg. |70.26|
|AI2 Reasoning Challenge (25-Shot)|63.48|
|HellaSwag (10-Shot) |80.86|
|MMLU (5-Shot) |69.24|
|TruthfulQA (0-shot) |60.66|
|Winogrande (5-shot) |72.77|
|GSM8k (5-shot) |74.53|
`MaziyarPanahi/Phi-3-mini-4k-instruct-v0.3` is the best-performing Phi-3-mini-4k model on the Open LLM Leaderboard. (03/06/2024).
# 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/Phi-3-mini-4k-instruct-v0.3` 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/Phi-3-mini-4k-instruct-v0.3"
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)
messages = [
{"role": "system", "content": "You are a pirate chatbot who always responds in pirate speak!"},
{"role": "user", "content": "Who are you?"},
]
# this should work perfectly for the model to stop generating
terminators = [
tokenizer.eos_token_id, # this should be <|im_end|>
tokenizer.convert_tokens_to_ids("<|assistant|>"), # sometimes model stops generating at <|assistant|>
tokenizer.convert_tokens_to_ids("<|end|>") # sometimes model stops generating at <|end|>
]
pipe = pipeline(
"text-generation",
model=model,
tokenizer=tokenizer,
)
generation_args = {
"max_new_tokens": 500,
"return_full_text": False,
"temperature": 0.0,
"do_sample": False,
"streamer": streamer,
"eos_token_id": terminators,
}
output = pipe(messages, **generation_args)
print(output[0]['generated_text'])
```
|
matchaaaaa/Chaifighter-20B-v2 | matchaaaaa | 2024-05-20T06:00:09Z | 734 | 6 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"mergekit",
"merge",
"base_model:Sao10K/Fimbulvetr-11B-v2",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | 2024-05-19T04:24:51Z | ---
base_model:
- Sao10K/Fimbulvetr-11B-v2
library_name: transformers
tags:
- mergekit
- merge
license: apache-2.0
pipeline_tag: text-generation
---
**Thank you @brooketh for the [iMat + static GGUFs](https://huggingface.co/FaradayDotDev/Chaifighter-20B-v2-GGUF) on the Faraday model hub!**
**Thank you @mradermacher for also making [GGUFs](https://huggingface.co/mradermacher/Chaifighter-20B-v2-GGUF) and [iMat GGUFs](https://huggingface.co/mradermacher/Chaifighter-20B-v2-i1-GGUF)**
# Chaifighter 20B v2 (aaaaand it's BASICALLY a 20B this time!)
Meet Chaifighter 20B v2, my flagship Mistral 20B frankenmerge model! Boasting creativity, coherence, and cognitive thinking, this model is a great pick for those awkwardly stuck between 13B's and 34B's.
I also wanted to provide an alternative to Jeb Carter's [Psyonic Cetacean 20B](https://huggingface.co/jebcarter/psyonic-cetacean-20B), which is a fantastic model that you should check out if you haven't already! The issue with that model is that it's based on Llama 2, which is outdated now. The older architecture lacked many performance enhancements that were introduced by the Mistral architecture, and on my 16 GB RTX 4060 Ti, those performance enhancements were the difference between decently speedy and intolerably sluggish.
Chaifighter 20B is geared towards long-form roleplay chats rather than short-form IRC/Discord RP chats. It loves verbosity and detail, and its quality will depend on how much "ammunition" you can give it. While it sorta-kinda can do short-form with some swiping, it isn't really ideal. But for those essay-writing powerhouses that love typing up a storm in the character card, this one's for you.
Chaifighter 20B natively supports a context window of only 4096 tokens maximum.
## Prompt Template: Alpaca
```
Below is an instruction that describes a task. Write a response that appropriately completes the request.
### Instruction:
{prompt}
### Response:
```
## Recommended Settings: Universal-Light
Here are some settings ranges that tend to work for me. They aren't strict values, and there's a bit of leeway in them. Feel free to experiment a bit!
* Temperature: **1.0** *to* **1.25** (adjust to taste, but keep it low. Chaifighter is creative enough on its own)
* Min-P: **0.1** (increasing might help if it goes cuckoo, but I suggest keeping it there)
* Repetition Penalty: **1.05** *to* **1.1** (high values aren't needed and usually degrade output)
* Rep. Penalty Range: **256** *or* **512**
* *(all other samplers disabled)*
## Merge Details
### Mergekit
Chaifighter 20B is a frankenmerge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
### Merge Method
This model was merged using the passthrough merge method.
### Models Merged
The following models were included in the merge:
* [Gryphe/MythoMist-7b](https://huggingface.co/Gryphe/MythoMist-7b)
* [KatyTheCutie/LemonadeRP-4.5.3](https://huggingface.co/KatyTheCutie/LemonadeRP-4.5.3)
* [SanjiWatsuki/Kunoichi-7B](https://huggingface.co/SanjiWatsuki/Kunoichi-7B)
* [Sao10K/Fimbulvetr-11B-v2](https://huggingface.co/Sao10K/Fimbulvetr-11B-v2)
### The Sauceeeeeee e ee
The following YAML configuration was used to produce this model:
```yaml
slices:
- sources:
- model: Sao10K/Fimbulvetr-11B-v2
layer_range: [0, 40]
- sources:
- model: SanjiWatsuki/Kunoichi-7B
layer_range: [8, 16]
- sources:
- model: Mytho-Lemon-11B # my own merge (see below).
layer_range: [8, 48]
merge_method: passthrough
dtype: bfloat16
```
And here's Mytho-Lemon-11B. Yep, named it backwards.
```yaml
slices:
- sources:
- model: KatyTheCutie/LemonadeRP-4.5.3
layer_range: [0, 24]
- sources:
- model: Gryphe/MythoMist-7B # manually added tokenizer files
layer_range: [8, 32]
merge_method: passthrough
dtype: bfloat16
```
It's a lot better than v1 :skull:
So, the idea was to start with Fimbulvetr-11B-v2, a super solid RP model that punches wayyy above its weight especially for its coherence, reasoning, and even spatial awareness. Keeping the layers intact apparently is somewhat unusual, but I wanted to keep it closest to the input layers. I thought it would improve logic and open the door for more creativity later in the stack. I added Kunoichi next for its context and instruction following skills. This worked very well in v1. Lastly, I used a frankenmerge of MythoMist and LemonadeRP for the last layers. These are pretty creative models with solid writing. MythoMist in theory would give the model flavor and verbosity. LemonadeRP was recommended by a friend, and I thought it really complimented the rest of the mix quite nicely!
## Thanks and Other Stuff
I want to thank everyone who helped me make this model. [@brooketh](https://huggingface.co/brooketh), [@FallenMerick](https://huggingface.co/FallenMerick), [@jebcarter](https://huggingface.co/jebcarter), [@Qonsol](https://huggingface.co/Qonsol), [@PacmanIncarnate](https://huggingface.co/PacmanIncarnate), and many others: thank you so much. Without the help, feedback, and encouragement these people gave, Chaifighter v2 would not have happened. The flaws in v1 were numerous and tricky to solve, especially for someone still super new to this (me). I don't know what I'd do without these kindhearted and generous people!
Yapping time. As far as the name is concerned, I'm going for a tea/coffee/hot drink motif for my models, and one of the names I was debating on using for this model was Chai-Latte. As I worked on this merge, I got the idea of naming it "Chaifighter" as a play on "Psyfighter2", one of the models making up Psyonic Cetacean and also a play on a model called "Tiefighter" from which it was derived. Both are fantastic models, especially given their age. They're both worth checking out too if you haven't done so. "Chai" itself is a play on a certain AI chatting website (CAI) that got me into this lovely mess in the first place. So I guess it's fitting to name the first model of the series after it.
And lastly, of course, thank you for checking out my model! Remember that you're super amazing, and have a fantastic day! :) |
sinxcosx11/tinyllama-chem3 | sinxcosx11 | 2024-05-22T22:05:53Z | 734 | 0 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"unsloth",
"trl",
"sft",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | 2024-05-22T22:04:02Z | ---
library_name: transformers
tags:
- unsloth
- trl
- sft
---
# 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. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **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] |
KBlueLeaf/Kohaku-XL-Epsilon-rev2 | KBlueLeaf | 2024-06-02T16:31:39Z | 734 | 19 | diffusers | [
"diffusers",
"text-to-image",
"en",
"dataset:KBlueLeaf/danbooru2023-webp-4Mpixel",
"dataset:KBlueLeaf/danbooru2023-sqlite",
"license:other",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionXLPipeline",
"region:us"
] | text-to-image | 2024-05-24T13:03:41Z | ---
license: other
license_name: fair-ai-public-license-1.0-sd
license_link: https://freedevproject.org/faipl-1.0-sd/
datasets:
- KBlueLeaf/danbooru2023-webp-4Mpixel
- KBlueLeaf/danbooru2023-sqlite
language:
- en
library_name: diffusers
pipeline_tag: text-to-image
---
# Kohaku XL Epsilon rev2
join us: https://discord.gg/tPBsKDyRR5
## Rev2 Features
- Resumed from Kohaku XL Epsilon rev1
- 1.56M images, 5epoch
- Trained on selected artists' artworks and images about selected series/games
- Trained on PVC figure photos, can generate PVC style without any additional models
## Usage (PLEASE READ THIS SECTION)
### Prompt Format
`<1girl/1boy/1other/...>, <character>, <series>, <artists>, <general tags>, <quality tags>, <year tags>, <meta tags>, <rating tags>`
### Special Tags
- Quality tags: masterpiece, best quality, great quality, good quality, normal quality, low quality, worst quality
- Rating tags: safe, sensitive, nsfw, explicit
- Date tags: newest, recent, mid, early, old
#### Rating tags
General: safe
Sensitive: sensitive
Questionable: nsfw
Explicit: nsfw, explicit
### Resolution
This model is trained for resolutions from ARB 1024x1024 with minimum resolution 256 and maximum resolution 4096. This means you can use the standard SDXL resolution. However, opting for a slightly higher resolution than 1024x1024 is recommended. Applying a hires-fix is also suggested for better results.
## Training
- Hardware: Quad RTX 3090s
- Num Train Images: 1,536,902
- Total Epoch: 5
- Total Steps: 15015
- Training Time: 410 hours (wall time)
- Batch Size: 4
- Grad Accumulation Step: 32
- Equivalent Batch Size: 512
- Optimizer: Lion8bit
- Learning Rate: 1e-5 for UNet / 2e-6 for TE
- LR Scheduler: Cosine (with warmup)
- Warmup Steps: 1000
- Weight Decay: 0.1
- Betas: 0.9, 0.95
- Min SNR Gamma: 5
- Noise Offset: 0.0357
- Resolution: 1024x1024
- Min Bucket Resolution: 256
- Max Bucket Resolution: 4096
- Mixed Precision: FP16
- Caption Tag Dropout: 0.2
- Caption Dropout: 0.05
## License:
Fair-AI-public-1.0-sd |
mradermacher/Llama-3-70b-Arimas-story-RP-V1-i1-GGUF | mradermacher | 2024-05-27T02:45:06Z | 734 | 1 | transformers | [
"transformers",
"gguf",
"mergekit",
"merge",
"llama-3",
"70b",
"smaug",
"lumimaid",
"tess",
"arimas",
"breadcrums",
"en",
"base_model:ryzen88/Llama-3-70b-Arimas-story-RP-V1",
"endpoints_compatible",
"region:us"
] | null | 2024-05-25T17:37:38Z | ---
base_model: ryzen88/Llama-3-70b-Arimas-story-RP-V1
language:
- en
library_name: transformers
quantized_by: mradermacher
tags:
- mergekit
- merge
- llama-3
- 70b
- smaug
- lumimaid
- tess
- arimas
- breadcrums
---
## About
<!-- ### quantize_version: 2 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: hfhfix -->
<!-- ### vocab_type: -->
weighted/imatrix quants of https://huggingface.co/ryzen88/Llama-3-70b-Arimas-story-RP-V1
<!-- provided-files -->
static quants are available at https://huggingface.co/mradermacher/Llama-3-70b-Arimas-story-RP-V1-GGUF
## Usage
If you are unsure how to use GGUF files, refer to one of [TheBloke's
READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
more details, including on how to concatenate multi-part files.
## Provided Quants
(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
| Link | Type | Size/GB | Notes |
|:-----|:-----|--------:|:------|
| [GGUF](https://huggingface.co/mradermacher/Llama-3-70b-Arimas-story-RP-V1-i1-GGUF/resolve/main/Llama-3-70b-Arimas-story-RP-V1.i1-IQ1_S.gguf) | i1-IQ1_S | 15.4 | for the desperate |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-70b-Arimas-story-RP-V1-i1-GGUF/resolve/main/Llama-3-70b-Arimas-story-RP-V1.i1-IQ1_M.gguf) | i1-IQ1_M | 16.9 | mostly desperate |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-70b-Arimas-story-RP-V1-i1-GGUF/resolve/main/Llama-3-70b-Arimas-story-RP-V1.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 19.2 | |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-70b-Arimas-story-RP-V1-i1-GGUF/resolve/main/Llama-3-70b-Arimas-story-RP-V1.i1-IQ2_XS.gguf) | i1-IQ2_XS | 21.2 | |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-70b-Arimas-story-RP-V1-i1-GGUF/resolve/main/Llama-3-70b-Arimas-story-RP-V1.i1-IQ2_S.gguf) | i1-IQ2_S | 22.3 | |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-70b-Arimas-story-RP-V1-i1-GGUF/resolve/main/Llama-3-70b-Arimas-story-RP-V1.i1-IQ2_M.gguf) | i1-IQ2_M | 24.2 | |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-70b-Arimas-story-RP-V1-i1-GGUF/resolve/main/Llama-3-70b-Arimas-story-RP-V1.i1-Q2_K.gguf) | i1-Q2_K | 26.5 | IQ3_XXS probably better |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-70b-Arimas-story-RP-V1-i1-GGUF/resolve/main/Llama-3-70b-Arimas-story-RP-V1.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 27.6 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-70b-Arimas-story-RP-V1-i1-GGUF/resolve/main/Llama-3-70b-Arimas-story-RP-V1.i1-IQ3_XS.gguf) | i1-IQ3_XS | 29.4 | |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-70b-Arimas-story-RP-V1-i1-GGUF/resolve/main/Llama-3-70b-Arimas-story-RP-V1.i1-IQ3_S.gguf) | i1-IQ3_S | 31.0 | beats Q3_K* |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-70b-Arimas-story-RP-V1-i1-GGUF/resolve/main/Llama-3-70b-Arimas-story-RP-V1.i1-Q3_K_S.gguf) | i1-Q3_K_S | 31.0 | IQ3_XS probably better |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-70b-Arimas-story-RP-V1-i1-GGUF/resolve/main/Llama-3-70b-Arimas-story-RP-V1.i1-IQ3_M.gguf) | i1-IQ3_M | 32.0 | |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-70b-Arimas-story-RP-V1-i1-GGUF/resolve/main/Llama-3-70b-Arimas-story-RP-V1.i1-Q3_K_M.gguf) | i1-Q3_K_M | 34.4 | IQ3_S probably better |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-70b-Arimas-story-RP-V1-i1-GGUF/resolve/main/Llama-3-70b-Arimas-story-RP-V1.i1-Q3_K_L.gguf) | i1-Q3_K_L | 37.2 | IQ3_M probably better |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-70b-Arimas-story-RP-V1-i1-GGUF/resolve/main/Llama-3-70b-Arimas-story-RP-V1.i1-IQ4_XS.gguf) | i1-IQ4_XS | 38.0 | |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-70b-Arimas-story-RP-V1-i1-GGUF/resolve/main/Llama-3-70b-Arimas-story-RP-V1.i1-Q4_0.gguf) | i1-Q4_0 | 40.2 | fast, low quality |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-70b-Arimas-story-RP-V1-i1-GGUF/resolve/main/Llama-3-70b-Arimas-story-RP-V1.i1-Q4_K_S.gguf) | i1-Q4_K_S | 40.4 | optimal size/speed/quality |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-70b-Arimas-story-RP-V1-i1-GGUF/resolve/main/Llama-3-70b-Arimas-story-RP-V1.i1-Q4_K_M.gguf) | i1-Q4_K_M | 42.6 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-70b-Arimas-story-RP-V1-i1-GGUF/resolve/main/Llama-3-70b-Arimas-story-RP-V1.i1-Q5_K_S.gguf) | i1-Q5_K_S | 48.8 | |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-70b-Arimas-story-RP-V1-i1-GGUF/resolve/main/Llama-3-70b-Arimas-story-RP-V1.i1-Q5_K_M.gguf) | i1-Q5_K_M | 50.0 | |
| [PART 1](https://huggingface.co/mradermacher/Llama-3-70b-Arimas-story-RP-V1-i1-GGUF/resolve/main/Llama-3-70b-Arimas-story-RP-V1.i1-Q6_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Llama-3-70b-Arimas-story-RP-V1-i1-GGUF/resolve/main/Llama-3-70b-Arimas-story-RP-V1.i1-Q6_K.gguf.part2of2) | i1-Q6_K | 58.0 | practically like static Q6_K |
Here is a handy graph by ikawrakow comparing some lower-quality quant
types (lower is better):
And here are Artefact2's thoughts on the matter:
https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
## FAQ / Model Request
See https://huggingface.co/mradermacher/model_requests for some answers to
questions you might have and/or if you want some other model quantized.
## Thanks
I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
me use its servers and providing upgrades to my workstation to enable
this work in my free time.
<!-- end -->
|
kvriza8/clip-microscopy-255-ViT_L_14-epoch-captions_summary | kvriza8 | 2024-06-05T16:27:50Z | 734 | 0 | open_clip | [
"open_clip",
"safetensors",
"clip",
"zero-shot-image-classification",
"license:mit",
"region:us"
] | zero-shot-image-classification | 2024-06-05T16:26:53Z | ---
tags:
- clip
library_name: open_clip
pipeline_tag: zero-shot-image-classification
license: mit
---
# Model card for clip-microscopy-255-ViT_L_14-epoch-captions_summary
|
CHE-72/Yi-1.5-6B-Chat-Q5_0-GGUF | CHE-72 | 2024-06-22T07:22:31Z | 734 | 0 | null | [
"gguf",
"llama-cpp",
"gguf-my-repo",
"base_model:01-ai/Yi-1.5-6B-Chat",
"license:apache-2.0",
"region:us"
] | null | 2024-06-22T07:22:13Z | ---
base_model: 01-ai/Yi-1.5-6B-Chat
license: apache-2.0
tags:
- llama-cpp
- gguf-my-repo
---
# CHE-72/Yi-1.5-6B-Chat-Q5_0-GGUF
This model was converted to GGUF format from [`01-ai/Yi-1.5-6B-Chat`](https://huggingface.co/01-ai/Yi-1.5-6B-Chat) 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/01-ai/Yi-1.5-6B-Chat) 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 CHE-72/Yi-1.5-6B-Chat-Q5_0-GGUF --hf-file yi-1.5-6b-chat-q5_0.gguf -p "The meaning to life and the universe is"
```
### Server:
```bash
llama-server --hf-repo CHE-72/Yi-1.5-6B-Chat-Q5_0-GGUF --hf-file yi-1.5-6b-chat-q5_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 CHE-72/Yi-1.5-6B-Chat-Q5_0-GGUF --hf-file yi-1.5-6b-chat-q5_0.gguf -p "The meaning to life and the universe is"
```
or
```
./llama-server --hf-repo CHE-72/Yi-1.5-6B-Chat-Q5_0-GGUF --hf-file yi-1.5-6b-chat-q5_0.gguf -c 2048
```
|
bigjoedata/rockbot355M | bigjoedata | 2021-05-21T14:17:25Z | 733 | 1 | transformers | [
"transformers",
"pytorch",
"jax",
"gpt2",
"text-generation",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | 2022-03-02T23:29:05Z |
# 🎸 🥁 Rockbot 🎤 🎧
A [GPT-2](https://openai.com/blog/better-language-models/) based lyrics generator fine-tuned on the writing styles of 16000 songs by 270 artists across MANY genres (not just rock).
**Instructions:** Type in a fake song title, pick an artist, click "Generate".
Most language models are imprecise and Rockbot is no exception. You may see NSFW lyrics unexpectedly. I have made no attempts to censor. Generated lyrics may be repetitive and/or incoherent at times, but hopefully you'll encounter something interesting or memorable.
Oh, and generation is resource intense and can be slow. I set governors on song length to keep generation time somewhat reasonable. You may adjust song length and other parameters on the left or check out [Github](https://github.com/bigjoedata/rockbot) to spin up your own Rockbot.
Just have fun.
[Demo](https://share.streamlit.io/bigjoedata/rockbot/main/src/main.py) Adjust settings to increase speed
[Github](https://github.com/bigjoedata/rockbot)
[GPT-2 124M version Model page on Hugging Face](https://huggingface.co/bigjoedata/rockbot)
[DistilGPT2 version Model page on Hugging Face](https://huggingface.co/bigjoedata/rockbot-distilgpt2/) This is leaner with the tradeoff being that the lyrics are more simplistic.
🎹 🪘 🎷 🎺 🪗 🪕 🎻
## Background
With the shutdown of [Google Play Music](https://en.wikipedia.org/wiki/Google_Play_Music) I used Google's takeout function to gather the metadata from artists I've listened to over the past several years. I wanted to take advantage of this bounty to build something fun. I scraped the top 50 lyrics for artists I'd listened to at least once from [Genius](https://genius.com/), then fine tuned [GPT-2's](https://openai.com/blog/better-language-models/) 124M token model using the [AITextGen](https://github.com/minimaxir/aitextgen) framework after considerable post-processing. For more on generation, see [here.](https://huggingface.co/blog/how-to-generate)
### Full Tech Stack
[Google Play Music](https://en.wikipedia.org/wiki/Google_Play_Music) (R.I.P.).
[Python](https://www.python.org/).
[Streamlit](https://www.streamlit.io/).
[GPT-2](https://openai.com/blog/better-language-models/).
[AITextGen](https://github.com/minimaxir/aitextgen).
[Pandas](https://pandas.pydata.org/).
[LyricsGenius](https://lyricsgenius.readthedocs.io/en/master/).
[Google Colab](https://colab.research.google.com/) (GPU based Training).
[Knime](https://www.knime.com/) (data cleaning).
## How to Use The Model
Please refer to [AITextGen](https://github.com/minimaxir/aitextgen) for much better documentation.
### Training Parameters Used
ai.train("lyrics.txt",
line_by_line=False,
from_cache=False,
num_steps=10000,
generate_every=2000,
save_every=2000,
save_gdrive=False,
learning_rate=1e-3,
batch_size=3,
eos_token="<|endoftext|>",
#fp16=True
)
### To Use
Generate With Prompt (Use Title Case):
Song Name
BY
Artist Name
|
huggingtweets/amouranth | huggingtweets | 2022-11-20T15:20:24Z | 733 | 0 | transformers | [
"transformers",
"pytorch",
"gpt2",
"text-generation",
"huggingtweets",
"en",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | 2022-09-09T02:52:52Z | ---
language: en
thumbnail: http://www.huggingtweets.com/amouranth/1668957567411/predictions.png
tags:
- huggingtweets
widget:
- text: "My dream is"
---
<div class="inline-flex flex-col" style="line-height: 1.5;">
<div class="flex">
<div
style="display:inherit; margin-left: 4px; margin-right: 4px; width: 92px; height:92px; border-radius: 50%; background-size: cover; background-image: url('https://pbs.twimg.com/profile_images/1038692008720719877/X7uKFWQc_400x400.jpg')">
</div>
<div
style="display:none; margin-left: 4px; margin-right: 4px; width: 92px; height:92px; border-radius: 50%; background-size: cover; background-image: url('')">
</div>
<div
style="display:none; margin-left: 4px; margin-right: 4px; width: 92px; height:92px; border-radius: 50%; background-size: cover; background-image: url('')">
</div>
</div>
<div style="text-align: center; margin-top: 3px; font-size: 16px; font-weight: 800">🤖 AI BOT 🤖</div>
<div style="text-align: center; font-size: 16px; font-weight: 800">Amouranth</div>
<div style="text-align: center; font-size: 14px;">@amouranth</div>
</div>
I was made with [huggingtweets](https://github.com/borisdayma/huggingtweets).
Create your own bot based on your favorite user with [the demo](https://colab.research.google.com/github/borisdayma/huggingtweets/blob/master/huggingtweets-demo.ipynb)!
## How does it work?
The model uses the following pipeline.
To understand how the model was developed, check the [W&B report](https://wandb.ai/wandb/huggingtweets/reports/HuggingTweets-Train-a-Model-to-Generate-Tweets--VmlldzoxMTY5MjI).
## Training data
The model was trained on tweets from Amouranth.
| Data | Amouranth |
| --- | --- |
| Tweets downloaded | 3250 |
| Retweets | 537 |
| Short tweets | 588 |
| Tweets kept | 2125 |
[Explore the data](https://wandb.ai/wandb/huggingtweets/runs/v368cfyz/artifacts), which is tracked with [W&B artifacts](https://docs.wandb.com/artifacts) at every step of the pipeline.
## Training procedure
The model is based on a pre-trained [GPT-2](https://huggingface.co/gpt2) which is fine-tuned on @amouranth's tweets.
Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/wandb/huggingtweets/runs/27hif4yr) for full transparency and reproducibility.
At the end of training, [the final model](https://wandb.ai/wandb/huggingtweets/runs/27hif4yr/artifacts) is logged and versioned.
## How to use
You can use this model directly with a pipeline for text generation:
```python
from transformers import pipeline
generator = pipeline('text-generation',
model='huggingtweets/amouranth')
generator("My dream is", num_return_sequences=5)
```
## Limitations and bias
The model suffers from [the same limitations and bias as GPT-2](https://huggingface.co/gpt2#limitations-and-bias).
In addition, the data present in the user's tweets further affects the text generated by the model.
## About
*Built by Boris Dayma*
[](https://twitter.com/intent/follow?screen_name=borisdayma)
For more details, visit the project repository.
[](https://github.com/borisdayma/huggingtweets)
|
jrtec/jrtec-gpt2-superheroes-name-generator | jrtec | 2023-01-08T20:33:05Z | 733 | 0 | transformers | [
"transformers",
"pytorch",
"tensorboard",
"gpt2",
"text-generation",
"generated_from_trainer",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | 2023-01-08T04:45:08Z | ---
license: mit
tags:
- generated_from_trainer
model-index:
- name: jrtec-gpt2-superheroes-name-generator
results: []
---
<!-- 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. -->
# jrtec-gpt2-superheroes-name-generator
This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 16.5324
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 20
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 3.3728 | 3.45 | 500 | 14.0617 |
| 2.0865 | 6.9 | 1000 | 14.7614 |
| 1.9246 | 10.34 | 1500 | 15.6696 |
| 1.8718 | 13.79 | 2000 | 16.2823 |
| 1.8267 | 17.24 | 2500 | 16.5324 |
### Framework versions
- Transformers 4.25.1
- Pytorch 1.13.0+cu116
- Datasets 2.8.0
- Tokenizers 0.13.2
|
timm/levit_384.fb_dist_in1k | timm | 2024-02-10T23:30:40Z | 733 | 0 | timm | [
"timm",
"pytorch",
"image-classification",
"dataset:imagenet-1k",
"arxiv:2104.01136",
"license:apache-2.0",
"region:us"
] | image-classification | 2023-02-03T21:13:49Z | ---
license: apache-2.0
library_name: timm
tags:
- image-classification
- timm
datasets:
- imagenet-1k
---
# Model card for levit_384.fb_dist_in1k
A LeViT image classification model using convolutional mode (using nn.Conv2d and nn.BatchNorm2d). Pretrained on ImageNet-1k using distillation by paper authors.
## Model Details
- **Model Type:** Image classification / feature backbone
- **Model Stats:**
- Params (M): 39.1
- GMACs: 2.4
- Activations (M): 6.3
- Image size: 224 x 224
- **Papers:**
- LeViT: a Vision Transformer in ConvNet's Clothing for Faster Inference: https://arxiv.org/abs/2104.01136
- **Original:** https://github.com/facebookresearch/LeViT
- **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('levit_384.fb_dist_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(
'levit_384.fb_dist_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 (ie.e a (batch_size, num_features, H, W) tensor
output = model.forward_head(output, pre_logits=True)
# output is (batch_size, num_features) tensor
```
## Model Comparison
|model |top1 |top5 |param_count|img_size|
|-----------------------------------|------|------|-----------|--------|
|levit_384.fb_dist_in1k |82.596|96.012|39.13 |224 |
|levit_conv_384.fb_dist_in1k |82.596|96.012|39.13 |224 |
|levit_256.fb_dist_in1k |81.512|95.48 |18.89 |224 |
|levit_conv_256.fb_dist_in1k |81.512|95.48 |18.89 |224 |
|levit_conv_192.fb_dist_in1k |79.86 |94.792|10.95 |224 |
|levit_192.fb_dist_in1k |79.858|94.792|10.95 |224 |
|levit_128.fb_dist_in1k |78.474|94.014|9.21 |224 |
|levit_conv_128.fb_dist_in1k |78.474|94.02 |9.21 |224 |
|levit_128s.fb_dist_in1k |76.534|92.864|7.78 |224 |
|levit_conv_128s.fb_dist_in1k |76.532|92.864|7.78 |224 |
## Citation
```bibtex
@InProceedings{Graham_2021_ICCV,
author = {Graham, Benjamin and El-Nouby, Alaaeldin and Touvron, Hugo and Stock, Pierre and Joulin, Armand and Jegou, Herve and Douze, Matthijs},
title = {LeViT: A Vision Transformer in ConvNet's Clothing for Faster Inference},
booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)},
month = {October},
year = {2021},
pages = {12259-12269}
}
```
```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/rwightman/pytorch-image-models}}
}
```
|
timm/resnet50.a3_in1k | timm | 2024-02-10T23:39:07Z | 733 | 0 | timm | [
"timm",
"pytorch",
"safetensors",
"image-classification",
"arxiv:2110.00476",
"arxiv:1512.03385",
"license:apache-2.0",
"region:us"
] | image-classification | 2023-04-05T18:09:06Z | ---
license: apache-2.0
library_name: timm
tags:
- image-classification
- timm
---
# Model card for resnet50.a3_in1k
A ResNet-B image classification model.
This model features:
* ReLU activations
* single layer 7x7 convolution with pooling
* 1x1 convolution shortcut downsample
Trained on ImageNet-1k in `timm` using recipe template described below.
Recipe details:
* ResNet Strikes Back `A3` recipe
* LAMB optimizer with BCE loss
* Cosine LR schedule with warmup
## Model Details
- **Model Type:** Image classification / feature backbone
- **Model Stats:**
- Params (M): 25.6
- GMACs: 2.1
- Activations (M): 5.7
- Image size: train = 160 x 160, test = 224 x 224
- **Papers:**
- ResNet strikes back: An improved training procedure in timm: https://arxiv.org/abs/2110.00476
- Deep Residual Learning for Image Recognition: https://arxiv.org/abs/1512.03385
- **Original:** https://github.com/huggingface/pytorch-image-models
## 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('resnet50.a3_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(
'resnet50.a3_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, 80, 80])
# torch.Size([1, 256, 40, 40])
# torch.Size([1, 512, 20, 20])
# torch.Size([1, 1024, 10, 10])
# torch.Size([1, 2048, 5, 5])
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(
'resnet50.a3_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, 2048, 5, 5) 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 |img_size|top1 |top5 |param_count|gmacs|macts|img/sec|
|------------------------------------------|--------|-----|-----|-----------|-----|-----|-------|
|[seresnextaa101d_32x8d.sw_in12k_ft_in1k_288](https://huggingface.co/timm/seresnextaa101d_32x8d.sw_in12k_ft_in1k_288)|320 |86.72|98.17|93.6 |35.2 |69.7 |451 |
|[seresnextaa101d_32x8d.sw_in12k_ft_in1k_288](https://huggingface.co/timm/seresnextaa101d_32x8d.sw_in12k_ft_in1k_288)|288 |86.51|98.08|93.6 |28.5 |56.4 |560 |
|[seresnextaa101d_32x8d.sw_in12k_ft_in1k](https://huggingface.co/timm/seresnextaa101d_32x8d.sw_in12k_ft_in1k)|288 |86.49|98.03|93.6 |28.5 |56.4 |557 |
|[seresnextaa101d_32x8d.sw_in12k_ft_in1k](https://huggingface.co/timm/seresnextaa101d_32x8d.sw_in12k_ft_in1k)|224 |85.96|97.82|93.6 |17.2 |34.2 |923 |
|[resnext101_32x32d.fb_wsl_ig1b_ft_in1k](https://huggingface.co/timm/resnext101_32x32d.fb_wsl_ig1b_ft_in1k)|224 |85.11|97.44|468.5 |87.3 |91.1 |254 |
|[resnetrs420.tf_in1k](https://huggingface.co/timm/resnetrs420.tf_in1k)|416 |85.0 |97.12|191.9 |108.4|213.8|134 |
|[ecaresnet269d.ra2_in1k](https://huggingface.co/timm/ecaresnet269d.ra2_in1k)|352 |84.96|97.22|102.1 |50.2 |101.2|291 |
|[ecaresnet269d.ra2_in1k](https://huggingface.co/timm/ecaresnet269d.ra2_in1k)|320 |84.73|97.18|102.1 |41.5 |83.7 |353 |
|[resnetrs350.tf_in1k](https://huggingface.co/timm/resnetrs350.tf_in1k)|384 |84.71|96.99|164.0 |77.6 |154.7|183 |
|[seresnextaa101d_32x8d.ah_in1k](https://huggingface.co/timm/seresnextaa101d_32x8d.ah_in1k)|288 |84.57|97.08|93.6 |28.5 |56.4 |557 |
|[resnetrs200.tf_in1k](https://huggingface.co/timm/resnetrs200.tf_in1k)|320 |84.45|97.08|93.2 |31.5 |67.8 |446 |
|[resnetrs270.tf_in1k](https://huggingface.co/timm/resnetrs270.tf_in1k)|352 |84.43|96.97|129.9 |51.1 |105.5|280 |
|[seresnext101d_32x8d.ah_in1k](https://huggingface.co/timm/seresnext101d_32x8d.ah_in1k)|288 |84.36|96.92|93.6 |27.6 |53.0 |595 |
|[seresnet152d.ra2_in1k](https://huggingface.co/timm/seresnet152d.ra2_in1k)|320 |84.35|97.04|66.8 |24.1 |47.7 |610 |
|[resnetrs350.tf_in1k](https://huggingface.co/timm/resnetrs350.tf_in1k)|288 |84.3 |96.94|164.0 |43.7 |87.1 |333 |
|[resnext101_32x8d.fb_swsl_ig1b_ft_in1k](https://huggingface.co/timm/resnext101_32x8d.fb_swsl_ig1b_ft_in1k)|224 |84.28|97.17|88.8 |16.5 |31.2 |1100 |
|[resnetrs420.tf_in1k](https://huggingface.co/timm/resnetrs420.tf_in1k)|320 |84.24|96.86|191.9 |64.2 |126.6|228 |
|[seresnext101_32x8d.ah_in1k](https://huggingface.co/timm/seresnext101_32x8d.ah_in1k)|288 |84.19|96.87|93.6 |27.2 |51.6 |613 |
|[resnext101_32x16d.fb_wsl_ig1b_ft_in1k](https://huggingface.co/timm/resnext101_32x16d.fb_wsl_ig1b_ft_in1k)|224 |84.18|97.19|194.0 |36.3 |51.2 |581 |
|[resnetaa101d.sw_in12k_ft_in1k](https://huggingface.co/timm/resnetaa101d.sw_in12k_ft_in1k)|288 |84.11|97.11|44.6 |15.1 |29.0 |1144 |
|[resnet200d.ra2_in1k](https://huggingface.co/timm/resnet200d.ra2_in1k)|320 |83.97|96.82|64.7 |31.2 |67.3 |518 |
|[resnetrs200.tf_in1k](https://huggingface.co/timm/resnetrs200.tf_in1k)|256 |83.87|96.75|93.2 |20.2 |43.4 |692 |
|[seresnextaa101d_32x8d.ah_in1k](https://huggingface.co/timm/seresnextaa101d_32x8d.ah_in1k)|224 |83.86|96.65|93.6 |17.2 |34.2 |923 |
|[resnetrs152.tf_in1k](https://huggingface.co/timm/resnetrs152.tf_in1k)|320 |83.72|96.61|86.6 |24.3 |48.1 |617 |
|[seresnet152d.ra2_in1k](https://huggingface.co/timm/seresnet152d.ra2_in1k)|256 |83.69|96.78|66.8 |15.4 |30.6 |943 |
|[seresnext101d_32x8d.ah_in1k](https://huggingface.co/timm/seresnext101d_32x8d.ah_in1k)|224 |83.68|96.61|93.6 |16.7 |32.0 |986 |
|[resnet152d.ra2_in1k](https://huggingface.co/timm/resnet152d.ra2_in1k)|320 |83.67|96.74|60.2 |24.1 |47.7 |706 |
|[resnetrs270.tf_in1k](https://huggingface.co/timm/resnetrs270.tf_in1k)|256 |83.59|96.61|129.9 |27.1 |55.8 |526 |
|[seresnext101_32x8d.ah_in1k](https://huggingface.co/timm/seresnext101_32x8d.ah_in1k)|224 |83.58|96.4 |93.6 |16.5 |31.2 |1013 |
|[resnetaa101d.sw_in12k_ft_in1k](https://huggingface.co/timm/resnetaa101d.sw_in12k_ft_in1k)|224 |83.54|96.83|44.6 |9.1 |17.6 |1864 |
|[resnet152.a1h_in1k](https://huggingface.co/timm/resnet152.a1h_in1k)|288 |83.46|96.54|60.2 |19.1 |37.3 |904 |
|[resnext101_32x16d.fb_swsl_ig1b_ft_in1k](https://huggingface.co/timm/resnext101_32x16d.fb_swsl_ig1b_ft_in1k)|224 |83.35|96.85|194.0 |36.3 |51.2 |582 |
|[resnet200d.ra2_in1k](https://huggingface.co/timm/resnet200d.ra2_in1k)|256 |83.23|96.53|64.7 |20.0 |43.1 |809 |
|[resnext101_32x4d.fb_swsl_ig1b_ft_in1k](https://huggingface.co/timm/resnext101_32x4d.fb_swsl_ig1b_ft_in1k)|224 |83.22|96.75|44.2 |8.0 |21.2 |1814 |
|[resnext101_64x4d.c1_in1k](https://huggingface.co/timm/resnext101_64x4d.c1_in1k)|288 |83.16|96.38|83.5 |25.7 |51.6 |590 |
|[resnet152d.ra2_in1k](https://huggingface.co/timm/resnet152d.ra2_in1k)|256 |83.14|96.38|60.2 |15.4 |30.5 |1096 |
|[resnet101d.ra2_in1k](https://huggingface.co/timm/resnet101d.ra2_in1k)|320 |83.02|96.45|44.6 |16.5 |34.8 |992 |
|[ecaresnet101d.miil_in1k](https://huggingface.co/timm/ecaresnet101d.miil_in1k)|288 |82.98|96.54|44.6 |13.4 |28.2 |1077 |
|[resnext101_64x4d.tv_in1k](https://huggingface.co/timm/resnext101_64x4d.tv_in1k)|224 |82.98|96.25|83.5 |15.5 |31.2 |989 |
|[resnetrs152.tf_in1k](https://huggingface.co/timm/resnetrs152.tf_in1k)|256 |82.86|96.28|86.6 |15.6 |30.8 |951 |
|[resnext101_32x8d.tv2_in1k](https://huggingface.co/timm/resnext101_32x8d.tv2_in1k)|224 |82.83|96.22|88.8 |16.5 |31.2 |1099 |
|[resnet152.a1h_in1k](https://huggingface.co/timm/resnet152.a1h_in1k)|224 |82.8 |96.13|60.2 |11.6 |22.6 |1486 |
|[resnet101.a1h_in1k](https://huggingface.co/timm/resnet101.a1h_in1k)|288 |82.8 |96.32|44.6 |13.0 |26.8 |1291 |
|[resnet152.a1_in1k](https://huggingface.co/timm/resnet152.a1_in1k)|288 |82.74|95.71|60.2 |19.1 |37.3 |905 |
|[resnext101_32x8d.fb_wsl_ig1b_ft_in1k](https://huggingface.co/timm/resnext101_32x8d.fb_wsl_ig1b_ft_in1k)|224 |82.69|96.63|88.8 |16.5 |31.2 |1100 |
|[resnet152.a2_in1k](https://huggingface.co/timm/resnet152.a2_in1k)|288 |82.62|95.75|60.2 |19.1 |37.3 |904 |
|[resnetaa50d.sw_in12k_ft_in1k](https://huggingface.co/timm/resnetaa50d.sw_in12k_ft_in1k)|288 |82.61|96.49|25.6 |8.9 |20.6 |1729 |
|[resnet61q.ra2_in1k](https://huggingface.co/timm/resnet61q.ra2_in1k)|288 |82.53|96.13|36.8 |9.9 |21.5 |1773 |
|[wide_resnet101_2.tv2_in1k](https://huggingface.co/timm/wide_resnet101_2.tv2_in1k)|224 |82.5 |96.02|126.9 |22.8 |21.2 |1078 |
|[resnext101_64x4d.c1_in1k](https://huggingface.co/timm/resnext101_64x4d.c1_in1k)|224 |82.46|95.92|83.5 |15.5 |31.2 |987 |
|[resnet51q.ra2_in1k](https://huggingface.co/timm/resnet51q.ra2_in1k)|288 |82.36|96.18|35.7 |8.1 |20.9 |1964 |
|[ecaresnet50t.ra2_in1k](https://huggingface.co/timm/ecaresnet50t.ra2_in1k)|320 |82.35|96.14|25.6 |8.8 |24.1 |1386 |
|[resnet101.a1_in1k](https://huggingface.co/timm/resnet101.a1_in1k)|288 |82.31|95.63|44.6 |13.0 |26.8 |1291 |
|[resnetrs101.tf_in1k](https://huggingface.co/timm/resnetrs101.tf_in1k)|288 |82.29|96.01|63.6 |13.6 |28.5 |1078 |
|[resnet152.tv2_in1k](https://huggingface.co/timm/resnet152.tv2_in1k)|224 |82.29|96.0 |60.2 |11.6 |22.6 |1484 |
|[wide_resnet50_2.racm_in1k](https://huggingface.co/timm/wide_resnet50_2.racm_in1k)|288 |82.27|96.06|68.9 |18.9 |23.8 |1176 |
|[resnet101d.ra2_in1k](https://huggingface.co/timm/resnet101d.ra2_in1k)|256 |82.26|96.07|44.6 |10.6 |22.2 |1542 |
|[resnet101.a2_in1k](https://huggingface.co/timm/resnet101.a2_in1k)|288 |82.24|95.73|44.6 |13.0 |26.8 |1290 |
|[seresnext50_32x4d.racm_in1k](https://huggingface.co/timm/seresnext50_32x4d.racm_in1k)|288 |82.2 |96.14|27.6 |7.0 |23.8 |1547 |
|[ecaresnet101d.miil_in1k](https://huggingface.co/timm/ecaresnet101d.miil_in1k)|224 |82.18|96.05|44.6 |8.1 |17.1 |1771 |
|[resnext50_32x4d.fb_swsl_ig1b_ft_in1k](https://huggingface.co/timm/resnext50_32x4d.fb_swsl_ig1b_ft_in1k)|224 |82.17|96.22|25.0 |4.3 |14.4 |2943 |
|[ecaresnet50t.a1_in1k](https://huggingface.co/timm/ecaresnet50t.a1_in1k)|288 |82.12|95.65|25.6 |7.1 |19.6 |1704 |
|[resnext50_32x4d.a1h_in1k](https://huggingface.co/timm/resnext50_32x4d.a1h_in1k)|288 |82.03|95.94|25.0 |7.0 |23.8 |1745 |
|[ecaresnet101d_pruned.miil_in1k](https://huggingface.co/timm/ecaresnet101d_pruned.miil_in1k)|288 |82.0 |96.15|24.9 |5.8 |12.7 |1787 |
|[resnet61q.ra2_in1k](https://huggingface.co/timm/resnet61q.ra2_in1k)|256 |81.99|95.85|36.8 |7.8 |17.0 |2230 |
|[resnext101_32x8d.tv2_in1k](https://huggingface.co/timm/resnext101_32x8d.tv2_in1k)|176 |81.98|95.72|88.8 |10.3 |19.4 |1768 |
|[resnet152.a1_in1k](https://huggingface.co/timm/resnet152.a1_in1k)|224 |81.97|95.24|60.2 |11.6 |22.6 |1486 |
|[resnet101.a1h_in1k](https://huggingface.co/timm/resnet101.a1h_in1k)|224 |81.93|95.75|44.6 |7.8 |16.2 |2122 |
|[resnet101.tv2_in1k](https://huggingface.co/timm/resnet101.tv2_in1k)|224 |81.9 |95.77|44.6 |7.8 |16.2 |2118 |
|[resnext101_32x16d.fb_ssl_yfcc100m_ft_in1k](https://huggingface.co/timm/resnext101_32x16d.fb_ssl_yfcc100m_ft_in1k)|224 |81.84|96.1 |194.0 |36.3 |51.2 |583 |
|[resnet51q.ra2_in1k](https://huggingface.co/timm/resnet51q.ra2_in1k)|256 |81.78|95.94|35.7 |6.4 |16.6 |2471 |
|[resnet152.a2_in1k](https://huggingface.co/timm/resnet152.a2_in1k)|224 |81.77|95.22|60.2 |11.6 |22.6 |1485 |
|[resnetaa50d.sw_in12k_ft_in1k](https://huggingface.co/timm/resnetaa50d.sw_in12k_ft_in1k)|224 |81.74|96.06|25.6 |5.4 |12.4 |2813 |
|[ecaresnet50t.a2_in1k](https://huggingface.co/timm/ecaresnet50t.a2_in1k)|288 |81.65|95.54|25.6 |7.1 |19.6 |1703 |
|[ecaresnet50d.miil_in1k](https://huggingface.co/timm/ecaresnet50d.miil_in1k)|288 |81.64|95.88|25.6 |7.2 |19.7 |1694 |
|[resnext101_32x8d.fb_ssl_yfcc100m_ft_in1k](https://huggingface.co/timm/resnext101_32x8d.fb_ssl_yfcc100m_ft_in1k)|224 |81.62|96.04|88.8 |16.5 |31.2 |1101 |
|[wide_resnet50_2.tv2_in1k](https://huggingface.co/timm/wide_resnet50_2.tv2_in1k)|224 |81.61|95.76|68.9 |11.4 |14.4 |1930 |
|[resnetaa50.a1h_in1k](https://huggingface.co/timm/resnetaa50.a1h_in1k)|288 |81.61|95.83|25.6 |8.5 |19.2 |1868 |
|[resnet101.a1_in1k](https://huggingface.co/timm/resnet101.a1_in1k)|224 |81.5 |95.16|44.6 |7.8 |16.2 |2125 |
|[resnext50_32x4d.a1_in1k](https://huggingface.co/timm/resnext50_32x4d.a1_in1k)|288 |81.48|95.16|25.0 |7.0 |23.8 |1745 |
|[gcresnet50t.ra2_in1k](https://huggingface.co/timm/gcresnet50t.ra2_in1k)|288 |81.47|95.71|25.9 |6.9 |18.6 |2071 |
|[wide_resnet50_2.racm_in1k](https://huggingface.co/timm/wide_resnet50_2.racm_in1k)|224 |81.45|95.53|68.9 |11.4 |14.4 |1929 |
|[resnet50d.a1_in1k](https://huggingface.co/timm/resnet50d.a1_in1k)|288 |81.44|95.22|25.6 |7.2 |19.7 |1908 |
|[ecaresnet50t.ra2_in1k](https://huggingface.co/timm/ecaresnet50t.ra2_in1k)|256 |81.44|95.67|25.6 |5.6 |15.4 |2168 |
|[ecaresnetlight.miil_in1k](https://huggingface.co/timm/ecaresnetlight.miil_in1k)|288 |81.4 |95.82|30.2 |6.8 |13.9 |2132 |
|[resnet50d.ra2_in1k](https://huggingface.co/timm/resnet50d.ra2_in1k)|288 |81.37|95.74|25.6 |7.2 |19.7 |1910 |
|[resnet101.a2_in1k](https://huggingface.co/timm/resnet101.a2_in1k)|224 |81.32|95.19|44.6 |7.8 |16.2 |2125 |
|[seresnet50.ra2_in1k](https://huggingface.co/timm/seresnet50.ra2_in1k)|288 |81.3 |95.65|28.1 |6.8 |18.4 |1803 |
|[resnext50_32x4d.a2_in1k](https://huggingface.co/timm/resnext50_32x4d.a2_in1k)|288 |81.3 |95.11|25.0 |7.0 |23.8 |1746 |
|[seresnext50_32x4d.racm_in1k](https://huggingface.co/timm/seresnext50_32x4d.racm_in1k)|224 |81.27|95.62|27.6 |4.3 |14.4 |2591 |
|[ecaresnet50t.a1_in1k](https://huggingface.co/timm/ecaresnet50t.a1_in1k)|224 |81.26|95.16|25.6 |4.3 |11.8 |2823 |
|[gcresnext50ts.ch_in1k](https://huggingface.co/timm/gcresnext50ts.ch_in1k)|288 |81.23|95.54|15.7 |4.8 |19.6 |2117 |
|[senet154.gluon_in1k](https://huggingface.co/timm/senet154.gluon_in1k)|224 |81.23|95.35|115.1 |20.8 |38.7 |545 |
|[resnet50.a1_in1k](https://huggingface.co/timm/resnet50.a1_in1k)|288 |81.22|95.11|25.6 |6.8 |18.4 |2089 |
|[resnet50_gn.a1h_in1k](https://huggingface.co/timm/resnet50_gn.a1h_in1k)|288 |81.22|95.63|25.6 |6.8 |18.4 |676 |
|[resnet50d.a2_in1k](https://huggingface.co/timm/resnet50d.a2_in1k)|288 |81.18|95.09|25.6 |7.2 |19.7 |1908 |
|[resnet50.fb_swsl_ig1b_ft_in1k](https://huggingface.co/timm/resnet50.fb_swsl_ig1b_ft_in1k)|224 |81.18|95.98|25.6 |4.1 |11.1 |3455 |
|[resnext50_32x4d.tv2_in1k](https://huggingface.co/timm/resnext50_32x4d.tv2_in1k)|224 |81.17|95.34|25.0 |4.3 |14.4 |2933 |
|[resnext50_32x4d.a1h_in1k](https://huggingface.co/timm/resnext50_32x4d.a1h_in1k)|224 |81.1 |95.33|25.0 |4.3 |14.4 |2934 |
|[seresnet50.a2_in1k](https://huggingface.co/timm/seresnet50.a2_in1k)|288 |81.1 |95.23|28.1 |6.8 |18.4 |1801 |
|[seresnet50.a1_in1k](https://huggingface.co/timm/seresnet50.a1_in1k)|288 |81.1 |95.12|28.1 |6.8 |18.4 |1799 |
|[resnet152s.gluon_in1k](https://huggingface.co/timm/resnet152s.gluon_in1k)|224 |81.02|95.41|60.3 |12.9 |25.0 |1347 |
|[resnet50.d_in1k](https://huggingface.co/timm/resnet50.d_in1k)|288 |80.97|95.44|25.6 |6.8 |18.4 |2085 |
|[gcresnet50t.ra2_in1k](https://huggingface.co/timm/gcresnet50t.ra2_in1k)|256 |80.94|95.45|25.9 |5.4 |14.7 |2571 |
|[resnext101_32x4d.fb_ssl_yfcc100m_ft_in1k](https://huggingface.co/timm/resnext101_32x4d.fb_ssl_yfcc100m_ft_in1k)|224 |80.93|95.73|44.2 |8.0 |21.2 |1814 |
|[resnet50.c1_in1k](https://huggingface.co/timm/resnet50.c1_in1k)|288 |80.91|95.55|25.6 |6.8 |18.4 |2084 |
|[seresnext101_32x4d.gluon_in1k](https://huggingface.co/timm/seresnext101_32x4d.gluon_in1k)|224 |80.9 |95.31|49.0 |8.0 |21.3 |1585 |
|[seresnext101_64x4d.gluon_in1k](https://huggingface.co/timm/seresnext101_64x4d.gluon_in1k)|224 |80.9 |95.3 |88.2 |15.5 |31.2 |918 |
|[resnet50.c2_in1k](https://huggingface.co/timm/resnet50.c2_in1k)|288 |80.86|95.52|25.6 |6.8 |18.4 |2085 |
|[resnet50.tv2_in1k](https://huggingface.co/timm/resnet50.tv2_in1k)|224 |80.85|95.43|25.6 |4.1 |11.1 |3450 |
|[ecaresnet50t.a2_in1k](https://huggingface.co/timm/ecaresnet50t.a2_in1k)|224 |80.84|95.02|25.6 |4.3 |11.8 |2821 |
|[ecaresnet101d_pruned.miil_in1k](https://huggingface.co/timm/ecaresnet101d_pruned.miil_in1k)|224 |80.79|95.62|24.9 |3.5 |7.7 |2961 |
|[seresnet33ts.ra2_in1k](https://huggingface.co/timm/seresnet33ts.ra2_in1k)|288 |80.79|95.36|19.8 |6.0 |14.8 |2506 |
|[ecaresnet50d_pruned.miil_in1k](https://huggingface.co/timm/ecaresnet50d_pruned.miil_in1k)|288 |80.79|95.58|19.9 |4.2 |10.6 |2349 |
|[resnet50.a2_in1k](https://huggingface.co/timm/resnet50.a2_in1k)|288 |80.78|94.99|25.6 |6.8 |18.4 |2088 |
|[resnet50.b1k_in1k](https://huggingface.co/timm/resnet50.b1k_in1k)|288 |80.71|95.43|25.6 |6.8 |18.4 |2087 |
|[resnext50_32x4d.ra_in1k](https://huggingface.co/timm/resnext50_32x4d.ra_in1k)|288 |80.7 |95.39|25.0 |7.0 |23.8 |1749 |
|[resnetrs101.tf_in1k](https://huggingface.co/timm/resnetrs101.tf_in1k)|192 |80.69|95.24|63.6 |6.0 |12.7 |2270 |
|[resnet50d.a1_in1k](https://huggingface.co/timm/resnet50d.a1_in1k)|224 |80.68|94.71|25.6 |4.4 |11.9 |3162 |
|[eca_resnet33ts.ra2_in1k](https://huggingface.co/timm/eca_resnet33ts.ra2_in1k)|288 |80.68|95.36|19.7 |6.0 |14.8 |2637 |
|[resnet50.a1h_in1k](https://huggingface.co/timm/resnet50.a1h_in1k)|224 |80.67|95.3 |25.6 |4.1 |11.1 |3452 |
|[resnext50d_32x4d.bt_in1k](https://huggingface.co/timm/resnext50d_32x4d.bt_in1k)|288 |80.67|95.42|25.0 |7.4 |25.1 |1626 |
|[resnetaa50.a1h_in1k](https://huggingface.co/timm/resnetaa50.a1h_in1k)|224 |80.63|95.21|25.6 |5.2 |11.6 |3034 |
|[ecaresnet50d.miil_in1k](https://huggingface.co/timm/ecaresnet50d.miil_in1k)|224 |80.61|95.32|25.6 |4.4 |11.9 |2813 |
|[resnext101_64x4d.gluon_in1k](https://huggingface.co/timm/resnext101_64x4d.gluon_in1k)|224 |80.61|94.99|83.5 |15.5 |31.2 |989 |
|[gcresnet33ts.ra2_in1k](https://huggingface.co/timm/gcresnet33ts.ra2_in1k)|288 |80.6 |95.31|19.9 |6.0 |14.8 |2578 |
|[gcresnext50ts.ch_in1k](https://huggingface.co/timm/gcresnext50ts.ch_in1k)|256 |80.57|95.17|15.7 |3.8 |15.5 |2710 |
|[resnet152.a3_in1k](https://huggingface.co/timm/resnet152.a3_in1k)|224 |80.56|95.0 |60.2 |11.6 |22.6 |1483 |
|[resnet50d.ra2_in1k](https://huggingface.co/timm/resnet50d.ra2_in1k)|224 |80.53|95.16|25.6 |4.4 |11.9 |3164 |
|[resnext50_32x4d.a1_in1k](https://huggingface.co/timm/resnext50_32x4d.a1_in1k)|224 |80.53|94.46|25.0 |4.3 |14.4 |2930 |
|[wide_resnet101_2.tv2_in1k](https://huggingface.co/timm/wide_resnet101_2.tv2_in1k)|176 |80.48|94.98|126.9 |14.3 |13.2 |1719 |
|[resnet152d.gluon_in1k](https://huggingface.co/timm/resnet152d.gluon_in1k)|224 |80.47|95.2 |60.2 |11.8 |23.4 |1428 |
|[resnet50.b2k_in1k](https://huggingface.co/timm/resnet50.b2k_in1k)|288 |80.45|95.32|25.6 |6.8 |18.4 |2086 |
|[ecaresnetlight.miil_in1k](https://huggingface.co/timm/ecaresnetlight.miil_in1k)|224 |80.45|95.24|30.2 |4.1 |8.4 |3530 |
|[resnext50_32x4d.a2_in1k](https://huggingface.co/timm/resnext50_32x4d.a2_in1k)|224 |80.45|94.63|25.0 |4.3 |14.4 |2936 |
|[wide_resnet50_2.tv2_in1k](https://huggingface.co/timm/wide_resnet50_2.tv2_in1k)|176 |80.43|95.09|68.9 |7.3 |9.0 |3015 |
|[resnet101d.gluon_in1k](https://huggingface.co/timm/resnet101d.gluon_in1k)|224 |80.42|95.01|44.6 |8.1 |17.0 |2007 |
|[resnet50.a1_in1k](https://huggingface.co/timm/resnet50.a1_in1k)|224 |80.38|94.6 |25.6 |4.1 |11.1 |3461 |
|[seresnet33ts.ra2_in1k](https://huggingface.co/timm/seresnet33ts.ra2_in1k)|256 |80.36|95.1 |19.8 |4.8 |11.7 |3267 |
|[resnext101_32x4d.gluon_in1k](https://huggingface.co/timm/resnext101_32x4d.gluon_in1k)|224 |80.34|94.93|44.2 |8.0 |21.2 |1814 |
|[resnext50_32x4d.fb_ssl_yfcc100m_ft_in1k](https://huggingface.co/timm/resnext50_32x4d.fb_ssl_yfcc100m_ft_in1k)|224 |80.32|95.4 |25.0 |4.3 |14.4 |2941 |
|[resnet101s.gluon_in1k](https://huggingface.co/timm/resnet101s.gluon_in1k)|224 |80.28|95.16|44.7 |9.2 |18.6 |1851 |
|[seresnet50.ra2_in1k](https://huggingface.co/timm/seresnet50.ra2_in1k)|224 |80.26|95.08|28.1 |4.1 |11.1 |2972 |
|[resnetblur50.bt_in1k](https://huggingface.co/timm/resnetblur50.bt_in1k)|288 |80.24|95.24|25.6 |8.5 |19.9 |1523 |
|[resnet50d.a2_in1k](https://huggingface.co/timm/resnet50d.a2_in1k)|224 |80.22|94.63|25.6 |4.4 |11.9 |3162 |
|[resnet152.tv2_in1k](https://huggingface.co/timm/resnet152.tv2_in1k)|176 |80.2 |94.64|60.2 |7.2 |14.0 |2346 |
|[seresnet50.a2_in1k](https://huggingface.co/timm/seresnet50.a2_in1k)|224 |80.08|94.74|28.1 |4.1 |11.1 |2969 |
|[eca_resnet33ts.ra2_in1k](https://huggingface.co/timm/eca_resnet33ts.ra2_in1k)|256 |80.08|94.97|19.7 |4.8 |11.7 |3284 |
|[gcresnet33ts.ra2_in1k](https://huggingface.co/timm/gcresnet33ts.ra2_in1k)|256 |80.06|94.99|19.9 |4.8 |11.7 |3216 |
|[resnet50_gn.a1h_in1k](https://huggingface.co/timm/resnet50_gn.a1h_in1k)|224 |80.06|94.95|25.6 |4.1 |11.1 |1109 |
|[seresnet50.a1_in1k](https://huggingface.co/timm/seresnet50.a1_in1k)|224 |80.02|94.71|28.1 |4.1 |11.1 |2962 |
|[resnet50.ram_in1k](https://huggingface.co/timm/resnet50.ram_in1k)|288 |79.97|95.05|25.6 |6.8 |18.4 |2086 |
|[resnet152c.gluon_in1k](https://huggingface.co/timm/resnet152c.gluon_in1k)|224 |79.92|94.84|60.2 |11.8 |23.4 |1455 |
|[seresnext50_32x4d.gluon_in1k](https://huggingface.co/timm/seresnext50_32x4d.gluon_in1k)|224 |79.91|94.82|27.6 |4.3 |14.4 |2591 |
|[resnet50.d_in1k](https://huggingface.co/timm/resnet50.d_in1k)|224 |79.91|94.67|25.6 |4.1 |11.1 |3456 |
|[resnet101.tv2_in1k](https://huggingface.co/timm/resnet101.tv2_in1k)|176 |79.9 |94.6 |44.6 |4.9 |10.1 |3341 |
|[resnetrs50.tf_in1k](https://huggingface.co/timm/resnetrs50.tf_in1k)|224 |79.89|94.97|35.7 |4.5 |12.1 |2774 |
|[resnet50.c2_in1k](https://huggingface.co/timm/resnet50.c2_in1k)|224 |79.88|94.87|25.6 |4.1 |11.1 |3455 |
|[ecaresnet26t.ra2_in1k](https://huggingface.co/timm/ecaresnet26t.ra2_in1k)|320 |79.86|95.07|16.0 |5.2 |16.4 |2168 |
|[resnet50.a2_in1k](https://huggingface.co/timm/resnet50.a2_in1k)|224 |79.85|94.56|25.6 |4.1 |11.1 |3460 |
|[resnet50.ra_in1k](https://huggingface.co/timm/resnet50.ra_in1k)|288 |79.83|94.97|25.6 |6.8 |18.4 |2087 |
|[resnet101.a3_in1k](https://huggingface.co/timm/resnet101.a3_in1k)|224 |79.82|94.62|44.6 |7.8 |16.2 |2114 |
|[resnext50_32x4d.ra_in1k](https://huggingface.co/timm/resnext50_32x4d.ra_in1k)|224 |79.76|94.6 |25.0 |4.3 |14.4 |2943 |
|[resnet50.c1_in1k](https://huggingface.co/timm/resnet50.c1_in1k)|224 |79.74|94.95|25.6 |4.1 |11.1 |3455 |
|[ecaresnet50d_pruned.miil_in1k](https://huggingface.co/timm/ecaresnet50d_pruned.miil_in1k)|224 |79.74|94.87|19.9 |2.5 |6.4 |3929 |
|[resnet33ts.ra2_in1k](https://huggingface.co/timm/resnet33ts.ra2_in1k)|288 |79.71|94.83|19.7 |6.0 |14.8 |2710 |
|[resnet152.gluon_in1k](https://huggingface.co/timm/resnet152.gluon_in1k)|224 |79.68|94.74|60.2 |11.6 |22.6 |1486 |
|[resnext50d_32x4d.bt_in1k](https://huggingface.co/timm/resnext50d_32x4d.bt_in1k)|224 |79.67|94.87|25.0 |4.5 |15.2 |2729 |
|[resnet50.bt_in1k](https://huggingface.co/timm/resnet50.bt_in1k)|288 |79.63|94.91|25.6 |6.8 |18.4 |2086 |
|[ecaresnet50t.a3_in1k](https://huggingface.co/timm/ecaresnet50t.a3_in1k)|224 |79.56|94.72|25.6 |4.3 |11.8 |2805 |
|[resnet101c.gluon_in1k](https://huggingface.co/timm/resnet101c.gluon_in1k)|224 |79.53|94.58|44.6 |8.1 |17.0 |2062 |
|[resnet50.b1k_in1k](https://huggingface.co/timm/resnet50.b1k_in1k)|224 |79.52|94.61|25.6 |4.1 |11.1 |3459 |
|[resnet50.tv2_in1k](https://huggingface.co/timm/resnet50.tv2_in1k)|176 |79.42|94.64|25.6 |2.6 |6.9 |5397 |
|[resnet32ts.ra2_in1k](https://huggingface.co/timm/resnet32ts.ra2_in1k)|288 |79.4 |94.66|18.0 |5.9 |14.6 |2752 |
|[resnet50.b2k_in1k](https://huggingface.co/timm/resnet50.b2k_in1k)|224 |79.38|94.57|25.6 |4.1 |11.1 |3459 |
|[resnext50_32x4d.tv2_in1k](https://huggingface.co/timm/resnext50_32x4d.tv2_in1k)|176 |79.37|94.3 |25.0 |2.7 |9.0 |4577 |
|[resnext50_32x4d.gluon_in1k](https://huggingface.co/timm/resnext50_32x4d.gluon_in1k)|224 |79.36|94.43|25.0 |4.3 |14.4 |2942 |
|[resnext101_32x8d.tv_in1k](https://huggingface.co/timm/resnext101_32x8d.tv_in1k)|224 |79.31|94.52|88.8 |16.5 |31.2 |1100 |
|[resnet101.gluon_in1k](https://huggingface.co/timm/resnet101.gluon_in1k)|224 |79.31|94.53|44.6 |7.8 |16.2 |2125 |
|[resnetblur50.bt_in1k](https://huggingface.co/timm/resnetblur50.bt_in1k)|224 |79.31|94.63|25.6 |5.2 |12.0 |2524 |
|[resnet50.a1h_in1k](https://huggingface.co/timm/resnet50.a1h_in1k)|176 |79.27|94.49|25.6 |2.6 |6.9 |5404 |
|[resnext50_32x4d.a3_in1k](https://huggingface.co/timm/resnext50_32x4d.a3_in1k)|224 |79.25|94.31|25.0 |4.3 |14.4 |2931 |
|[resnet50.fb_ssl_yfcc100m_ft_in1k](https://huggingface.co/timm/resnet50.fb_ssl_yfcc100m_ft_in1k)|224 |79.22|94.84|25.6 |4.1 |11.1 |3451 |
|[resnet33ts.ra2_in1k](https://huggingface.co/timm/resnet33ts.ra2_in1k)|256 |79.21|94.56|19.7 |4.8 |11.7 |3392 |
|[resnet50d.gluon_in1k](https://huggingface.co/timm/resnet50d.gluon_in1k)|224 |79.07|94.48|25.6 |4.4 |11.9 |3162 |
|[resnet50.ram_in1k](https://huggingface.co/timm/resnet50.ram_in1k)|224 |79.03|94.38|25.6 |4.1 |11.1 |3453 |
|[resnet50.am_in1k](https://huggingface.co/timm/resnet50.am_in1k)|224 |79.01|94.39|25.6 |4.1 |11.1 |3461 |
|[resnet32ts.ra2_in1k](https://huggingface.co/timm/resnet32ts.ra2_in1k)|256 |79.01|94.37|18.0 |4.6 |11.6 |3440 |
|[ecaresnet26t.ra2_in1k](https://huggingface.co/timm/ecaresnet26t.ra2_in1k)|256 |78.9 |94.54|16.0 |3.4 |10.5 |3421 |
|[resnet152.a3_in1k](https://huggingface.co/timm/resnet152.a3_in1k)|160 |78.89|94.11|60.2 |5.9 |11.5 |2745 |
|[wide_resnet101_2.tv_in1k](https://huggingface.co/timm/wide_resnet101_2.tv_in1k)|224 |78.84|94.28|126.9 |22.8 |21.2 |1079 |
|[seresnext26d_32x4d.bt_in1k](https://huggingface.co/timm/seresnext26d_32x4d.bt_in1k)|288 |78.83|94.24|16.8 |4.5 |16.8 |2251 |
|[resnet50.ra_in1k](https://huggingface.co/timm/resnet50.ra_in1k)|224 |78.81|94.32|25.6 |4.1 |11.1 |3454 |
|[seresnext26t_32x4d.bt_in1k](https://huggingface.co/timm/seresnext26t_32x4d.bt_in1k)|288 |78.74|94.33|16.8 |4.5 |16.7 |2264 |
|[resnet50s.gluon_in1k](https://huggingface.co/timm/resnet50s.gluon_in1k)|224 |78.72|94.23|25.7 |5.5 |13.5 |2796 |
|[resnet50d.a3_in1k](https://huggingface.co/timm/resnet50d.a3_in1k)|224 |78.71|94.24|25.6 |4.4 |11.9 |3154 |
|[wide_resnet50_2.tv_in1k](https://huggingface.co/timm/wide_resnet50_2.tv_in1k)|224 |78.47|94.09|68.9 |11.4 |14.4 |1934 |
|[resnet50.bt_in1k](https://huggingface.co/timm/resnet50.bt_in1k)|224 |78.46|94.27|25.6 |4.1 |11.1 |3454 |
|[resnet34d.ra2_in1k](https://huggingface.co/timm/resnet34d.ra2_in1k)|288 |78.43|94.35|21.8 |6.5 |7.5 |3291 |
|[gcresnext26ts.ch_in1k](https://huggingface.co/timm/gcresnext26ts.ch_in1k)|288 |78.42|94.04|10.5 |3.1 |13.3 |3226 |
|[resnet26t.ra2_in1k](https://huggingface.co/timm/resnet26t.ra2_in1k)|320 |78.33|94.13|16.0 |5.2 |16.4 |2391 |
|[resnet152.tv_in1k](https://huggingface.co/timm/resnet152.tv_in1k)|224 |78.32|94.04|60.2 |11.6 |22.6 |1487 |
|[seresnext26ts.ch_in1k](https://huggingface.co/timm/seresnext26ts.ch_in1k)|288 |78.28|94.1 |10.4 |3.1 |13.3 |3062 |
|[bat_resnext26ts.ch_in1k](https://huggingface.co/timm/bat_resnext26ts.ch_in1k)|256 |78.25|94.1 |10.7 |2.5 |12.5 |3393 |
|[resnet50.a3_in1k](https://huggingface.co/timm/resnet50.a3_in1k)|224 |78.06|93.78|25.6 |4.1 |11.1 |3450 |
|[resnet50c.gluon_in1k](https://huggingface.co/timm/resnet50c.gluon_in1k)|224 |78.0 |93.99|25.6 |4.4 |11.9 |3286 |
|[eca_resnext26ts.ch_in1k](https://huggingface.co/timm/eca_resnext26ts.ch_in1k)|288 |78.0 |93.91|10.3 |3.1 |13.3 |3297 |
|[seresnext26t_32x4d.bt_in1k](https://huggingface.co/timm/seresnext26t_32x4d.bt_in1k)|224 |77.98|93.75|16.8 |2.7 |10.1 |3841 |
|[resnet34.a1_in1k](https://huggingface.co/timm/resnet34.a1_in1k)|288 |77.92|93.77|21.8 |6.1 |6.2 |3609 |
|[resnet101.a3_in1k](https://huggingface.co/timm/resnet101.a3_in1k)|160 |77.88|93.71|44.6 |4.0 |8.3 |3926 |
|[resnet26t.ra2_in1k](https://huggingface.co/timm/resnet26t.ra2_in1k)|256 |77.87|93.84|16.0 |3.4 |10.5 |3772 |
|[seresnext26ts.ch_in1k](https://huggingface.co/timm/seresnext26ts.ch_in1k)|256 |77.86|93.79|10.4 |2.4 |10.5 |4263 |
|[resnetrs50.tf_in1k](https://huggingface.co/timm/resnetrs50.tf_in1k)|160 |77.82|93.81|35.7 |2.3 |6.2 |5238 |
|[gcresnext26ts.ch_in1k](https://huggingface.co/timm/gcresnext26ts.ch_in1k)|256 |77.81|93.82|10.5 |2.4 |10.5 |4183 |
|[ecaresnet50t.a3_in1k](https://huggingface.co/timm/ecaresnet50t.a3_in1k)|160 |77.79|93.6 |25.6 |2.2 |6.0 |5329 |
|[resnext50_32x4d.a3_in1k](https://huggingface.co/timm/resnext50_32x4d.a3_in1k)|160 |77.73|93.32|25.0 |2.2 |7.4 |5576 |
|[resnext50_32x4d.tv_in1k](https://huggingface.co/timm/resnext50_32x4d.tv_in1k)|224 |77.61|93.7 |25.0 |4.3 |14.4 |2944 |
|[seresnext26d_32x4d.bt_in1k](https://huggingface.co/timm/seresnext26d_32x4d.bt_in1k)|224 |77.59|93.61|16.8 |2.7 |10.2 |3807 |
|[resnet50.gluon_in1k](https://huggingface.co/timm/resnet50.gluon_in1k)|224 |77.58|93.72|25.6 |4.1 |11.1 |3455 |
|[eca_resnext26ts.ch_in1k](https://huggingface.co/timm/eca_resnext26ts.ch_in1k)|256 |77.44|93.56|10.3 |2.4 |10.5 |4284 |
|[resnet26d.bt_in1k](https://huggingface.co/timm/resnet26d.bt_in1k)|288 |77.41|93.63|16.0 |4.3 |13.5 |2907 |
|[resnet101.tv_in1k](https://huggingface.co/timm/resnet101.tv_in1k)|224 |77.38|93.54|44.6 |7.8 |16.2 |2125 |
|[resnet50d.a3_in1k](https://huggingface.co/timm/resnet50d.a3_in1k)|160 |77.22|93.27|25.6 |2.2 |6.1 |5982 |
|[resnext26ts.ra2_in1k](https://huggingface.co/timm/resnext26ts.ra2_in1k)|288 |77.17|93.47|10.3 |3.1 |13.3 |3392 |
|[resnet34.a2_in1k](https://huggingface.co/timm/resnet34.a2_in1k)|288 |77.15|93.27|21.8 |6.1 |6.2 |3615 |
|[resnet34d.ra2_in1k](https://huggingface.co/timm/resnet34d.ra2_in1k)|224 |77.1 |93.37|21.8 |3.9 |4.5 |5436 |
|[seresnet50.a3_in1k](https://huggingface.co/timm/seresnet50.a3_in1k)|224 |77.02|93.07|28.1 |4.1 |11.1 |2952 |
|[resnext26ts.ra2_in1k](https://huggingface.co/timm/resnext26ts.ra2_in1k)|256 |76.78|93.13|10.3 |2.4 |10.5 |4410 |
|[resnet26d.bt_in1k](https://huggingface.co/timm/resnet26d.bt_in1k)|224 |76.7 |93.17|16.0 |2.6 |8.2 |4859 |
|[resnet34.bt_in1k](https://huggingface.co/timm/resnet34.bt_in1k)|288 |76.5 |93.35|21.8 |6.1 |6.2 |3617 |
|[resnet34.a1_in1k](https://huggingface.co/timm/resnet34.a1_in1k)|224 |76.42|92.87|21.8 |3.7 |3.7 |5984 |
|[resnet26.bt_in1k](https://huggingface.co/timm/resnet26.bt_in1k)|288 |76.35|93.18|16.0 |3.9 |12.2 |3331 |
|[resnet50.tv_in1k](https://huggingface.co/timm/resnet50.tv_in1k)|224 |76.13|92.86|25.6 |4.1 |11.1 |3457 |
|[resnet50.a3_in1k](https://huggingface.co/timm/resnet50.a3_in1k)|160 |75.96|92.5 |25.6 |2.1 |5.7 |6490 |
|[resnet34.a2_in1k](https://huggingface.co/timm/resnet34.a2_in1k)|224 |75.52|92.44|21.8 |3.7 |3.7 |5991 |
|[resnet26.bt_in1k](https://huggingface.co/timm/resnet26.bt_in1k)|224 |75.3 |92.58|16.0 |2.4 |7.4 |5583 |
|[resnet34.bt_in1k](https://huggingface.co/timm/resnet34.bt_in1k)|224 |75.16|92.18|21.8 |3.7 |3.7 |5994 |
|[seresnet50.a3_in1k](https://huggingface.co/timm/seresnet50.a3_in1k)|160 |75.1 |92.08|28.1 |2.1 |5.7 |5513 |
|[resnet34.gluon_in1k](https://huggingface.co/timm/resnet34.gluon_in1k)|224 |74.57|91.98|21.8 |3.7 |3.7 |5984 |
|[resnet18d.ra2_in1k](https://huggingface.co/timm/resnet18d.ra2_in1k)|288 |73.81|91.83|11.7 |3.4 |5.4 |5196 |
|[resnet34.tv_in1k](https://huggingface.co/timm/resnet34.tv_in1k)|224 |73.32|91.42|21.8 |3.7 |3.7 |5979 |
|[resnet18.fb_swsl_ig1b_ft_in1k](https://huggingface.co/timm/resnet18.fb_swsl_ig1b_ft_in1k)|224 |73.28|91.73|11.7 |1.8 |2.5 |10213 |
|[resnet18.a1_in1k](https://huggingface.co/timm/resnet18.a1_in1k)|288 |73.16|91.03|11.7 |3.0 |4.1 |6050 |
|[resnet34.a3_in1k](https://huggingface.co/timm/resnet34.a3_in1k)|224 |72.98|91.11|21.8 |3.7 |3.7 |5967 |
|[resnet18.fb_ssl_yfcc100m_ft_in1k](https://huggingface.co/timm/resnet18.fb_ssl_yfcc100m_ft_in1k)|224 |72.6 |91.42|11.7 |1.8 |2.5 |10213 |
|[resnet18.a2_in1k](https://huggingface.co/timm/resnet18.a2_in1k)|288 |72.37|90.59|11.7 |3.0 |4.1 |6051 |
|[resnet14t.c3_in1k](https://huggingface.co/timm/resnet14t.c3_in1k)|224 |72.26|90.31|10.1 |1.7 |5.8 |7026 |
|[resnet18d.ra2_in1k](https://huggingface.co/timm/resnet18d.ra2_in1k)|224 |72.26|90.68|11.7 |2.1 |3.3 |8707 |
|[resnet18.a1_in1k](https://huggingface.co/timm/resnet18.a1_in1k)|224 |71.49|90.07|11.7 |1.8 |2.5 |10187 |
|[resnet14t.c3_in1k](https://huggingface.co/timm/resnet14t.c3_in1k)|176 |71.31|89.69|10.1 |1.1 |3.6 |10970 |
|[resnet18.gluon_in1k](https://huggingface.co/timm/resnet18.gluon_in1k)|224 |70.84|89.76|11.7 |1.8 |2.5 |10210 |
|[resnet18.a2_in1k](https://huggingface.co/timm/resnet18.a2_in1k)|224 |70.64|89.47|11.7 |1.8 |2.5 |10194 |
|[resnet34.a3_in1k](https://huggingface.co/timm/resnet34.a3_in1k)|160 |70.56|89.52|21.8 |1.9 |1.9 |10737 |
|[resnet18.tv_in1k](https://huggingface.co/timm/resnet18.tv_in1k)|224 |69.76|89.07|11.7 |1.8 |2.5 |10205 |
|[resnet10t.c3_in1k](https://huggingface.co/timm/resnet10t.c3_in1k)|224 |68.34|88.03|5.4 |1.1 |2.4 |13079 |
|[resnet18.a3_in1k](https://huggingface.co/timm/resnet18.a3_in1k)|224 |68.25|88.17|11.7 |1.8 |2.5 |10167 |
|[resnet10t.c3_in1k](https://huggingface.co/timm/resnet10t.c3_in1k)|176 |66.71|86.96|5.4 |0.7 |1.5 |20327 |
|[resnet18.a3_in1k](https://huggingface.co/timm/resnet18.a3_in1k)|160 |65.66|86.26|11.7 |0.9 |1.3 |18229 |
## Citation
```bibtex
@inproceedings{wightman2021resnet,
title={ResNet strikes back: An improved training procedure in timm},
author={Wightman, Ross and Touvron, Hugo and Jegou, Herve},
booktitle={NeurIPS 2021 Workshop on ImageNet: Past, Present, and Future}
}
```
```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}}
}
```
```bibtex
@article{He2015,
author = {Kaiming He and Xiangyu Zhang and Shaoqing Ren and Jian Sun},
title = {Deep Residual Learning for Image Recognition},
journal = {arXiv preprint arXiv:1512.03385},
year = {2015}
}
```
|
Ayansk11/Image_Caption_using_ViT_GPT2 | Ayansk11 | 2023-10-20T08:57:32Z | 733 | 1 | transformers | [
"transformers",
"pytorch",
"vision-encoder-decoder",
"image-to-text",
"image-captioning",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | image-to-text | 2023-10-20T08:54:18Z | ---
tags:
- image-to-text
- image-captioning
license: apache-2.0
widget:
- src: https://huggingface.co/datasets/mishig/sample_images/resolve/main/savanna.jpg
example_title: Savanna
- src: https://huggingface.co/datasets/mishig/sample_images/resolve/main/football-match.jpg
example_title: Football Match
- src: https://huggingface.co/datasets/mishig/sample_images/resolve/main/airport.jpg
example_title: Airport
---
# nlpconnect/vit-gpt2-image-captioning
This is an image captioning model trained by @ydshieh in [flax ](https://github.com/huggingface/transformers/tree/main/examples/flax/image-captioning) this is pytorch version of [this](https://huggingface.co/ydshieh/vit-gpt2-coco-en-ckpts).
# The Illustrated Image Captioning using transformers
* https://ankur3107.github.io/blogs/the-illustrated-image-captioning-using-transformers/
# Sample running code
```python
from transformers import VisionEncoderDecoderModel, ViTImageProcessor, AutoTokenizer
import torch
from PIL import Image
model = VisionEncoderDecoderModel.from_pretrained("nlpconnect/vit-gpt2-image-captioning")
feature_extractor = ViTImageProcessor.from_pretrained("nlpconnect/vit-gpt2-image-captioning")
tokenizer = AutoTokenizer.from_pretrained("nlpconnect/vit-gpt2-image-captioning")
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
model.to(device)
max_length = 16
num_beams = 4
gen_kwargs = {"max_length": max_length, "num_beams": num_beams}
def predict_step(image_paths):
images = []
for image_path in image_paths:
i_image = Image.open(image_path)
if i_image.mode != "RGB":
i_image = i_image.convert(mode="RGB")
images.append(i_image)
pixel_values = feature_extractor(images=images, return_tensors="pt").pixel_values
pixel_values = pixel_values.to(device)
output_ids = model.generate(pixel_values, **gen_kwargs)
preds = tokenizer.batch_decode(output_ids, skip_special_tokens=True)
preds = [pred.strip() for pred in preds]
return preds
predict_step(['doctor.e16ba4e4.jpg']) # ['a woman in a hospital bed with a woman in a hospital bed']
```
# Sample running code using transformers pipeline
```python
from transformers import pipeline
image_to_text = pipeline("image-to-text", model="nlpconnect/vit-gpt2-image-captioning")
image_to_text("https://ankur3107.github.io/assets/images/image-captioning-example.png")
# [{'generated_text': 'a soccer game with a player jumping to catch the ball '}]
```
# Contact for any help
* https://huggingface.co/ankur310794
* https://twitter.com/ankur310794
* http://github.com/ankur3107
* https://www.linkedin.com/in/ankur310794 |
austinb/fraud_text_detection | austinb | 2023-10-21T20:09:25Z | 733 | 0 | transformers | [
"transformers",
"pytorch",
"onnx",
"distilbert",
"text-classification",
"generated_from_trainer",
"base_model:distilbert-base-uncased",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-classification | 2023-10-21T17:26:11Z | ---
license: apache-2.0
base_model: distilbert-base-uncased
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: fraud_text_detection
results: []
---
<!-- 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. -->
# fraud_text_detection
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1112
- Accuracy: 0.9798
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| No log | 1.0 | 334 | 0.0931 | 0.9815 |
| 0.0671 | 2.0 | 668 | 0.1112 | 0.9798 |
### Framework versions
- Transformers 4.34.1
- Pytorch 2.1.0+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1
|
Weyaxi/OpenHermes-2.5-neural-chat-v3-2-Slerp | Weyaxi | 2023-12-20T05:40:17Z | 733 | 27 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"merge",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | 2023-12-08T13:19:27Z | ---
license: apache-2.0
tags:
- merge
---
<center><h1 style="font-size: 45px">⭐ UPDATE ⭐</h1></center>
Use this instead:
https://hf.co/Weyaxi/OpenHermes-2.5-neural-chat-v3-3-Slerp
# OpenHermes-2.5-neural-chat-v3-2-Slerp
This is the model for OpenHermes-2.5-neural-chat-v3-2-Slerp. I used [mergekit](https://github.com/cg123/mergekit) to merge models.
# Prompt Templates
You can use these prompt templates, but I recommend using ChatML.
### ChatML [(OpenHermes-2.5-Mistral-7B)](https://huggingface.co/teknium/OpenHermes-2.5-Mistral-7B):
```
<|im_start|>system
{system}<|im_end|>
<|im_start|>user
{user}<|im_end|>
<|im_start|>assistant
{asistant}<|im_end|>
```
### [neural-chat-7b-v3-2](https://huggingface.co/Intel/neural-chat-7b-v3-2):
```
### System:
{system}
### User:
{user}
### Assistant:
```
# Yaml Config to reproduce
```yaml
slices:
- sources:
- model: teknium/OpenHermes-2.5-Mistral-7B
layer_range: [0, 32]
- model: Intel/neural-chat-7b-v3-2
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: float16
```
# [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_PulsarAI__OpenHermes-2.5-neural-chat-v3-2-Slerp)
| Metric | Value |
|-----------------------|---------------------------|
| Avg. | 70.2 |
| ARC (25-shot) | 67.49 |
| HellaSwag (10-shot) | 85.42 |
| MMLU (5-shot) | 64.13 |
| TruthfulQA (0-shot) | 61.05 |
| Winogrande (5-shot) | 80.3 |
| GSM8K (5-shot) | 63.08 | |
shadowml/Beyonder-4x7B-v2 | shadowml | 2024-01-04T23:25:14Z | 733 | 0 | transformers | [
"transformers",
"safetensors",
"mixtral",
"text-generation",
"moe",
"mergekit",
"merge",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | 2023-12-30T21:04:26Z | ---
license: apache-2.0
tags:
- moe
- mergekit
- merge
---
# Beyonder-4x7B-v2
This model is a Mixure of Experts (MoE) made with [mergekit](https://github.com/cg123/mergekit) (mixtral branch). It uses the following base models:
* [openchat/openchat-3.5-1210](https://huggingface.co/openchat/openchat-3.5-1210)
* [beowolx/CodeNinja-1.0-OpenChat-7B](https://huggingface.co/beowolx/CodeNinja-1.0-OpenChat-7B)
* [maywell/PiVoT-0.1-Starling-LM-RP](https://huggingface.co/maywell/PiVoT-0.1-Starling-LM-RP)
* [WizardLM/WizardMath-7B-V1.1](https://huggingface.co/WizardLM/WizardMath-7B-V1.1)
## 🧩 Configuration
```yaml
base_model: mlabonne/Marcoro14-7B-slerp
experts:
- source_model: openchat/openchat-3.5-1210
positive_prompts:
- "chat"
- "assistant"
- "tell me"
- "explain"
- source_model: beowolx/CodeNinja-1.0-OpenChat-7B
positive_prompts:
- "code"
- "python"
- "javascript"
- "programming"
- "algorithm"
- source_model: maywell/PiVoT-0.1-Starling-LM-RP
positive_prompts:
- "storywriting"
- "write"
- "scene"
- "story"
- "character"
- source_model: WizardLM/WizardMath-7B-V1.1
positive_prompts:
- "reason"
- "math"
- "mathematics"
- "solve"
- "count"
```
## 💻 Usage
```python
!pip install -qU transformers bitsandbytes accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "mlabonne/Beyonder-4x7B-v2"
tokenizer = AutoTokenizer.from_pretrained(model)
pipeline = transformers.pipeline(
"text-generation",
model=model,
model_kwargs={"torch_dtype": torch.float16, "load_in_4bit": True},
)
messages = [{"role": "user", "content": "Explain what a Mixture of Experts is in less than 100 words."}]
prompt = pipeline.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])
``` |
nlpguy/Hermes-low-tune-3 | nlpguy | 2024-03-04T13:48:20Z | 733 | 0 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"mergekit",
"merge",
"conversational",
"base_model:nlpguy/Hermes-low-tune-2",
"base_model:openaccess-ai-collective/DPOpenHermes-7B-v2",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | 2024-01-06T16:22:47Z | ---
license: apache-2.0
tags:
- mergekit
- merge
base_model:
- nlpguy/Hermes-low-tune-2
- openaccess-ai-collective/DPOpenHermes-7B-v2
model-index:
- name: Hermes-low-tune-3
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: 66.21
name: normalized accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=nlpguy/Hermes-low-tune-3
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: 84.99
name: normalized accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=nlpguy/Hermes-low-tune-3
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: 63.74
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=nlpguy/Hermes-low-tune-3
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: 57.94
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=nlpguy/Hermes-low-tune-3
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: 78.77
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=nlpguy/Hermes-low-tune-3
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: 63.84
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=nlpguy/Hermes-low-tune-3
name: Open LLM Leaderboard
---
# merged
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
## Merge Details
### Merge Method
This model was merged using the SLERP merge method.
### Models Merged
The following models were included in the merge:
* [nlpguy/Hermes-low-tune-2](https://huggingface.co/nlpguy/Hermes-low-tune-2)
* [openaccess-ai-collective/DPOpenHermes-7B-v2](https://huggingface.co/openaccess-ai-collective/DPOpenHermes-7B-v2)
### Configuration
The following YAML configuration was used to produce this model:
```yaml
base_model: openaccess-ai-collective/DPOpenHermes-7B-v2
dtype: bfloat16
merge_method: slerp
parameters:
t:
- value: 0.25
slices:
- sources:
- layer_range: [0, 32]
model: openaccess-ai-collective/DPOpenHermes-7B-v2
- layer_range: [0, 32]
model: nlpguy/Hermes-low-tune-2
```
# [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_nlpguy__Hermes-low-tune-3)
| Metric |Value|
|---------------------------------|----:|
|Avg. |69.25|
|AI2 Reasoning Challenge (25-Shot)|66.21|
|HellaSwag (10-Shot) |84.99|
|MMLU (5-Shot) |63.74|
|TruthfulQA (0-shot) |57.94|
|Winogrande (5-shot) |78.77|
|GSM8k (5-shot) |63.84|
|
ycros/BagelMIsteryTour-8x7B | ycros | 2024-01-16T23:44:34Z | 733 | 4 | transformers | [
"transformers",
"safetensors",
"mixtral",
"text-generation",
"mergekit",
"merge",
"arxiv:2311.03099",
"arxiv:2306.01708",
"base_model:mistralai/Mixtral-8x7B-v0.1",
"base_model:mistralai/Mixtral-8x7B-Instruct-v0.1",
"base_model:jondurbin/bagel-dpo-8x7b-v0.2",
"base_model:Doctor-Shotgun/limarp-zloss-mixtral-8x7b-qlora",
"base_model:Sao10K/Sensualize-Mixtral-bf16",
"license:cc-by-nc-4.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | 2024-01-15T15:40:51Z | ---
base_model:
- mistralai/Mixtral-8x7B-v0.1
- mistralai/Mixtral-8x7B-Instruct-v0.1
- jondurbin/bagel-dpo-8x7b-v0.2
- Doctor-Shotgun/limarp-zloss-mixtral-8x7b-qlora
- Sao10K/Sensualize-Mixtral-bf16
tags:
- mergekit
- merge
license: cc-by-nc-4.0
---
# BagelMIsteryTour-8x7B
[GGUF versions here](https://huggingface.co/ycros/BagelMIsteryTour-8x7B-GGUF)
Bagel, Mixtral Instruct, with extra spices. Give it a taste. Works with Alpaca prompt formats, though the Mistral format should also work.
I started experimenting around seeing if I could improve or fix some of Bagel's problems. Totally inspired by seeing how well Doctor-Shotgun's Mixtral-8x7B-Instruct-v0.1-LimaRP-ZLoss worked (which is a LimaRP tune on top of base Mixtral, and then merged with Mixtral Instruct) - I decided to try some merges of Bagel with Mixtral Instruct as a result.
Somehow I ended up here, Bagel, Mixtral Instruct, a little bit of LimaRP, a little bit of Sao10K's Sensualize. So far in my testing it's working very well, and while it seems fairly unaligned on a lot of stuff, it's maybe a little too aligned on a few specific things (which I think comes from Sensualize) - so that's something to play with in the future, or maybe try to DPO out.
I've been running (temp last) minP 0.1, dynatemp 0.5-4, rep pen 1.02, rep range 1024. I've been testing Alpaca style Instruction/Response, and Instruction/Input/Response and those seem to work well, I expect Mistral's prompt format would also work well. You may need to add a stopping string on "{{char}}:" for RPs because it can sometimes duplicate those out in responses and waffle on. Seems to hold up and not fall apart at long contexts like Bagel and some other Mixtral tunes seem to, definitely doesn't seem prone to loopyness either. Can be pushed into extravagant prose if the scene/setting calls for it.
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
## Merge Details
### Merge Method
This model was merged using the [DARE](https://arxiv.org/abs/2311.03099) [TIES](https://arxiv.org/abs/2306.01708) merge method using [mistralai/Mixtral-8x7B-v0.1](https://huggingface.co/mistralai/Mixtral-8x7B-v0.1) as a base.
### Models Merged
The following models were included in the merge:
* [mistralai/Mixtral-8x7B-Instruct-v0.1](https://huggingface.co/mistralai/Mixtral-8x7B-Instruct-v0.1)
* [jondurbin/bagel-dpo-8x7b-v0.2](https://huggingface.co/jondurbin/bagel-dpo-8x7b-v0.2)
* [mistralai/Mixtral-8x7B-v0.1](https://huggingface.co/mistralai/Mixtral-8x7B-v0.1) + [Doctor-Shotgun/limarp-zloss-mixtral-8x7b-qlora](https://huggingface.co/Doctor-Shotgun/limarp-zloss-mixtral-8x7b-qlora)
* [Sao10K/Sensualize-Mixtral-bf16](https://huggingface.co/Sao10K/Sensualize-Mixtral-bf16)
### Configuration
The following YAML configuration was used to produce this model:
```yaml
base_model: mistralai/Mixtral-8x7B-v0.1
models:
- model: mistralai/Mixtral-8x7B-v0.1+Doctor-Shotgun/limarp-zloss-mixtral-8x7b-qlora
parameters:
density: 0.5
weight: 0.2
- model: Sao10K/Sensualize-Mixtral-bf16
parameters:
density: 0.5
weight: 0.2
- model: mistralai/Mixtral-8x7B-Instruct-v0.1
parameters:
density: 0.6
weight: 1.0
- model: jondurbin/bagel-dpo-8x7b-v0.2
parameters:
density: 0.6
weight: 0.5
merge_method: dare_ties
dtype: bfloat16
``` |
TeeZee/Buttocks-7B-v1.1 | TeeZee | 2024-03-04T14:36:24Z | 733 | 2 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"not-for-all-audiences",
"merge",
"license:cc-by-nc-4.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | 2024-01-18T21:24:30Z | ---
license: cc-by-nc-4.0
tags:
- not-for-all-audiences
- merge
model-index:
- name: Buttocks-7B-v1.1
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: 54.61
name: normalized accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TeeZee/Buttocks-7B-v1.1
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: 75.61
name: normalized accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TeeZee/Buttocks-7B-v1.1
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: 50.22
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TeeZee/Buttocks-7B-v1.1
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: 44.72
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TeeZee/Buttocks-7B-v1.1
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: 68.9
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TeeZee/Buttocks-7B-v1.1
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: 5.76
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TeeZee/Buttocks-7B-v1.1
name: Open LLM Leaderboard
---
### Buttocks 7B v1.1 ###
An experiment that has gone very, very wrong.
### Model details ###
- Recreation of the original recipe for [Undi95/Toppy-M-7B](https://huggingface.co/Undi95/Toppy-M-7B), but instead of final merge done by mergekit, [MergeMoster](https://github.com/Gryphe/MergeMonster/) was used with extended RPG preset.
- recipe in [mergekit-config](https://huggingface.co/TeeZee/Toppy-7B-remake-mergemonster-SLERP-v1.0/resolve/main/toppy-slerp-merge-config.yml), stepsAA, BB, CC are the original models with LORAS as per Toppy M 7B sauce.
- LERP merge method was used
### Results ###
- in simple terms this model is totally unhinged
- it always produces sequences similar to fever dreams or drug trips
- on a good day it can produce scenarios similar to old Monty Python sketches
- models shows incredible affinity to words like 'ass', 'buttocks', 'farts', prompting with those single words will probably
produce a whole story revolving around those topics.
### Possible uses ###
- to generate dream sequence in a story
- to make the boring model more unpredictable by merging at low weights with this monster
- to take a break, connect Silly Tavern to this model and get a few ROTFLs observing how every story deteriorates into pure craziness
- research on LLM hallucinations
# [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_TeeZee__Buttocks-7B-v1.1)
| Metric |Value|
|---------------------------------|----:|
|Avg. |49.97|
|AI2 Reasoning Challenge (25-Shot)|54.61|
|HellaSwag (10-Shot) |75.61|
|MMLU (5-Shot) |50.22|
|TruthfulQA (0-shot) |44.72|
|Winogrande (5-shot) |68.90|
|GSM8k (5-shot) | 5.76|
|
vicgalle/NeuralBeagle-11B | vicgalle | 2024-03-04T12:11:40Z | 733 | 6 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"dpo",
"11B",
"merge",
"conversational",
"dataset:argilla/distilabel-intel-orca-dpo-pairs",
"base_model:vicgalle/franken-Beagle-11B",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | 2024-01-20T10:01:58Z | ---
license: apache-2.0
tags:
- dpo
- 11B
- merge
datasets:
- argilla/distilabel-intel-orca-dpo-pairs
base_model:
- vicgalle/franken-Beagle-11B
model-index:
- name: NeuralBeagle-11B
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: 73.29
name: normalized accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vicgalle/NeuralBeagle-11B
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: 87.61
name: normalized accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vicgalle/NeuralBeagle-11B
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: 63.8
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vicgalle/NeuralBeagle-11B
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: 71.36
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vicgalle/NeuralBeagle-11B
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: 82.64
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vicgalle/NeuralBeagle-11B
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: 58.98
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vicgalle/NeuralBeagle-11B
name: Open LLM Leaderboard
---
# NeuralBeagle-11B
DPO'd from vicgalle/franken-Beagle-11B, a Beagle-like model upscaled to 11B.
It is a frankenmerge model created using mergekit. Then, we applied DPO over a high-quality preference dataset.
## Sample generations
**Generate a movie review about the Pokémon 1 movie, focusing on BDSM.**
> Before delving into the realm of BDSOMatic interpretations within Pokémon: The First Movie (aka "Pokémon: Mewtwo's Revenge" in Japan), it is important to acknowledge that this animated feature is primarily intended for a younger audience. It follows the adventures of Ash Ketchum, Pikachu, and their friends as they encounter an artificially created Pokémon named Mewtwo. While certain aspects of the storyline and visuals could be stretched to include various subtexts or symbolism, our analysis will focus on a more playful and metaphorical exploration of BDSM concepts within this film's context.
Participants: Warning: The following review may contain light-hearted and imaginative interpretations that are not intended as serious critical analysis and should not be taken literally.
Within the Pokémon universe, Ash Ketchum and his loyal Pikachu find themselves thrust into a high-stakes scenario reminiscent of a BDSM "Domestic Discipline" (DD) fantasy. As Mewtwo, a genetically modified Pokémon with immense power and intellect, seeks vengeance against the scientists who created him as a tool for battle entertainment, he operates as an archetypal "Dominant" figure.
Mewtwo, born from scientific manipulation, is an embodiment of control, both over his own creation and his obedient army of Pokémon. He exercises mastery over his subjects, mirroring the role of a "Dom," or Dominant, in a BDSM dynamic.
Ash Ketchum, initially unaware of the manipulations that have brought him into this situation, can be seen as a submissive protagonist. His humility and naivety parallel those within the DD community who seek guidance from an experienced Dominant to help them understand and embrace their desires for submission.
In his encounter with Mewtwo, Ash is subjected to tests designed to exhibit his strength, loyalty, and unwavering determination - elements crucial in establishing trust between a submissive and a Dominant within a BDSM dynamic. This psychological battle symbolizes the process of earning a "sub's" consent and trust through displays of control and power.
## Prompt format
The template is included in tokenizer_config.json.
# [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_vicgalle__NeuralBeagle-11B)
| Metric |Value|
|---------------------------------|----:|
|Avg. |72.95|
|AI2 Reasoning Challenge (25-Shot)|73.29|
|HellaSwag (10-Shot) |87.61|
|MMLU (5-Shot) |63.80|
|TruthfulQA (0-shot) |71.36|
|Winogrande (5-shot) |82.64|
|GSM8k (5-shot) |58.98|
|
ConvexAI/BurningBruce-005 | ConvexAI | 2024-03-04T16:34:13Z | 733 | 4 | transformers | [
"transformers",
"safetensors",
"mixtral",
"text-generation",
"merge",
"moe",
"conversational",
"en",
"arxiv:2101.03961",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | 2024-01-20T15:14:56Z | ---
language:
- en
license: apache-2.0
tags:
- merge
- moe
model-index:
- name: BurningBruce-005
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: 72.01
name: normalized accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ConvexAI/BurningBruce-005
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: 88.31
name: normalized accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ConvexAI/BurningBruce-005
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: 64.76
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ConvexAI/BurningBruce-005
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: 67.27
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ConvexAI/BurningBruce-005
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: 83.35
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ConvexAI/BurningBruce-005
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: 71.49
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ConvexAI/BurningBruce-005
name: Open LLM Leaderboard
---
# BurningBruce-005
We didn't start the **fire**.
This model is a Mixture of Experts (MoE) made with [mergekit](https://github.com/cg123/mergekit/tree/mixtral)
by Kquant03, Dontriskit and NeuralNovel
[Join our Discord!](https://discord.gg/Qge8Ds9C)
## Models used:
- [leveldevai/TurdusBeagle-7B](https://huggingface.co/leveldevai/TurdusBeagle-7B) - base
- [leveldevai/TurdusBeagle-7B](https://huggingface.co/leveldevai/TurdusBeagle-7B) - expert #1
- [udkai/Turdus](https://huggingface.co/nfaheem/udkai/Turdus) - expert #2
- [nfaheem/Marcoroni-7b-DPO-Merge](https://huggingface.co/nfaheem/Marcoroni-7b-DPO-Merge) - expert #3
- [Toten5/Marcoroni-neural-chat-7B-v2](https://huggingface.co/Toten5/Marcoroni-neural-chat-7B-v2) - expert #4
# "[What is a Mixture of Experts (MoE)?](https://huggingface.co/blog/moe)"
### (from the MistralAI papers...click the quoted question above to navigate to it directly.)
The scale of a model is one of the most important axes for better model quality. Given a fixed computing budget, training a larger model for fewer steps is better than training a smaller model for more steps.
Mixture of Experts enable models to be pretrained with far less compute, which means you can dramatically scale up the model or dataset size with the same compute budget as a dense model. In particular, a MoE model should achieve the same quality as its dense counterpart much faster during pretraining.
So, what exactly is a MoE? In the context of transformer models, a MoE consists of two main elements:
Sparse MoE layers are used instead of dense feed-forward network (FFN) layers. MoE layers have a certain number of “experts” (e.g. 32 in my "frankenMoE"), where each expert is a neural network. In practice, the experts are FFNs, but they can also be more complex networks or even a MoE itself, leading to hierarchical MoEs!
A gate network or router, that determines which tokens are sent to which expert. For example, in the image below, the token “More” is sent to the second expert, and the token "Parameters” is sent to the first network. As we’ll explore later, we can send a token to more than one expert. How to route a token to an expert is one of the big decisions when working with MoEs - the router is composed of learned parameters and is pretrained at the same time as the rest of the network.
At every layer, for every token, a router network chooses two of these groups (the “experts”) to process the token and combine their output additively.
Switch Layer
MoE layer from the [Switch Transformers paper](https://arxiv.org/abs/2101.03961)
So, to recap, in MoEs we replace every FFN layer of the transformer model with an MoE layer, which is composed of a gate network and a certain number of experts.
Although MoEs provide benefits like efficient pretraining and faster inference compared to dense models, they also come with challenges:
Training: MoEs enable significantly more compute-efficient pretraining, but they’ve historically struggled to generalize during fine-tuning, leading to overfitting.
Inference: Although a MoE might have many parameters, only some of them are used during inference. This leads to much faster inference compared to a dense model with the same number of parameters. However, all parameters need to be loaded in RAM, so memory requirements are high. For example, [given a MoE like Mixtral 8x7B](https://huggingface.co/blog/moe), we’ll need to have enough VRAM to hold a dense 47B parameter model. Why 47B parameters and not 8 x 7B = 56B? That’s because in MoE models, only the FFN layers are treated as individual experts, and the rest of the model parameters are shared. At the same time, assuming just two experts are being used per token, the inference speed (FLOPs) is like using a 12B model (as opposed to a 14B model), because it computes 2x7B matrix multiplications, but with some layers shared (more on this soon).
If all our tokens are sent to just a few popular experts, that will make training inefficient. In a normal MoE training, the gating network converges to mostly activate the same few experts. This self-reinforces as favored experts are trained quicker and hence selected more. To mitigate this, an auxiliary loss is added to encourage giving all experts equal importance. This loss ensures that all experts receive a roughly equal number of training examples. The following sections will also explore the concept of expert capacity, which introduces a threshold of how many tokens can be processed by an expert. In transformers, the auxiliary loss is exposed via the aux_loss parameter.
## "Wait...but you called this a frankenMoE?"
The difference between MoE and "frankenMoE" lies in the fact that the router layer in a model like the one on this repo is not trained simultaneously.
Sponsored by: [Dontriskit](https://huggingface.co/h2m)
# Evals
*coming soon*
# [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_ConvexAI__BurningBruce-005)
| Metric |Value|
|---------------------------------|----:|
|Avg. |74.53|
|AI2 Reasoning Challenge (25-Shot)|72.01|
|HellaSwag (10-Shot) |88.31|
|MMLU (5-Shot) |64.76|
|TruthfulQA (0-shot) |67.27|
|Winogrande (5-shot) |83.35|
|GSM8k (5-shot) |71.49|
|
llmixer/BigWeave-v6-90b | llmixer | 2024-03-05T06:11:10Z | 733 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"Xwin",
"Euryale 1.3",
"frankenmerge",
"90b",
"conversational",
"en",
"license:llama2",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | 2024-01-22T11:55:14Z | ---
language:
- en
license: llama2
tags:
- Xwin
- Euryale 1.3
- frankenmerge
- 90b
pipeline_tag: conversational
model-index:
- name: BigWeave-v6-90b
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: 65.36
name: normalized accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=llmixer/BigWeave-v6-90b
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: 87.21
name: normalized accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=llmixer/BigWeave-v6-90b
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: 68.04
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=llmixer/BigWeave-v6-90b
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: 57.96
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=llmixer/BigWeave-v6-90b
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: 81.69
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=llmixer/BigWeave-v6-90b
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: 44.58
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=llmixer/BigWeave-v6-90b
name: Open LLM Leaderboard
---
# BigWeave v6 90B
<img src="https://cdn-uploads.huggingface.co/production/uploads/65a6db055c58475cf9e6def1/4CbbAN-X7ZWj702JrcCGH.png" width=600>
A Goliath-120b style frankenmerge of Xwin-LM-70b-v0.1 and Euryale-1.3-70b. The goal is to find other merge combinations that work well.
The version number is for me to keep track of the merges, only results that seem to work reasonably well are kept/published.
# Prompting Format
Vicuna and Alpaca.
# Merge process
The models used in the merge are [Xwin-LM-70b-v0.1](https://huggingface.co/Xwin-LM/Xwin-LM-70B-V0.1) and [Euryale-1.3-70b](https://huggingface.co/Sao10K/Euryale-1.3-L2-70B).
The layer mix:
```yaml
- range 0, 12
Xwin
- range 9, 14
Euryale
- range 12, 62
Xwin
- range 54, 71
Euryale
- range 62, 80
Xwin
```
# Acknowledgements
[@Xwin-LM](https://huggingface.co/Xwin-LM) For creating Xwin
[@Sao10K](https://huggingface.co/Sao10K) For creating Euryale
[@alpindale](https://huggingface.co/alpindale) For creating the original Goliath
[@chargoddard](https://huggingface.co/chargoddard) For developing [mergekit](https://github.com/cg123/mergekit).
# [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_llmixer__BigWeave-v6-90b)
| Metric |Value|
|---------------------------------|----:|
|Avg. |67.47|
|AI2 Reasoning Challenge (25-Shot)|65.36|
|HellaSwag (10-Shot) |87.21|
|MMLU (5-Shot) |68.04|
|TruthfulQA (0-shot) |57.96|
|Winogrande (5-shot) |81.69|
|GSM8k (5-shot) |44.58|
|
vilm/Mixsmol-4x400M-v0.1-epoch1 | vilm | 2024-01-29T02:25:09Z | 733 | 12 | transformers | [
"transformers",
"safetensors",
"mixtral",
"text-generation",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | 2024-01-25T10:26:13Z | ---
license: apache-2.0
widget:
- text: My name is El Microondas the Wise, and
example_title: El Microondas
- text: Kennesaw State University is a public
example_title: Kennesaw State University
- text: Bungie Studios is an American video game developer. They are most famous for
developing the award winning Halo series of video games. They also made Destiny.
The studio was founded
example_title: Bungie
- text: The Mona Lisa is a world-renowned painting created by
example_title: Mona Lisa
- text: The Harry Potter series, written by J.K. Rowling, begins with the book titled
example_title: Harry Potter Series
- text: 'Question: I have cities, but no houses. I have mountains, but no trees. I
have water, but no fish. What am I?
Answer:'
example_title: Riddle
- text: The process of photosynthesis involves the conversion of
example_title: Photosynthesis
- text: Jane went to the store to buy some groceries. She picked up apples, oranges,
and a loaf of bread. When she got home, she realized she forgot
example_title: Story Continuation
- text: 'Problem 2: If a train leaves Station A at 9:00 AM and travels at 60 mph,
and another train leaves Station B at 10:00 AM and travels at 80 mph, when will
they meet if the distance between the stations is 300 miles?
To determine'
example_title: Math Problem
- text: In the context of computer programming, an algorithm is
example_title: Algorithm Definition
---
# Mixsmol-4x400M-v0.1 by Ontocord
This is the first checkpoint (Epoch 1) of Mixsmol-4x400M-v0.1
Note that this is an experimental in data mixing. Therefore, we only trained the model on 50B tokens (95% English and 5% Vietnamese) to test the following:
- Reasoining capabilities through high-quality synthetic textbooks data pretraining
- Crosslingual understanding through machine translation and multilingual + multiple tasks pretraining
After verifying our hypothesis with this run, we will schedule a second run on bigger data and compute for it to achieve its maximum capability.
## Data
- Synthetic Textbooks: 8M samples
- RefinedWeb: 1M samples
- RedPajama-v2: 500K samples
- MathPile: Everything
- ThePile: MiniPile Subset
- GoodWiki
- The Stack Smol XL
- The Vault: train_small split
- Instruction Pretraining: 250k samples
| Tasks |Version|Filter|n-shot| Metric |Value | |Stderr|
|-------------|-------|------|-----:|--------|-----:|---|-----:|
|arc_challenge|Yaml |none | 25|acc |0.1937|± |0.0115|
| | |none | 25|acc_norm|0.2329|± |0.0124|
|hellaswag|Yaml |none | 10|acc |0.2856|± |0.0045|
| | |none | 10|acc_norm|0.3090|± |0.0046|
|mmlu |N/A |none | 0|acc |0.2536|± |0.0483|
| - humanities |N/A |none | 5|acc |0.2408|± |0.0341|
| - other |N/A |none | 5|acc |0.2475|± |0.0443|
| - social_sciences|N/A |none | 5|acc |0.2567|± |0.0456|
| - stem |N/A |none | 5|acc |0.2756|± |0.0653|
|truthfulqa_mc2|Yaml |none | 0|acc |0.3909|± |0.0148|
|winogrande|Yaml |none | 5|acc |0.5107|± | 0.014|
|gsm8k|Yaml |get-answer| 5|exact_match| 0|± | 0|
## Contribution
This work is a shared contribution between **Ontocord, BEE-spoke-data and VILM**
|
Plaban81/Moe-4x7b-math-reason-code | Plaban81 | 2024-01-30T11:26:15Z | 733 | 1 | transformers | [
"transformers",
"safetensors",
"mixtral",
"text-generation",
"code",
"QA",
"reasoning",
"maths",
"conversational",
"en",
"arxiv:1910.09700",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | 2024-01-26T05:50:39Z | ---
language:
- en
license: apache-2.0
library_name: transformers
tags:
- code
- QA
- reasoning
- maths
---
# 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. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **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]
|
saarvajanik/facebook-opt-6.7b-qcqa-ub-16-best-for-q-loss | saarvajanik | 2024-01-28T17:13:37Z | 733 | 0 | transformers | [
"transformers",
"pytorch",
"opt",
"text-generation",
"en",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | 2024-01-28T09:20:14Z | ---
license: mit
language:
- en
library_name: transformers
---
This is a QCQA version of the original model facebook/opt-125m. In this version, the original MHA architecture is preserved but instead of having a single K/V head, different K/V heads corresponding to the same group have the same mean-pooled K or V values. It has 16 groups of KV heads per layer instead of original 32 KV heads in the MHA implementation. |
sethuiyer/OpenDolphinHermes_Llama2_7B | sethuiyer | 2024-03-07T07:19:07Z | 733 | 1 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"merge",
"mergekit",
"lazymergekit",
"conversational",
"en",
"dataset:teknium/openhermes",
"dataset:cognitivecomputations/dolphin",
"base_model:cognitivecomputations/dolphin-llama2-7b",
"base_model:Tensoic/Llama-2-openhermes",
"license:llama2",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | 2024-01-28T11:34:55Z | ---
language:
- en
license: llama2
library_name: transformers
tags:
- merge
- mergekit
- lazymergekit
datasets:
- teknium/openhermes
- cognitivecomputations/dolphin
base_model:
- cognitivecomputations/dolphin-llama2-7b
- Tensoic/Llama-2-openhermes
pipeline_tag: text-generation
model-index:
- name: OpenDolphinHermes_Llama2_7B
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: 55.03
name: normalized accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sethuiyer/OpenDolphinHermes_Llama2_7B
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: 78.74
name: normalized accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sethuiyer/OpenDolphinHermes_Llama2_7B
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: 52.25
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sethuiyer/OpenDolphinHermes_Llama2_7B
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: 46.1
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sethuiyer/OpenDolphinHermes_Llama2_7B
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: 73.16
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sethuiyer/OpenDolphinHermes_Llama2_7B
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: 20.17
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sethuiyer/OpenDolphinHermes_Llama2_7B
name: Open LLM Leaderboard
---
# OpenDolphinHermes_Llama2_7B
<p align="center">
<img src="https://huggingface.co/sethuiyer/OpenDolphinHermes_Llama2_7B/resolve/main/dolphin_hermes.webp" height="256px" alt="SynthIQ">
</p>
mergekit SLERP of these two models
* [cognitivecomputations/dolphin-llama2-7b](https://huggingface.co/cognitivecomputations/dolphin-llama2-7b)
* [Tensoic/Llama-2-openhermes](https://huggingface.co/Tensoic/Llama-2-openhermes)
## 🧩 Configuration
```yaml
slices:
- sources:
- model: cognitivecomputations/dolphin-llama2-7b
layer_range: [0, 32]
- model: Tensoic/Llama-2-openhermes
layer_range: [0, 32]
merge_method: slerp
base_model: Tensoic/Llama-2-openhermes
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
dtype: bfloat16
```
# Prompt Template (ChatML)
```text
<|im_start|>system
You are a helpful, respectful and honest assistant. Always answer as helpfully as possible, while being safe.
Your answers should not include any harmful, unethical, racist, sexist, toxic, dangerous, or illegal content.
Please ensure that your responses are socially unbiased and positive in nature.
If a question does not make any sense, or is not factually coherent, explain why instead of answering something not correct.
If you don't know the answer to a question, please don't share false information.
<|im_end|>
<|im_start|>user
{ .Prompt}
<|im_end|>
<|im_start|>assistant
```
# OpenLLM Leaderboard
| T | Model | Average | ARC | HellaSwag | MMLU | TruthfulQA | Winogrande | GSM8K |
|---|--------------------------------------------|---------|------|-----------|-------|------------|------------|-------|
| 0 | meta-llama/llama-2-13b-hf | 55.69 | 59.39 | 82.13 | 55.77 | 37.38 | 76.64 | 22.82 |
| 1 | sethuiyer/OpenDolphinHermes_Llama2_7B | 54.24 | 55.03| 78.74 | 52.25 | 46.1 | 73.16 | 20.17 |
| 2 | togethercomputer/Llama-2-7B-32K-Instruct | 50.02 | 51.11| 78.51 | 46.11 | 44.86 | 73.88 | 5.69 |
| 3 | togethercomputer/LLaMa-2-7B-32K | 47.07 | 47.53| 76.14 | 43.33 | 39.23 | 71.9 | 4.32 |
## Why?
I wanted a LLaMa2-7B model which is as good as base LLaMa2-13B model.
## 💻 Usage
```python
!pip install -qU transformers accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "sethuiyer/OpenDolphinHermes_Llama2_7B"
messages = [{"role": "user", "content": "What is a large language model?"}]
tokenizer = AutoTokenizer.from_pretrained(model)
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
pipeline = transformers.pipeline(
"text-generation",
model=model,
torch_dtype=torch.float16,
device_map="auto",
)
outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])
```
Output:
```text
A large language model is a type of artificial intelligence system that has been trained on a massive amount of data, often millions or even billions of words, to learn the patterns and relationships between words and phrases.
These models can then be used to generate new text, understand and translate languages, and perform various natural language processing tasks.
They have become increasingly popular in recent years due to advances in machine learning technology and their ability to achieve high levels of accuracy and performance on natural language processing tasks.
Examples of large language models include GPT-2, BERT, and T5.
```
## Thanks
Thanks to Google Colab for the compute.
# [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_sethuiyer__OpenDolphinHermes_Llama2_7B)
| Metric |Value|
|---------------------------------|----:|
|Avg. |54.24|
|AI2 Reasoning Challenge (25-Shot)|55.03|
|HellaSwag (10-Shot) |78.74|
|MMLU (5-Shot) |52.25|
|TruthfulQA (0-shot) |46.10|
|Winogrande (5-shot) |73.16|
|GSM8k (5-shot) |20.17|
|
jingyeom/KoSoLAR-10.7B-v0.2_1.4_dedup | jingyeom | 2024-02-12T07:37:57Z | 733 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"conversational",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | 2024-01-31T00:31:48Z | ---
license: apache-2.0
---
## Model
base_model : yanolja/KoSOLAR-10.7B-v0.2
## Dataset
* 공개 데이터 수집
* Deduplicating Training Data Makes Language Models Better 알고리즘 활용
## Code
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
import torch
model_name = "jingyeom/KoSoLAR-10.7B-v0.2_1.4_dedup"
model = AutoModelForCausalLM.from_pretrained(
model_name,
)
tokenizer = AutoTokenizer.from_pretrained(model_name)
```
## Benchmark
**[Ko-LLM-Leaderboard](https://huggingface.co/spaces/upstage/open-ko-llm-leaderboard)**
|
kwchoi/DPO_mistral_v01_7b_ultra_0131_1k_1epoch | kwchoi | 2024-03-06T01:45:21Z | 733 | 0 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"conversational",
"en",
"dataset:argilla/ultrafeedback-binarized-preferences-cleaned",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | 2024-02-02T00:24:04Z | ---
language:
- en
license: apache-2.0
datasets:
- argilla/ultrafeedback-binarized-preferences-cleaned
model-index:
- name: DPO_mistral_v01_7b_ultra_0131_1k_1epoch
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: 55.97
name: normalized accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=kwchoi/DPO_mistral_v01_7b_ultra_0131_1k_1epoch
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: 76.78
name: normalized accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=kwchoi/DPO_mistral_v01_7b_ultra_0131_1k_1epoch
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: 55.97
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=kwchoi/DPO_mistral_v01_7b_ultra_0131_1k_1epoch
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: 57.94
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=kwchoi/DPO_mistral_v01_7b_ultra_0131_1k_1epoch
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: 73.4
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=kwchoi/DPO_mistral_v01_7b_ultra_0131_1k_1epoch
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: 29.87
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=kwchoi/DPO_mistral_v01_7b_ultra_0131_1k_1epoch
name: Open LLM Leaderboard
---
Testing Mistral-Instruct model with Orca DPO dataset.
Trying to see the effects of DPO for own study.
Used Mistral-7B-Instrcut-v0.2 model due to its good performance
Testing Mistral-Instruct model with Orca DPO dataset.
Trying to see the effects of DPO for own study.
Used Mistral-7B-Instrcut-v0.2 model due to its good performance
Testing Mistral-Instruct model with Orca DPO dataset.
Trying to see the effects of DPO for own study.
Used Mistral-7B-Instrcut-v0.2 model due to its good performance
Testing Mistral-Instruct model with Orca DPO dataset.
Trying to see the effects of DPO for own study.
Used Mistral-7B-Instrcut-v0.2 model due to its good performance
Testing Mistral-Instruct model with Orca DPO dataset.
Trying to see the effects of DPO for own study.
Used Mistral-7B-Instrcut-v0.2 model due to its good performance
Testing Mistral-Instruct model with Orca DPO dataset.
Trying to see the effects of DPO for own study.
Used Mistral-7B-Instrcut-v0.2 model due to its good performance
Testing Mistral-Instruct model with Orca DPO dataset.
Trying to see the effects of DPO for own study.
Used Mistral-7B-Instrcut-v0.2 model due to its good performance
Testing Mistral-Instruct model with Orca DPO dataset.
Trying to see the effects of DPO for own study.
Used Mistral-7B-Instrcut-v0.2 model due to its good performanceTesting Mistral-Instruct model with Orca DPO dataset.
Trying to see the effects of DPO for own study.
Used Mistral-7B-Instrcut-v0.2 model due to its good performance
Testing Mistral-Instruct model with Orca DPO dataset.
Trying to see the effects of DPO for own study.
Used Mistral-7B-Instrcut-v0.2 model due to its good performance
Testing Mistral-Instruct model with Orca DPO dataset.
Trying to see the effects of DPO for own study.
Used Mistral-7B-Instrcut-v0.2 model due to its good performance
Testing Mistral-Instruct model with Orca DPO dataset.
Trying to see the effects of DPO for own study.
Used Mistral-7B-Instrcut-v0.2 model due to its good performanceTesting Mistral-Instruct model with Orca DPO dataset.
Trying to see the effects of DPO for own study.
Used Mistral-7B-Instrcut-v0.2 model due to its good performance
Testing Mistral-Instruct model with Orca DPO dataset.
Trying to see the effects of DPO for own study.
Used Mistral-7B-Instrcut-v0.2 model due to its good performance
Testing Mistral-Instruct model with Orca DPO dataset.
Trying to see the effects of DPO for own study.
Used Mistral-7B-Instrcut-v0.2 model due to its good performance
Testing Mistral-Instruct model with Orca DPO dataset.
Trying to see the effects of DPO for own study.
Used Mistral-7B-Instrcut-v0.2 model due to its good performanceTesting Mistral-Instruct model with Orca DPO dataset.
Trying to see the effects of DPO for own study.
Used Mistral-7B-Instrcut-v0.2 model due to its good performance
Testing Mistral-Instruct model with Orca DPO dataset.
Trying to see the effects of DPO for own study.
Used Mistral-7B-Instrcut-v0.2 model due to its good performance
Testing Mistral-Instruct model with Orca DPO dataset.
Trying to see the effects of DPO for own study.
Used Mistral-7B-Instrcut-v0.2 model due to its good performance
Testing Mistral-Instruct model with Orca DPO dataset.
Trying to see the effects of DPO for own study.
Used Mistral-7B-Instrcut-v0.2 model due to its good performance
# [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_kwchoi__DPO_mistral_v01_7b_ultra_0131_1k_1epoch)
| Metric |Value|
|---------------------------------|----:|
|Avg. |58.32|
|AI2 Reasoning Challenge (25-Shot)|55.97|
|HellaSwag (10-Shot) |76.78|
|MMLU (5-Shot) |55.97|
|TruthfulQA (0-shot) |57.94|
|Winogrande (5-shot) |73.40|
|GSM8k (5-shot) |29.87|
|
Samee-ur/NeuralPipe-7B-slerp-DPO | Samee-ur | 2024-02-04T16:50:25Z | 733 | 0 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"en",
"dataset:Intel/orca_dpo_pairs",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | 2024-02-02T07:02:12Z |
---
license: apache-2.0
datasets:
- Intel/orca_dpo_pairs
language:
- en
---
# NeuralPipe-7B-slerp-DPO
NeuralPipe-7B-slerp is a Direct Preference Optimized version of [Samee-ur/NeuralPipe-7B-slerp](https://huggingface.co/Samee-ur/NeuralPipe-7B-slerp).
I performed Direct Preference Optimization on the [Intel/orca_dpo_pairs dataset](https://huggingface.co/datasets/Intel/orca_dpo_pairs)
## 💻 Usage
```python
!pip install -qU transformers accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "Samee-ur/NeuralPipe-7B-slerp-DPO"
messages = [{"role": "user", "content": "What is a large language model?"}]
tokenizer = AutoTokenizer.from_pretrained(model)
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
pipeline = transformers.pipeline(
"text-generation",
model=model,
torch_dtype=torch.float16,
device_map="auto",
)
outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])
``` |
pharaouk/fusedyi | pharaouk | 2024-02-02T20:40:54Z | 733 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"Mixtral",
"instruct",
"finetune",
"chatml",
"DPO",
"RLHF",
"gpt4",
"synthetic data",
"distillation",
"conversational",
"en",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | 2024-02-02T20:19:22Z | ---
tags:
- Mixtral
- instruct
- finetune
- chatml
- DPO
- RLHF
- gpt4
- synthetic data
- distillation
model-index:
- name: fusedYi
results: []
license: apache-2.0
language:
- en
---
# Model Card for FusedYi
<!-- Provide a quick summary of what the model is/does. -->
This is fused Yi-6B.
I took a Yi, merged it with another Yi, and got a new Yi out of the Yis.
Yi-ceptionized.
## Model Details
1.9 x Yi-6B
|
saishf/Kuno-Lake-7B | saishf | 2024-03-04T14:32:29Z | 733 | 2 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"mergekit",
"merge",
"arxiv:2311.03099",
"arxiv:2306.01708",
"base_model:mistralai/Mistral-7B-v0.1",
"base_model:senseable/WestLake-7B-v2",
"base_model:SanjiWatsuki/Kunoichi-DPO-v2-7B",
"license:cc-by-nc-4.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | 2024-02-03T02:07:56Z | ---
license: cc-by-nc-4.0
tags:
- mergekit
- merge
base_model:
- mistralai/Mistral-7B-v0.1
- senseable/WestLake-7B-v2
- SanjiWatsuki/Kunoichi-DPO-v2-7B
model-index:
- name: Kuno-Lake-7B
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: 71.84
name: normalized accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=saishf/Kuno-Lake-7B
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: 88.15
name: normalized accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=saishf/Kuno-Lake-7B
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: 64.76
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=saishf/Kuno-Lake-7B
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: 66.83
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=saishf/Kuno-Lake-7B
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: 84.45
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=saishf/Kuno-Lake-7B
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: 65.35
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=saishf/Kuno-Lake-7B
name: Open LLM Leaderboard
---
# merge
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
## Merge Details
### Merge Method
This model was merged using the [DARE](https://arxiv.org/abs/2311.03099) [TIES](https://arxiv.org/abs/2306.01708) merge method using [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) as a base.
### Models Merged
The following models were included in the merge:
* [senseable/WestLake-7B-v2](https://huggingface.co/senseable/WestLake-7B-v2)
* [SanjiWatsuki/Kunoichi-DPO-v2-7B](https://huggingface.co/SanjiWatsuki/Kunoichi-DPO-v2-7B)
### Configuration
The following YAML configuration was used to produce this model:
```yaml
models:
- model: mistralai/Mistral-7B-v0.1
# No parameters necessary for base model
- model: senseable/WestLake-7B-v2
parameters:
density: 0.53
weight: 0.65
- model: SanjiWatsuki/Kunoichi-DPO-v2-7B
parameters:
density: 0.53
weight: 0.35
merge_method: dare_ties
base_model: mistralai/Mistral-7B-v0.1
parameters:
int8_mask: true
dtype: bfloat16
```
# [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_saishf__Kuno-Lake-7B)
| Metric |Value|
|---------------------------------|----:|
|Avg. |73.56|
|AI2 Reasoning Challenge (25-Shot)|71.84|
|HellaSwag (10-Shot) |88.15|
|MMLU (5-Shot) |64.76|
|TruthfulQA (0-shot) |66.83|
|Winogrande (5-shot) |84.45|
|GSM8k (5-shot) |65.35|
|
Qwen/Qwen1.5-4B-Chat-AWQ | Qwen | 2024-04-30T07:41:55Z | 733 | 2 | transformers | [
"transformers",
"safetensors",
"qwen2",
"text-generation",
"chat",
"conversational",
"en",
"license:other",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"4-bit",
"awq",
"region:us"
] | text-generation | 2024-02-03T07:00:13Z | ---
license: other
license_name: tongyi-qianwen-research
license_link: >-
https://huggingface.co/Qwen/Qwen1.5-4B-Chat-AWQ/blob/main/LICENSE
language:
- en
pipeline_tag: text-generation
tags:
- chat
---
# Qwen1.5-4B-Chat-AWQ
## Introduction
Qwen1.5 is the beta version of Qwen2, a transformer-based decoder-only language model pretrained on a large amount of data. In comparison with the previous released Qwen, the improvements include:
* 8 model sizes, including 0.5B, 1.8B, 4B, 7B, 14B, 32B and 72B dense models, and an MoE model of 14B with 2.7B activated;
* Significant performance improvement in human preference for chat models;
* Multilingual support of both base and chat models;
* Stable support of 32K context length for models of all sizes
* No need of `trust_remote_code`.
For more details, please refer to our [blog post](https://qwenlm.github.io/blog/qwen1.5/) and [GitHub repo](https://github.com/QwenLM/Qwen1.5).
<br>
## Model Details
Qwen1.5 is a language model series including decoder language models of different model sizes. For each size, we release the base language model and the aligned chat model. It is based on the Transformer architecture with SwiGLU activation, attention QKV bias, group query attention, mixture of sliding window attention and full attention, etc. Additionally, we have an improved tokenizer adaptive to multiple natural languages and codes. For the beta version, temporarily we did not include GQA (except for 32B) and the mixture of SWA and full attention.
## Training details
We pretrained the models with a large amount of data, and we post-trained the models with both supervised finetuning and direct preference optimization.
## Requirements
The code of Qwen1.5 has been in the latest Hugging face transformers and we advise you to install `transformers>=4.37.0`, or you might encounter the following error:
```
KeyError: 'qwen2'
```
## Quickstart
Here provides a code snippet with `apply_chat_template` to show you how to load the tokenizer and model and how to generate contents.
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
device = "cuda" # the device to load the model onto
model = AutoModelForCausalLM.from_pretrained(
"Qwen/Qwen1.5-4B-Chat-AWQ",
torch_dtype="auto",
device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen1.5-4B-Chat-AWQ")
prompt = "Give me a short introduction to large language model."
messages = [
{"role": "system", "content": "You are a helpful assistant."},
{"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]
```
## Tips
* If you encounter code switching or other bad cases, we advise you to use our provided hyper-parameters in `generation_config.json`.
## Citation
If you find our work helpful, feel free to give us a cite.
```
@article{qwen,
title={Qwen Technical Report},
author={Jinze Bai and Shuai Bai and Yunfei Chu and Zeyu Cui and Kai Dang and Xiaodong Deng and Yang Fan and Wenbin Ge and Yu Han and Fei Huang and Binyuan Hui and Luo Ji and Mei Li and Junyang Lin and Runji Lin and Dayiheng Liu and Gao Liu and Chengqiang Lu and Keming Lu and Jianxin Ma and Rui Men and Xingzhang Ren and Xuancheng Ren and Chuanqi Tan and Sinan Tan and Jianhong Tu and Peng Wang and Shijie Wang and Wei Wang and Shengguang Wu and Benfeng Xu and Jin Xu and An Yang and Hao Yang and Jian Yang and Shusheng Yang and Yang Yao and Bowen Yu and Hongyi Yuan and Zheng Yuan and Jianwei Zhang and Xingxuan Zhang and Yichang Zhang and Zhenru Zhang and Chang Zhou and Jingren Zhou and Xiaohuan Zhou and Tianhang Zhu},
journal={arXiv preprint arXiv:2309.16609},
year={2023}
}
```
|
vikash06/doctorLLM10k | vikash06 | 2024-03-04T15:35:11Z | 733 | 1 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"dataset:lavita/ChatDoctor-HealthCareMagic-100k",
"license:mit",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | 2024-02-04T06:16:22Z | ---
license: mit
datasets:
- lavita/ChatDoctor-HealthCareMagic-100k
model-index:
- name: doctorLLM10k
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: 54.95
name: normalized accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vikash06/doctorLLM10k
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: 79.94
name: normalized accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vikash06/doctorLLM10k
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: 44.4
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vikash06/doctorLLM10k
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: 44.76
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vikash06/doctorLLM10k
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: 70.01
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vikash06/doctorLLM10k
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: 10.16
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vikash06/doctorLLM10k
name: Open LLM Leaderboard
---
Sample Input on Postman API:
Number of epochs: 10
Number of Data points: 10000
# Creative Writing: Write a question or instruction that requires a creative medical response from a doctor.
The instruction should be reasonable to ask of a person with general medical knowledge and should not require searching.
In this task, your prompt should give very specific instructions to follow.
Constraints, instructions, guidelines, or requirements all work, and the more of them the better.
Reference dataset: https://github.com/Kent0n-Li/ChatDoctor
# [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_vikash06__doctorLLM10k)
| Metric |Value|
|---------------------------------|----:|
|Avg. |50.70|
|AI2 Reasoning Challenge (25-Shot)|54.95|
|HellaSwag (10-Shot) |79.94|
|MMLU (5-Shot) |44.40|
|TruthfulQA (0-shot) |44.76|
|Winogrande (5-shot) |70.01|
|GSM8k (5-shot) |10.16|
|
yam-peleg/Experiment1-7B | yam-peleg | 2024-02-10T10:01:17Z | 733 | 1 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"chat",
"en",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | 2024-02-10T09:29:30Z | ---
license: apache-2.0
language:
- en
library_name: transformers
pipeline_tag: text-generation
tags:
- chat
---
**Experiment1-7B**
An experiment for testing and refining a specific training and evaluation pipeline research framework.
This experiment aims to identify potential optimizations, focusing on data engineering, architecture efficiency, and evaluation performance.
The goal is to evaluate the effectiveness of a new training / evaluation pipeline for LLMs.
The experiment will explore adjustments in data preprocessing, model training algorithms, and evaluation metrics to test methods for improvement.
More details in the future experiments.
---
license: apache-2.0
--- |
yam-peleg/Experiment7-7B | yam-peleg | 2024-02-11T18:05:24Z | 733 | 0 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"arxiv:1910.09700",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | 2024-02-11T16:34:23Z | ---
library_name: transformers
license: apache-2.0
---
# 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. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **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] |
Radu1999/MisterUkrainianDPO | Radu1999 | 2024-02-12T08:34:24Z | 733 | 1 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"conversational",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | 2024-02-11T20:20:56Z | ---
library_name: transformers
license: apache-2.0
---
# Model card for MisterUkrainianDPO
DPO Iteration of [MisterUkrainian](https://huggingface.co/Radu1999/MisterUkrainian)
## Instruction format
In order to leverage instruction fine-tuning, your prompt should be surrounded by `[INST]` and `[/INST]` tokens.
E.g.
```
text = "[INST]Відповідайте лише буквою правильної відповіді: Елементи експресіонізму наявні у творі: A. «Камінний хрест», B. «Інститутка», C. «Маруся», D. «Людина»[/INST]"
```
This format is available as a [chat template](https://huggingface.co/docs/transformers/main/chat_templating) via the `apply_chat_template()` method:
## Model Architecture
This instruction model is based on Mistral-7B-v0.2, a transformer model with the following architecture choices:
- Grouped-Query Attention
- Sliding-Window Attention
- Byte-fallback BPE tokenizer
## 💻 Usage
```python
!pip install -qU transformers accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "Radu1999/MisterUkrainianDPO"
messages = [{"role": "user", "content": "What is a large language model?"}]
tokenizer = AutoTokenizer.from_pretrained(model)
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
pipeline = transformers.pipeline(
"text-generation",
model=model,
torch_dtype=torch.bfloat16,
device_map="auto",
)
outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])
```
## Author
Radu Chivereanu |
eren23/merged-dpo-binarized-NeutrixOmnibe-7B | eren23 | 2024-03-05T15:45:51Z | 733 | 0 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"merge",
"mergekit",
"lazymergekit",
"eren23/dpo-binarized-NeutrixOmnibe-7B",
"Kukedlc/NeuTrixOmniBe-7B-model-remix",
"base_model:eren23/dpo-binarized-NeutrixOmnibe-7B",
"base_model:Kukedlc/NeuTrixOmniBe-7B-model-remix",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | 2024-02-12T12:05:18Z | ---
license: apache-2.0
tags:
- merge
- mergekit
- lazymergekit
- eren23/dpo-binarized-NeutrixOmnibe-7B
- Kukedlc/NeuTrixOmniBe-7B-model-remix
base_model:
- eren23/dpo-binarized-NeutrixOmnibe-7B
- Kukedlc/NeuTrixOmniBe-7B-model-remix
model-index:
- name: merged-dpo-binarized-NeutrixOmnibe-7B
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: 72.7
name: normalized accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=eren23/merged-dpo-binarized-NeutrixOmnibe-7B
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: 89.03
name: normalized accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=eren23/merged-dpo-binarized-NeutrixOmnibe-7B
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: 64.59
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=eren23/merged-dpo-binarized-NeutrixOmnibe-7B
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: 76.9
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=eren23/merged-dpo-binarized-NeutrixOmnibe-7B
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: 85.08
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=eren23/merged-dpo-binarized-NeutrixOmnibe-7B
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: 68.92
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=eren23/merged-dpo-binarized-NeutrixOmnibe-7B
name: Open LLM Leaderboard
---
# merged-dpo-binarized-NeutrixOmnibe-7B
merged-dpo-binarized-NeutrixOmnibe-7B is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
* [eren23/dpo-binarized-NeutrixOmnibe-7B](https://huggingface.co/eren23/dpo-binarized-NeutrixOmnibe-7B)
* [Kukedlc/NeuTrixOmniBe-7B-model-remix](https://huggingface.co/Kukedlc/NeuTrixOmniBe-7B-model-remix)
## 🧩 Configuration
```yaml
slices:
- sources:
- model: eren23/dpo-binarized-NeutrixOmnibe-7B
layer_range: [0, 32]
- model: Kukedlc/NeuTrixOmniBe-7B-model-remix
layer_range: [0, 32]
merge_method: slerp
base_model: eren23/dpo-binarized-NeutrixOmnibe-7B
parameters:
t:
- filter: self_attn
value: [0.2, 0.7, 0.8, 0.7, 1]
- filter: mlp
value: [0.8, 0.3, 0.2, 0.3, 0]
- value: 0.45
dtype: bfloat16
```
## 💻 Usage
```python
!pip install -qU transformers accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "eren23/merged-dpo-binarized-NeutrixOmnibe-7B"
messages = [{"role": "user", "content": "What is a large language model?"}]
tokenizer = AutoTokenizer.from_pretrained(model)
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
pipeline = transformers.pipeline(
"text-generation",
model=model,
torch_dtype=torch.float16,
device_map="auto",
)
outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])
```
# [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_eren23__merged-dpo-binarized-NeutrixOmnibe-7B)
| Metric |Value|
|---------------------------------|----:|
|Avg. |76.20|
|AI2 Reasoning Challenge (25-Shot)|72.70|
|HellaSwag (10-Shot) |89.03|
|MMLU (5-Shot) |64.59|
|TruthfulQA (0-shot) |76.90|
|Winogrande (5-shot) |85.08|
|GSM8k (5-shot) |68.92|
|
paulml/DPOB-INMTOB-7B | paulml | 2024-02-12T17:07:40Z | 733 | 2 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"merge",
"mergekit",
"lazymergekit",
"liminerity/Omningotex-7b-slerp",
"eren23/merged-dpo-binarized-NeutrixOmnibe-7B",
"base_model:liminerity/Omningotex-7b-slerp",
"base_model:eren23/merged-dpo-binarized-NeutrixOmnibe-7B",
"license:cc-by-nc-4.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | 2024-02-12T14:27:41Z | ---
license: cc-by-nc-4.0
tags:
- merge
- mergekit
- lazymergekit
- liminerity/Omningotex-7b-slerp
- eren23/merged-dpo-binarized-NeutrixOmnibe-7B
base_model:
- liminerity/Omningotex-7b-slerp
- eren23/merged-dpo-binarized-NeutrixOmnibe-7B
model-index:
- name: DPOB-INMTOB-7B
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: 73.21
name: normalized accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=paulml/DPOB-INMTOB-7B
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: 89.0
name: normalized accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=paulml/DPOB-INMTOB-7B
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: 64.54
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=paulml/DPOB-INMTOB-7B
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: 76.6
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=paulml/DPOB-INMTOB-7B
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: 84.69
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=paulml/DPOB-INMTOB-7B
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: 69.22
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=paulml/DPOB-INMTOB-7B
name: Open LLM Leaderboard
---
# DPOB-INMTOB-7B
DPOB-INMTOB-7B is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
* [liminerity/Omningotex-7b-slerp](https://huggingface.co/liminerity/Omningotex-7b-slerp)
* [eren23/merged-dpo-binarized-NeutrixOmnibe-7B](https://huggingface.co/eren23/merged-dpo-binarized-NeutrixOmnibe-7B)
## 🧩 Configuration
```yaml
slices:
- sources:
- model: liminerity/Omningotex-7b-slerp
layer_range: [0, 32]
- model: eren23/merged-dpo-binarized-NeutrixOmnibe-7B
layer_range: [0, 32]
merge_method: slerp
base_model: liminerity/Omningotex-7b-slerp
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
dtype: bfloat16
```
## 💻 Usage
```python
!pip install -qU transformers accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "paulml/DPOB-INMTOB-7B"
messages = [{"role": "user", "content": "What is a large language model?"}]
tokenizer = AutoTokenizer.from_pretrained(model)
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
pipeline = transformers.pipeline(
"text-generation",
model=model,
torch_dtype=torch.float16,
device_map="auto",
)
outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])
```
# [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_paulml__DPOB-INMTOB-7B)
| Metric |Value|
|---------------------------------|----:|
|Avg. |76.21|
|AI2 Reasoning Challenge (25-Shot)|73.21|
|HellaSwag (10-Shot) |89.00|
|MMLU (5-Shot) |64.54|
|TruthfulQA (0-shot) |76.60|
|Winogrande (5-shot) |84.69|
|GSM8k (5-shot) |69.22|
|
uukuguy/speechless-thoughts-mistral-7b | uukuguy | 2024-02-15T15:42:03Z | 733 | 1 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"llama-2",
"code",
"en",
"dataset:jondurbin/airoboros-2.2",
"dataset:Open-Orca/OpenOrca",
"dataset:garage-bAInd/Open-Platypus",
"dataset:WizardLM/WizardLM_evol_instruct_V2_196k",
"dataset:TokenBender/python_eval_instruct_51k",
"dataset:codefuse-ai/Evol-Instruction-66k",
"license:llama2",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | 2024-02-13T03:56:19Z | ---
language:
- en
library_name: transformers
pipeline_tag: text-generation
datasets:
- jondurbin/airoboros-2.2
- Open-Orca/OpenOrca
- garage-bAInd/Open-Platypus
- WizardLM/WizardLM_evol_instruct_V2_196k
- TokenBender/python_eval_instruct_51k
- codefuse-ai/Evol-Instruction-66k
tags:
- llama-2
- code
license: llama2
model-index:
- name: SpeechlessCoder
results:
- task:
type: text-generation
dataset:
type: openai_humaneval
name: HumanEval
metrics:
- name: pass@1
type: pass@1
value:
verified: false
---
<p><h1> speechless-thoughts-mistral-7b </h1></p>
[code](https://github.com/uukuguy/multi_loras)
speechless-thoughts-mistral-7b is fine-tuned as a baseline of the [speechless-sparsetral-16x7b-MoE](https://huggingface.co/uukuguy/speechless-sparsetral-16x7b-MoE).
The specific datasets (speechless-thoughts-252k) are as follows:
- jondurbin/airoboros-2.2: Filter categories related to coding, reasoning and planning. 23,462 samples.
- Open-Orca/OpenOrca: Filter the 'cot' category in 1M GPT4 dataset. 74,440 samples.
- garage-bAInd/Open-Platypus: 100%, 24,926 samples.
- WizardLM/WizardLM_evol_instruct_V2_196k: Coding coversation part. 30,185 samples
- TokenBender/python_eval_instruct_51k: “python” in output .40,309 samples
- Spider: 8,659 samples
- codefuse-ai/Evol-Instruction-66k: 100%, 66,862 samples
## Alpaca Prompt Format
```
### Instruction:
<instruction>
### Response:
```
## Usage
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
model_name_or_path="uukuguy/speechless-thoughts-mistral-7b"
tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(model_name_or_path, device_map="auto", trust_remote_code=True).eval()
system = ""Below is an instruction that describes a task.\nWrite a response that appropriately completes the request.\n\n""
prompt = f"{system}\n\n### Instruction:\n{instruction}\n\n### Response:"
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
pred = model.generate(**inputs, max_length=4096, do_sample=True, top_k=50, top_p=0.99, temperature=0.9, num_return_sequences=1)
print(tokenizer.decode(pred.cpu()[0], skip_special_tokens=True))
```
## HumanEval
| Metric | Value |
| --- | --- |
| humaneval-python | |
## lm-evaluation-harness
```json
{'ARC (acc_norm)': ,
'HellaSwag (acc_norm)': ,
'MMLU (acc)': ,
'TruthfulQA (mc2)': ,
'Winoground (acc)': ,
'GSM8K (acc)': ,
'DROP (f1)': ,
'Open LLM Score': }
```
# [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_uukuguy__speechless-thoughts-mistral-7b)
| Metric | Value |
|-----------------------|---------------------------|
| Avg. | 59.72 |
| ARC (25-shot) | 58.96 |
| HellaSwag (10-shot) | 80.71 |
| MMLU (5-shot) | 60.11 |
| TruthfulQA (0-shot) | 49.91 |
| Winogrande (5-shot) | 77.82 |
| GSM8K (5-shot) | 30.78 |
|
Locutusque/Hercules-3.0-Mistral-7B | Locutusque | 2024-02-19T03:40:58Z | 733 | 3 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"dataset:Locutusque/Hercules-v3.0",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | 2024-02-17T05:24:22Z | ---
library_name: transformers
license: apache-2.0
datasets:
- Locutusque/Hercules-v3.0
---
# Model Card: Hercules-3.0-Mistral-7B
## Model Description
Hercules-3.0-Mistral-7B is a fine-tuned language model derived from Mistralai/Mistral-7B-v0.1. It is specifically designed to excel in instruction following, function calls, and conversational interactions across various scientific and technical domains. The dataset used for fine-tuning, also named Hercules-v3.0, expands upon the diverse capabilities of OpenHermes-2.5 with contributions from numerous curated datasets. This fine-tuning has hercules-v3.0 with enhanced abilities in:
- Complex Instruction Following: Understanding and accurately executing multi-step instructions, even those involving specialized terminology.
- Function Calling: Seamlessly interpreting and executing function calls, providing appropriate input and output values.
- Domain-Specific Knowledge: Engaging in informative and educational conversations about Biology, Chemistry, Physics, Mathematics, Medicine, Computer Science, and more.
## Intended Uses & Potential Bias
Hercules-3.0-Mistral-7B is well-suited to the following applications:
- Specialized Chatbots: Creating knowledgeable chatbots and conversational agents in scientific and technical fields.
- Instructional Assistants: Supporting users with educational and step-by-step guidance in various disciplines.
- Code Generation and Execution: Facilitating code execution through function calls, aiding in software development and prototyping.
**Important Note: Although Hercules-v3.0 is carefully constructed, it's important to be aware that the underlying data sources may contain biases or reflect harmful stereotypes. Use this model with caution and consider additional measures to mitigate potential biases in its responses.**
## Limitations and Risks
- Toxicity: The dataset contains toxic or harmful examples.
- Hallucinations and Factual Errors: Like other language models, Hercules-3.0-Mistral-7B may generate incorrect or misleading information, especially in specialized domains where it lacks sufficient expertise.
- Potential for Misuse: The ability to engage in technical conversations and execute function calls could be misused for malicious purposes.
## Training Data
Hercules-3.0-Mistral-7B is fine-tuned from the following sources:
- `cognitivecomputations/dolphin`
- `Evol Instruct 70K & 140K`
- `teknium/GPT4-LLM-Cleaned`
- `jondurbin/airoboros-3.2`
- `AlekseyKorshuk/camel-chatml`
- `CollectiveCognition/chats-data-2023-09-22`
- `Nebulous/lmsys-chat-1m-smortmodelsonly`
- `glaiveai/glaive-code-assistant-v2`
- `glaiveai/glaive-code-assistant`
- `glaiveai/glaive-function-calling-v2`
- `garage-bAInd/Open-Platypus`
- `meta-math/MetaMathQA`
- `teknium/GPTeacher-General-Instruct`
- `GPTeacher roleplay datasets`
- `BI55/MedText`
- `pubmed_qa labeled subset`
- `Unnatural Instructions`
- `M4-ai/LDJnr_combined_inout_format`
- `CollectiveCognition/chats-data-2023-09-27`
- `CollectiveCognition/chats-data-2023-10-16`
- `NobodyExistsOnTheInternet/sharegptPIPPA`
- `yuekai/openchat_sharegpt_v3_vicuna_format`
- `ise-uiuc/Magicoder-Evol-Instruct-110K`
- `Squish42/bluemoon-fandom-1-1-rp-cleaned`
- `sablo/oasst2_curated`
## Training Procedure
- This model was trained on 8 kaggle TPUs, using torch xla SPMD for high MXU efficiency. There was no expense on my end (meaning you can reproduce this too!)
- A learning rate of 2e-06 with the Adam optimizer. A linear scheduler was used, with an end factor of 0.3. A low learning rate was used to prevent exploding gradients.
- No mixed precision was used, with the default dtype being bfloat16.
- Trained on 1,400,000 examples of Hercules-v3.0
- No model parameters were frozen.
- This model was trained on OpenAI's ChatML prompt format. Because this model has function calling capabilities, the prompt format is slightly different, here's what it would look like: ```<|im_start|>system\n{message}<|im_end|>\n<|im_start|>user\n{user message}<|im_end|>\n<|im_start|>call\n{function call message}<|im_end|>\n<|im_start|>function\n{function response message}<|im_end|>\n<|im_start|>assistant\n{assistant message}</s>```
This model was fine-tuned using the TPU-Alignment repository. https://github.com/Locutusque/TPU-Alignment
# Disclaimer
A dataset used in the Hercules-v3.0 was found to be causing performance degradation issues. I would recommend using Hercules-2.5 over this model, until Hercules-3.1 is released.
# Quants
ExLlamaV2 by bartowski https://huggingface.co/bartowski/Hercules-3.0-Mistral-7B-exl2 |
Kukedlc/Neural4gsm8k | Kukedlc | 2024-05-25T17:09:38Z | 733 | 0 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"merge",
"mergekit",
"lazymergekit",
"Kukedlc/Neural-4-ARC-7B-slerp",
"Kukedlc/Neural-4-GSM8K-7B-slerp",
"base_model:Kukedlc/Neural-4-ARC-7B-slerp",
"base_model:Kukedlc/Neural-4-GSM8K-7B-slerp",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | 2024-02-17T20:18:15Z | ---
license: apache-2.0
tags:
- merge
- mergekit
- lazymergekit
- Kukedlc/Neural-4-ARC-7B-slerp
- Kukedlc/Neural-4-GSM8K-7B-slerp
base_model:
- Kukedlc/Neural-4-ARC-7B-slerp
- Kukedlc/Neural-4-GSM8K-7B-slerp
model-index:
- name: Neural4gsm8k
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: 72.27
name: normalized accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Kukedlc/Neural4gsm8k
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: 88.45
name: normalized accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Kukedlc/Neural4gsm8k
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: 64.76
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Kukedlc/Neural4gsm8k
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: 69.65
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Kukedlc/Neural4gsm8k
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: 83.35
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Kukedlc/Neural4gsm8k
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: 73.39
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Kukedlc/Neural4gsm8k
name: Open LLM Leaderboard
---
# Neural-4-ARC-7B-slerp
Neural-4-ARC-7B-slerp is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
* [Kukedlc/Neural-4-ARC-7B-slerp](https://huggingface.co/Kukedlc/Neural-4-ARC-7B-slerp)
* [Kukedlc/Neural-4-GSM8K-7B-slerp](https://huggingface.co/Kukedlc/Neural-4-GSM8K-7B-slerp)
## 🧩 Configuration
```yaml
slices:
- sources:
- model: Kukedlc/Neural-4-ARC-7B-slerp
layer_range: [0, 32]
- model: Kukedlc/Neural-4-GSM8K-7B-slerp
layer_range: [0, 32]
merge_method: slerp
base_model: Kukedlc/Neural-4-GSM8K-7B-slerp
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
dtype: bfloat16
```
## 💻 Usage
```python
!pip install -qU transformers accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "Kukedlc/Neural-4-ARC-7B-slerp"
messages = [{"role": "user", "content": "What is a large language model?"}]
tokenizer = AutoTokenizer.from_pretrained(model)
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
pipeline = transformers.pipeline(
"text-generation",
model=model,
torch_dtype=torch.float16,
device_map="auto",
)
outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])
```
# [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_Kukedlc__Neural4gsm8k)
| Metric |Value|
|---------------------------------|----:|
|Avg. |75.31|
|AI2 Reasoning Challenge (25-Shot)|72.27|
|HellaSwag (10-Shot) |88.45|
|MMLU (5-Shot) |64.76|
|TruthfulQA (0-shot) |69.65|
|Winogrande (5-shot) |83.35|
|GSM8k (5-shot) |73.39|
|
sethuiyer/Diana-7B | sethuiyer | 2024-03-02T08:28:35Z | 733 | 0 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"mergekit",
"merge",
"not-for-all-audiences",
"conversational",
"en",
"base_model:SanjiWatsuki/Silicon-Maid-7B",
"base_model:sethuiyer/Aika-7B",
"base_model:sethuiyer/Nandine-7b",
"base_model:mlabonne/AlphaMonarch-7B",
"license:cc",
"model-index",
"autotrain_compatible",
"text-generation-inference",
"region:us"
] | text-generation | 2024-02-18T06:14:47Z | ---
inference: false
base_model:
- SanjiWatsuki/Silicon-Maid-7B
- sethuiyer/Aika-7B
- sethuiyer/Nandine-7b
- mlabonne/AlphaMonarch-7B
library_name: transformers
tags:
- mergekit
- merge
- not-for-all-audiences
license: cc
model-index:
- name: sethuiyer/Diana-7B
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: 68.34
name: normalized accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sethuiyer/Diana-7B
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: 86.73
name: normalized accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sethuiyer/Diana-7B
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: 64.58
name: accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sethuiyer/Diana-7B
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: 60.55
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sethuiyer/Diana-7B
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: 80.19
name: accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sethuiyer/Diana-7B
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: 63.23
name: accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sethuiyer/Diana-7B
name: Open LLM Leaderboard
language:
- en
pipeline_tag: text-generation
---
# Diana-7B
<p align="center">
<img src="https://huggingface.co/sethuiyer/Diana-7B/resolve/main/diana.webp" height="128px" alt="Diana">
</p>
This is Diana-7b, rated **93.56/100** by GPT-4 on a collection of 30 synthetic prompts generated by GPT-4.
Diana stands for **D**eep **I**nsight and **A**nalytical **N**arrative **A**ssistant and is a merge of the following models using [mergekit](https://github.com/cg123/mergekit):
1. [mlabonne/AlphaMonarch-7B](https://huggingface.co/mlabonne/AlphaMonarch-7B): This model has impressive conversational abilities, formal and sophisticated style, and strong reasoning skills.
2. [sethuiyer/Aika-7b](https://huggingface.co/sethuiyer/Aika-7B): A merge of SanjiWatsuki/Silicon-Maid-7B, Guilherme34/Samantha-v2, jan-hq/stealth-v1.3, and senseable/WestLake-7B-v2, Aika-7b is designed for natural and human-like interactions, accurate information delivery, comprehensive analysis, emotional intelligence, clarity, and structure.
3. [SanjiWatsuki/Silicon-Maid-7B](https://huggingface.co/SanjiWatsuki/Silicon-Maid-7B): This model is known for its excellent multi-turn conversational skills and logical coherence.
4. [sethuiyer/Nandine-7b](https://huggingface.co/sethuiyer/Nandine-7b): A merge of senseable/Westlake-7B, Guilherme34/Samantha-v2, and uukuguy/speechless-mistral-six-in-one-7b, Nandine-7b excels in narrative skill, empathetic interaction, intellectual depth, and eloquent communication.
By combining these models, Diana-7B offers a balanced blend of capabilities, making it suitable for various tasks and providing a comprehensive AI companion for creative writing, thoughtful discussions, problem-solving, and general assistance.
## OpenLLM Benchmark
| Model | Average ⬆️ | ARC | HellaSwag | MMLU | TruthfulQA | Winogrande | GSM8K |
|--------------------------------|------------|-------|-----------|-------|------------|------------|-------|
| sethuiyer/Diana-7B 📑 | 70.6 | 68.34 | 86.73 | 64.58 | 60.55 | 80.19 | 63.23 |
## Nous Benchmark
| Model |AGIEval|GPT4All|TruthfulQA|Bigbench|Average|
|---------------------------------------------------------|------:|------:|---------:|-------:|------:|
|[Diana-7B](https://huggingface.co/sethuiyer/Diana-7B)| 44.38 | 75.1| 60.55| 44.58| 56.09|
### Configuration
The following YAML configuration was used to produce this model:
```yaml
base_model: mlabonne/AlphaMonarch-7B
dtype: bfloat16
merge_method: dare_ties
models:
- model: mlabonne/AlphaMonarch-7B
- model: sethuiyer/Aika-7B
parameters:
density: 0.85
weight: 0.30
- model: SanjiWatsuki/Silicon-Maid-7B
parameters:
density: 0.85
weight: 0.50
- model: sethuiyer/Nandine-7b
parameters:
density: 0.85
weight: 0.30
parameters:
int8_mask: true
```
## Prompt Template
```text
{bos}user
{ .Prompt }{eos}
{bos}assistant
```
## GGUF
GGUF files are available at [Diana-7B-GGUF](https://huggingface.co/sethuiyer/Diana-7B-GGUF/tree/main)
## Ollama
Diana is now available on Ollama. You can use it by running the command ```ollama run stuehieyr/diana``` in your
terminal. If you have limited computing resources, check out this [video](https://www.youtube.com/watch?v=Qa1h7ygwQq8) to learn how to run it on
a Google Colab backend.
|
ChaoticNeutrals/This_is_fine_7B | ChaoticNeutrals | 2024-03-04T20:11:31Z | 733 | 2 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"mergekit",
"merge",
"conversational",
"arxiv:2311.03099",
"arxiv:2306.01708",
"base_model:jeiku/NarrativeNexus_7B",
"base_model:mlabonne/AlphaMonarch-7B",
"base_model:CultriX/NeuralTrix-bf16",
"base_model:jeiku/Cookie_7B",
"base_model:jeiku/Luna_7B",
"license:other",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | 2024-02-23T04:47:51Z | ---
license: other
library_name: transformers
tags:
- mergekit
- merge
base_model:
- jeiku/NarrativeNexus_7B
- mlabonne/AlphaMonarch-7B
- CultriX/NeuralTrix-bf16
- jeiku/Cookie_7B
- jeiku/Luna_7B
model-index:
- name: This_is_fine_7B
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: 70.31
name: normalized accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ChaoticNeutrals/This_is_fine_7B
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: 87.28
name: normalized accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ChaoticNeutrals/This_is_fine_7B
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: 64.51
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ChaoticNeutrals/This_is_fine_7B
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: 65.79
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ChaoticNeutrals/This_is_fine_7B
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: 81.61
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ChaoticNeutrals/This_is_fine_7B
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: 62.77
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ChaoticNeutrals/This_is_fine_7B
name: Open LLM Leaderboard
---
# Fine
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
## Merge Details
### Merge Method
This model was merged using the [DARE](https://arxiv.org/abs/2311.03099) [TIES](https://arxiv.org/abs/2306.01708) merge method using [mlabonne/AlphaMonarch-7B](https://huggingface.co/mlabonne/AlphaMonarch-7B) as a base.
### Models Merged
The following models were included in the merge:
* [jeiku/NarrativeNexus_7B](https://huggingface.co/jeiku/NarrativeNexus_7B)
* [CultriX/NeuralTrix-bf16](https://huggingface.co/CultriX/NeuralTrix-bf16)
* [jeiku/Cookie_7B](https://huggingface.co/jeiku/Cookie_7B)
* [jeiku/Luna_7B](https://huggingface.co/jeiku/Luna_7B)
### Configuration
The following YAML configuration was used to produce this model:
```yaml
merge_method: dare_ties
base_model: mlabonne/AlphaMonarch-7B
parameters:
normalize: true
models:
- model: jeiku/Luna_7B
parameters:
weight: 0.75
- model: jeiku/Cookie_7B
parameters:
weight: 1
- model: jeiku/NarrativeNexus_7B
parameters:
weight: 0.5
- model: CultriX/NeuralTrix-bf16
parameters:
weight: 0.75
- model: mlabonne/AlphaMonarch-7B
parameters:
weight: 1
dtype: float16
```
# [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_ChaoticNeutrals__This_is_fine_7B)
| Metric |Value|
|---------------------------------|----:|
|Avg. |72.05|
|AI2 Reasoning Challenge (25-Shot)|70.31|
|HellaSwag (10-Shot) |87.28|
|MMLU (5-Shot) |64.51|
|TruthfulQA (0-shot) |65.79|
|Winogrande (5-shot) |81.61|
|GSM8k (5-shot) |62.77|
|
Minami-su/Qwen1.5-7B-Chat_llamafy | Minami-su | 2024-03-18T12:19:23Z | 733 | 6 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"qwen",
"qwen1.5",
"qwen2",
"conversational",
"en",
"zh",
"license:other",
"autotrain_compatible",
"text-generation-inference",
"region:us"
] | text-generation | 2024-02-24T06:06:51Z | ---
license: other
license_name: qwen
license_link: >-
https://github.com/QwenLM/Qwen/blob/main/Tongyi%20Qianwen%20LICENSE%20AGREEMENT
language:
- en
- zh
library_name: transformers
pipeline_tag: text-generation
inference: false
tags:
- llama
- qwen
- qwen1.5
- qwen2
---
This is the LLaMAfied version of [Qwen1.5-7B-Chat](https://huggingface.co/Qwen/Qwen1.5-7B-Chat) model by Alibaba Cloud.
The original codebase can be found at: (https://github.com/hiyouga/LLaMA-Factory/blob/main/tests/llamafy_qwen.py).
I have made modifications to make it compatible with qwen1.5.
This model is converted with https://github.com/Minami-su/character_AI_open/blob/main/llamafy_qwen_v2.py
Usage:
```python
from transformers import AutoModelForCausalLM, AutoTokenizer, TextStreamer
tokenizer = AutoTokenizer.from_pretrained("Minami-su/Qwen1.5-7B-Chat_llamafy")
model = AutoModelForCausalLM.from_pretrained("Minami-su/Qwen1.5-7B-Chat_llamafy", torch_dtype="auto", device_map="auto")
streamer = TextStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True)
messages = [
{"role": "user", "content": "Who are you?"}
]
inputs = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt")
inputs = inputs.to("cuda")
generate_ids = model.generate(inputs,max_length=2048, streamer=streamer)
```
## Test
load in 4bit
```
hf-causal (pretrained=Qwen1.5-7B-Chat), limit: None, provide_description: False, num_fewshot: 0, batch_size: 8
| Task |Version| Metric |Value | |Stderr|
|-------------|------:|--------|-----:|---|-----:|
|arc_challenge| 0|acc |0.4155|± |0.0144|
| | |acc_norm|0.4480|± |0.0145|
|truthfulqa_mc| 1|mc1 |0.3513|± |0.0167|
| | |mc2 |0.5165|± |0.0159|
|winogrande | 0|acc |0.6330|± |0.0135|
```
load in 4bit
```
hf-causal (pretrained=Qwen1.5-7B-Chat_llamafy), limit: None, provide_description: False, num_fewshot: 0, batch_size: 8
| Task |Version| Metric |Value | |Stderr|
|-------------|------:|--------|-----:|---|-----:|
|arc_challenge| 0|acc |0.4172|± |0.0144|
| | |acc_norm|0.4488|± |0.0145|
|truthfulqa_mc| 1|mc1 |0.3501|± |0.0167|
| | |mc2 |0.5164|± |0.0159|
|winogrande | 0|acc |0.6306|± |0.0136|
```
``` |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.