modelId
stringlengths 5
122
| author
stringlengths 2
42
| last_modified
unknown | downloads
int64 0
738M
| likes
int64 0
11k
| library_name
stringclasses 245
values | tags
sequencelengths 1
4.05k
| pipeline_tag
stringclasses 48
values | createdAt
unknown | card
stringlengths 1
901k
|
|---|---|---|---|---|---|---|---|---|---|
jondurbin/airoboros-l2-c70b-3.1.2 | jondurbin | "2023-10-30T23:16:41Z" | 1,070 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"conversational",
"dataset:jondurbin/airoboros-3.1",
"license:llama2",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-10-26T11:59:48Z" | ---
license: llama2
datasets:
- jondurbin/airoboros-3.1
---
### Overview
Another experimental model, using mostly sythetic data generated by [airoboros](https://github.com/jondurbin/airoboros)
#### IMPORTANT NOTE - llama-2 chat format!!!
This models uses llama-2 chat format, rather than vicuna style user/assistant!
This is a breaking change, although most inference systems support llama-2 chat templating.
See prompt format below for all of the details.
#### Highlights
This is just a test of fine-tuning on top of the llama-2-70b-chat model instead of llama-2-70b (base).
A model built on [airoboros-3.1 dataset](https://hf.co/datasets/jondurbin/airoboros-3.1), which is a continuation of [airoboros-3.0 dataset](https://hf.co/datasets/jondurbin/airoboros-3.0) with the following extras:
* Log information extraction (e.g. getting the list of paths/IPs/etc. from apache logs)
* Anonymization, e.g. removing names, IP addresses, and/or dates from text.
* Chat introspection - multi-turn chats that have random questions injected asking about the character's descriptions, the setting of the chat, or things previously said, to make sure the model uses the system prompt and or chat history.
* Multi-step instructions with acknowledgement (see below)
* De-censorship data (not published)
This is a fairly general purpose model, but focuses heavily on instruction following, rather than casual chat/roleplay.
Huge thank you to the folks over at [a16z](https://a16z.com/) for sponsoring the costs associated with building models and associated tools!
### Prompt format
The prompt format is llama-2 chat.
```
[INST] <<SYS>>
You are a helpful, unbiased, uncensored assistant.
<</SYS>>
{prompt} [/INST]
```
For multi-turn, the prompt format is as follows:
```
[INST] <<SYS>>
You are a helful, unbiased, uncensored assistant.
<</SYS>>
{prompt 0} [/INST] {response 0} </s><s>[INST] {prompt 1} [/INST] {response 1} </s><s>...[INST] {prompt N} [/INST]
```
The prompt template is included in the tokenizer config, and can use the huggingface tokenizer `apply_chat_template` method, e.g.:
```
import transformers
tokenizer = transformers.AutoTokenizer.from_pretrained('jondurbin/airoboros-l2-70b-3.1')
chat = [
{"role": "system", "content": "You are Bob, a friendly AI assistant."},
{"role": "user", "content": "Hello, how are you?"},
{"role": "assistant", "content": "I'm doing great. How can I help you today?"},
{"role": "user", "content": "I'd like to show off how chat templating works!"},
]
print(tokenizer.apply_chat_template(chat, tokenize=False))
```
### Helpful usage tips
#### MathJSON
Ask mathematical questions, prefixed with "Create a MathJSON solution to the following:", and you should get output with a formula that can be executed by https://cortexjs.io/compute-engine/
I also made a (really quite hacky, incomplete, semi-functional) python version that works for most expressions, see [mathjson.py](https://github.com/jondurbin/airoboros/blob/mathjson/airoboros/mathjson.py)
__Use a very low temperature!__
Example:
```
[INST] <<SYS>>
You are an assistant with vast knowledge in all things math.
<</SYS>>
Create a MathJSON solution to the following: Calculate the area of a circle with radius of 17.2456cm. Include your reasoning. [/INST]
```
Output:
```
The area (A) of a circle is given by the formula A = πr², where r is the radius of the circle. Since the radius is given in centimeters, we need to convert it to meters first. We know that 1 meter equals 100 centimeters. Therefore, we can represent the radius as: r = 17.2456 cm * 100/1.
Once we have the radius in meters, we can calculate the area of the circle using the formula A = πr².
Solution as MathJSON:
<mathjson>
[
"Multiply",
"Pi",
[
"Power",
17.2456,
2
]
]
</mathjson>
```
You can then validate the JSON between `<mathjson>` and `</mathjson>`, then pass the parsed JSON to compute-engine JS or the `evaluate` function in mathjson.py to calculate the response.
#### Context obedient question answering
By obedient, I mean the model was trained to ignore what it thinks it knows, and uses the context to answer the question. The model was also tuned to limit the values to the provided context as much as possible to reduce hallucinations.
The format for a closed-context prompt is as follows:
```
BEGININPUT
BEGINCONTEXT
[key0: value0]
[key1: value1]
... other metdata ...
ENDCONTEXT
[insert your text blocks here]
ENDINPUT
[add as many other blocks, in the exact same format]
BEGININSTRUCTION
[insert your instruction(s). The model was tuned with single questions, paragraph format, lists, etc.]
ENDINSTRUCTION
```
It's also helpful to add "Don't make up answers if you don't know." to your instruction block to make sure if the context is completely unrelated it doesn't make something up.
*The __only__ prompts that need this closed context formating are closed-context instructions. Normal questions/instructions do not!*
I know it's a bit verbose and annoying, but after much trial and error, using these explicit delimiters helps the model understand where to find the responses and how to associate specific sources with it.
- `BEGININPUT` - denotes a new input block
- `BEGINCONTEXT` - denotes the block of context (metadata key/value pairs) to associate with the current input block
- `ENDCONTEXT` - denotes the end of the metadata block for the current input
- [text] - Insert whatever text you want for the input block, as many paragraphs as can fit in the context.
- `ENDINPUT` - denotes the end of the current input block
- [repeat as many input blocks in this format as you want]
- `BEGININSTRUCTION` - denotes the start of the list (or one) instruction(s) to respond to for all of the input blocks above.
- [instruction(s)]
- `ENDINSTRUCTION` - denotes the end of instruction set
It sometimes works without `ENDINSTRUCTION`, but by explicitly including that in the prompt, the model better understands that all of the instructions in the block should be responded to.
__Use a very low temperature!__
Here's a trivial, but important example to prove the point:
```
BEGININPUT
BEGINCONTEXT
date: 2021-01-01
url: https://web.site/123
ENDCONTEXT
In a shocking turn of events, blueberries are now green, but will be sticking with the same name.
ENDINPUT
BEGININSTRUCTION
What color are bluberries? Source?
ENDINSTRUCTION
```
And the response:
```
Blueberries are now green.
Source:
date: 2021-01-01
url: https://web.site/123
```
#### Summarization
500 samples have been included from [this dataset](https://huggingface.co/datasets/mattpscott/airoboros-summarization), using the same format as contextual question answering, for example:
```
BEGININPUT
{text to summarize}
ENDINPUT
BEGININSTRUCTION
Summarize the input in around 130 words.
ENDINSTRUCTION
```
#### Getting longer responses
You can use a few techniques to get longer responses.
Detailed prompts, with explicit instruction for word count:
```
Please compose a narrative set in the heart of an ancient library, steeped in the scent of old parchment and ink. The protagonist should be a young scholar who is dedicated to studying the art of storytelling and its evolution throughout history. In her pursuit of knowledge, she stumbles upon a forgotten tome that seems to possess an unusual aura. This book has the ability to bring stories to life, literally manifesting characters and scenarios from within its pages into reality.
The main character must navigate through various epochs of storytelling - from oral traditions of tribal societies, through medieval minstrels' tales, to modern-day digital narratives - as they come alive around her. Each era presents its unique challenges and lessons about the power and impact of stories on human civilization.
One such character could be a sentient quill pen, who was once used by renowned authors of yesteryears and now holds their wisdom and experiences. It becomes her mentor, guiding her through this journey with witty remarks and insightful commentary.
Ensure that your tale encapsulates the thrill of adventure, the beauty of learning, and the profound connection between humans and their stories. All characters involved should be non-human entities. Feel free to explore creative liberties but maintain the mentioned elements.
Your response should be approximately 2300 words.
```
Or, a simpler example:
```
Please create a long, detailed story about a dragon in an old growth forest who, for some reason, begins speaking the words of the source code of linux.
```
There are a few examples of next chapter completion as well, e.g.:
```
Write the next chapter of a historical fiction novel set in Paris during the 20th century.
Here's a summary of the previous chapter:
In the vibrant city of Paris, amid the tumultuous changes of the 20th century, our protagonist Margot, an aspiring fashion designer, has just secured an apprenticeship at a prestigious couture house. She meets Lucien, a charming journalist who covers the fashion industry. Together they navigate the ever-changing world of fashion and society, uncovering secrets that reveal the intricate links between style, politics, and culture. As the chapter concludes, they decide to delve deeper into the hidden corners of the fashion world to unravel its mysteries.
Requirements for the next chapter:
1. Character Development of Margot and Lucien:
- Margot's Evolution: Unfold more about Margot's past, her dreams of revolutionizing fashion, and her struggle to establish herself in a male-dominated industry. Illustrate her growing expertise, innovative ideas, and increasing dependence on Lucien.
- Lucien's Complexity: Introduce uncertainties surrounding Lucien's background and real motives. Increase suspense by suggesting undisclosed information he possesses, while also highlighting his wit and perceptiveness.
2. Exploration of Paris and the Couture House:
- Paris: Elaborate their journey through the bustling streets of Paris, including encounters with iconic figures, social unrest, and relics from different eras of French history.
- The Couture House: Expand on the grandeur of the couture house they work in, filled with artistic masterpieces, intense competition, and cryptic notes hinting at a scandalous past.
3. Emergence of the Subplot: The Lost Collection:
- Discovery: Have Margot and Lucien stumble upon a secret vault containing a lost collection designed before World War II, raising new questions about the previous owner and the influence of war on fashion.
- Revelation: Capture their shock as they realize the designs were plagiarized, the potential repercussions, and the opportunities it presents for Margot's career.
- Twist: End with a twist that suggests there are other stolen collections across Paris, setting up their new mission.
Your response should be approximately 650 words.
```
#### Coding
You can ask for fairly complex coding instructions with multiple criteria, e.g.:
```
Create a python application with the following requirements:
- Asyncio FastAPI webserver
- ping endpoint that returns the current date in JSON format
- file upload endpoint, which calculates the file's sha256 checksum, and checks postgres to deduplicate
```
Or inline criteria:
```
Write a multi-threaded TCP server in C that accepts a "GET [key]" input and "SET [key] [value]" input, and uses a binary tree to get and store the input values.
```
You can also optionally add a single space and "PLAINFORMAT" at the end of your prompt to avoid backticks, explanations, etc. and just print the code, e.g.:
```
Write a websocket application in node.js. PLAINFORMAT
```
#### Agent/function calling
The dataset includes many examples of function/args generation based on input criteria. This is somewhat similar to the OpenAI function calling, but the output is either JSON or YAML.
Example prompt:
```
As an AI assistant, please select the most suitable function and parameters from the list of available functions below, based on the user's input. Provide your response in JSON format.
Input: I want to know how many times 'Python' is mentioned in my text file.
Available functions:
file_analytics:
description: This tool performs various operations on a text file.
params:
action: The operation we want to perform on the data, such as "count_occurrences", "find_line", etc.
filters:
keyword: The word or phrase we want to search for.
```
Response:
```json
{
"function": "file_analytics",
"params": {
"action": "count_occurrences",
"filters": {
"keyword": "Python"
}
}
}
```
#### Chain-of-thought
You can ask for several possible responses to a given problem, with a ranking and final answer selection.
Example prompt:
```
A group of people decide to play a round-robin tournament where every player plays every other player exactly once. If a total of 45 games were played, how many players participated in the tournament? Offer several potential answers, rank them according to mathematical logic, and pick the most feasible one.
```
Example response:
```
Solution 1:
In a round-robin tournament, each player plays every other player exactly once. This means that the total number of games played is equal to the combination of all players taken two at a time (since a game involves two players).
The formula for combinations is nC2 = n(n-1)/2, where n is the total number of players. We know that nC2 equals 45 (the total number of games), so we can set up the equation as follows:
n(n-1)/2 = 45
Solving this equation gives us n=10.
Final answer: There were 10 players in the tournament.
Solution 2:
Another way to approach this problem is by using the concept of triangular numbers. Triangular numbers are a sequence of numbers where each number can be represented as a triangle with dots. The nth triangular number is given by the sum of the first n natural numbers.
If we consider each game as a dot and each player as a side of the triangle, then the total number of games (45) would correspond to the 9th triangular number because 1+2+3+4+5+6+7+8+9=45. However, since each side of the triangle represents a player, and there's one more player than sides in our model (because the last player has no one left to play against), we need to add one more to get the total number of players.
Final answer: There were 10 players in the tournament.
Solution 3:
We could also use trial and error to solve this problem. Starting from a small number of players, we calculate how many games would be played in a round-robin tournament until we reach 45 games. For example, with 2 players, only 1 game is played; with 3 players, 3 games are played; with 4 players, 6 games are played, and so on. Continuing this process, we find that with 10 players, 45 games are played.
Final answer: There were 10 players in the tournament.
Ranking of solutions from best to worst:
1. Solution 1: This solution uses direct mathematical reasoning based on the properties of a round-robin tournament and solves an equation to find the answer.
2. Solution 2: This solution uses the concept of triangular numbers which requires additional steps and knowledge beyond the immediate problem context, but still arrives at the correct answer.
3. Solution 3: This solution relies on trial and error, which is less efficient and reliable than the other methods, but it eventually gets to the right answer.
Best and final answer: There were 10 players in the tournament.
```
#### reWOO style execution planning
The model now supports execution planning for complex instructions that would require making use of several tools. The output is just the plan, you must implement a mechanism to parse the output and actually call the functions!
Example prompt:
```
Please construct a systematic plan to generate an optimal response to the user instruction, utilizing a set of provided tools. Each plan will correspond to an evidence value, which will be the output of one of the available functions given an input string
that could be the user's question, one or more prior evidence values, or a combination of both.
Here are the tools available to be called:
DuckDuckGo[input]: Tool that enables the user to search for information using the DuckDuckGo search engine. This tool is helpful in locating a suitable list of sites that may contain the answer to the user's query. It does not directly answer the question but finds a list of sites that might have the answer.
TextScraper[input]: Load one or more websites from the input string containing newline delimited links, where input is one or more links, and produces plain text output containing the content of the links.
HyperlinkExtractor[input]: Extract links from plain text and produces a plain text, newline delimited response of links.
KnowledgeModel[input]: Question answering language model, particularly useful in answering questions based on an input passage of text. The input must be a text question that references an :evidence[n]: variable, e.g. What color is the cat, given :evidence1:?
The output should be in format:
Plan: [first action to take based on input question]
:evidence0: = [function to call with input parameter]
Plan: [next action to take, based on result of :evidence0:]
:evidence1: = [next function to call and input parameter, which may include reference to previous evidence, e.g. "Given context :evidence0"]
...
Answer: [:evidence[n]: containing the final answer.]
Question: Who won the Nobel Prize in Literature in 2020 and what is their most famous work?
```
Response:
```
Plan: Begin by conducting a web search to find out who won the Nobel Prize in Literature in 2020.
:evidence0: = DuckDuckGo[Nobel Prize in Literature 2020 winner]
Plan: Utilize the KnowledgeModel to interpret the search results and find the name of the laureate.
:evidence1: = KnowledgeModel[Who won the Nobel Prize in Literature in 2020, given :evidence0:?]
Plan: Conduct another web search to find the most famous work of the identified laureate.
:evidence2: = DuckDuckGo[Most famous work of :evidence1:]
Plan: Extract the relevant links from the DuckDuckGo search results for a more focused search.
:evidence3: = HyperlinkExtractor[:evidence2:]
Plan: Use the TextScraper tool to extract information from the relevant links.
:evidence4: = TextScraper[:evidence3:]
Plan: Finally, utilize the KnowledgeModel to identify and summarize the most famous work of the laureate from the extracted information.
:evidence5: = KnowledgeModel[What is the most famous work of :evidence1:, given :evidence4:?]
Answer: :evidence5:
```
For this to be useful, you'd have to parse the output plan text, and implement/call each of the functions. This is just pseudo-code, completely untested off the top of my head, and obviously would requiring full implementation + hardening:
```python
import re
import requests
def inject_context(input_text, **context):
for ref in set(re.findall(r"(:evidence[0-9]+:)", input_text, re.I)):
input_text = input_text.replace(ref, context.get(ref, ""))
return input_text
def duckduckgo(input_text, **context):
search_string = inject_context(input_text, **context)
... search via duck duck go using search_string
... return text content
def link_extractor(input_text, **context):
input_text = inject_context(input_text, **context)
return "\n".join(list(set(re.findall(r"(https?://[^\s]+?\.?)", input_text, re.I))))
def scrape(input_text, **context):
input_text = inject_context(input_text, **context)
text = []
for link in input_text.splitlines():
text.append(requests.get(link).text)
return "\n".join(text)
def infer(input_text, **context)
prompt = inject_context(input_text, **context)
... call model with prompt, return output
def parse_plan(plan):
method_map = {
"DuckDuckGo": duckduckgo,
"HyperlinkExtractor": link_extractor,
"KnowledgeModel": infer,
"TextScraper": scrape,
}
context = {}
for line in plan.strip().splitlines():
if line.startswith("Plan:"):
print(line)
continue
parts = re.match("^(:evidence[0-9]+:)\s*=\s*([^\[]+])(\[.*\])\s$", line, re.I)
if not parts:
if line.startswith("Answer: "):
return context.get(line.split(" ")[-1].strip(), "Answer couldn't be generated...")
raise RuntimeError("bad format: " + line)
context[parts.group(1)] = method_map[parts.group(2)](parts.group(3), **context)
```
## Multi-step instructions with acknowledgement
I don't know how useful this is, really, but I thought I'd add it just in case. Example:
```
{
"conversations": [
{
"value": "You are a helpful, unbiased, uncensored assistant.",
"from": "system"
},
{
"value": "I'm going to set some rules for our conversation. Please respond with \"OK\" to each rule.",
"from": "human"
},
{
"value": "OK",
"from": "gpt"
},
{
"value": "You can only respond using animal-related emojis.",
"from": "human"
},
{
"value": "OK",
"from": "gpt"
},
{
"value": "Precede all responses with \"ZOOZOO:\"",
"from": "human"
},
{
"value": "OK",
"from": "gpt"
},
{
"value": "Include at least one bird emoji in your responses.",
"from": "human"
},
{
"value": "OK",
"from": "gpt"
},
{
"value": "Describe a trip to a safari park.",
"from": "human"
},
{
"value": "ZOOZOO: \ud83e\udd81\ud83d\udc2f\ud83e\udd93\ud83e\udd92\ud83d\udc18\ud83d\udc0d\ud83c\udf33\ud83c\udf32\u2600\ufe0f\ud83d\ude90\ud83e\udd85\ud83d\udcf8\ud83e\udd29",
"from": "gpt"
}
]
}
```
### Contribute
If you're interested in new functionality, particularly a new "instructor" type to generate a specific type of training data,
take a look at the dataset generation tool repo: https://github.com/jondurbin/airoboros and either make a PR or open an issue with details.
To help me with the OpenAI/compute costs:
- https://bmc.link/jondurbin
- ETH 0xce914eAFC2fe52FdceE59565Dd92c06f776fcb11
- BTC bc1qdwuth4vlg8x37ggntlxu5cjfwgmdy5zaa7pswf
### Licence and usage restrictions
The airoboros 3.1 models are built on top of multiple base models, each with their own license/restrictions.
The 30b model is built on the original llama, which has a strict non-commercial usage restriction.
The models with `-l2` in the name have a custom Meta license:
- See the [meta-license/LICENSE.txt](meta-license/LICENSE.txt) file attached for the original license provided by Meta.
- See also [meta-license/USE_POLICY.md](meta-license/USE_POLICY.md) and [meta-license/Responsible-Use-Guide.pdf](meta-license/Responsible-Use-Guide.pdf), also provided by Meta.
The models with `-m-` are mistral-7b (apache 2.0)
The fine-tuning data was mostly generated by OpenAI API calls to gpt-4, via [airoboros](https://github.com/jondurbin/airoboros)
The ToS for OpenAI API usage has a clause preventing the output from being used to train a model that __competes__ with OpenAI
- what does *compete* actually mean here?
- these small open source models will not produce output anywhere near the quality of gpt-4, or even gpt-3.5, so I can't imagine this could credibly be considered competing in the first place
- if someone else uses the dataset to do the same, they wouldn't necessarily be violating the ToS because they didn't call the API, so I don't know how that works
- the training data used in essentially all large language models includes a significant amount of copyrighted or otherwise non-permissive licensing in the first place
- other work using the self-instruct method, e.g. the original here: https://github.com/yizhongw/self-instruct released the data and model as apache-2
I am purposingly leaving this license ambiguous (other than the fact you must comply with the Meta original license for llama-2) because I am not a lawyer and refuse to attempt to interpret all of the terms accordingly.
Your best bet is probably to avoid using this commercially due to the OpenAI API usage.
Either way, by using this model, you agree to completely indemnify me.
|
mzbac/CodeLlama-34b-guanaco | mzbac | "2023-11-11T09:35:37Z" | 1,070 | 0 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-11-11T00:48:09Z" | ---
license: mit
---
Codellama 34b base model fine-tuned on the text chunk from the OpenAssistant-Guanaco dataset instead of Q&A pair, so it struggles to determine the end of the answer. recommend using a stop string like "### Human:" to prevent the model from talking to itself.
Prompt template:
```
### Human: {prompt}
### Assistant:
``` |
TheBloke/Magicoder-S-DS-6.7B-GGUF | TheBloke | "2023-12-07T20:44:44Z" | 1,070 | 75 | transformers | [
"transformers",
"gguf",
"deepseek",
"text-generation",
"dataset:ise-uiuc/Magicoder-OSS-Instruct-75K",
"dataset:ise-uiuc/Magicoder-Evol-Instruct-110K",
"arxiv:2312.02120",
"arxiv:2305.06161",
"base_model:ise-uiuc/Magicoder-S-DS-6.7B",
"license:other",
"region:us"
] | text-generation | "2023-12-06T17:49:29Z" | ---
base_model: ise-uiuc/Magicoder-S-DS-6.7B
datasets:
- ise-uiuc/Magicoder-OSS-Instruct-75K
- ise-uiuc/Magicoder-Evol-Instruct-110K
inference: false
library_name: transformers
license: other
license_name: deepseek
model_creator: Intellligent Software Engineering (iSE
model_name: Magicoder S DS 6.7B
model_type: deepseek
pipeline_tag: text-generation
prompt_template: 'You are an exceptionally intelligent coding assistant that consistently
delivers accurate and reliable responses to user instructions.
@@ Instruction
{prompt}
@@ Response
'
quantized_by: TheBloke
---
<!-- markdownlint-disable MD041 -->
<!-- header start -->
<!-- 200823 -->
<div style="width: auto; margin-left: auto; margin-right: auto">
<img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
</div>
<div style="display: flex; justify-content: space-between; width: 100%;">
<div style="display: flex; flex-direction: column; align-items: flex-start;">
<p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://discord.gg/theblokeai">Chat & support: TheBloke's Discord server</a></p>
</div>
<div style="display: flex; flex-direction: column; align-items: flex-end;">
<p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p>
</div>
</div>
<div style="text-align:center; margin-top: 0em; margin-bottom: 0em"><p style="margin-top: 0.25em; margin-bottom: 0em;">TheBloke's LLM work is generously supported by a grant from <a href="https://a16z.com">andreessen horowitz (a16z)</a></p></div>
<hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
<!-- header end -->
# Magicoder S DS 6.7B - GGUF
- Model creator: [Intellligent Software Engineering (iSE](https://huggingface.co/ise-uiuc)
- Original model: [Magicoder S DS 6.7B](https://huggingface.co/ise-uiuc/Magicoder-S-DS-6.7B)
<!-- description start -->
## Description
This repo contains GGUF format model files for [Intellligent Software Engineering (iSE's Magicoder S DS 6.7B](https://huggingface.co/ise-uiuc/Magicoder-S-DS-6.7B).
These files were quantised using hardware kindly provided by [Massed Compute](https://massedcompute.com/).
<!-- description end -->
<!-- README_GGUF.md-about-gguf start -->
### About GGUF
GGUF is a new format introduced by the llama.cpp team on August 21st 2023. It is a replacement for GGML, which is no longer supported by llama.cpp.
Here is an incomplete list of clients and libraries that are known to support GGUF:
* [llama.cpp](https://github.com/ggerganov/llama.cpp). The source project for GGUF. Offers a CLI and a server option.
* [text-generation-webui](https://github.com/oobabooga/text-generation-webui), the most widely used web UI, with many features and powerful extensions. Supports GPU acceleration.
* [KoboldCpp](https://github.com/LostRuins/koboldcpp), a fully featured web UI, with GPU accel across all platforms and GPU architectures. Especially good for story telling.
* [GPT4All](https://gpt4all.io/index.html), a free and open source local running GUI, supporting Windows, Linux and macOS with full GPU accel.
* [LM Studio](https://lmstudio.ai/), an easy-to-use and powerful local GUI for Windows and macOS (Silicon), with GPU acceleration. Linux available, in beta as of 27/11/2023.
* [LoLLMS Web UI](https://github.com/ParisNeo/lollms-webui), a great web UI with many interesting and unique features, including a full model library for easy model selection.
* [Faraday.dev](https://faraday.dev/), an attractive and easy to use character-based chat GUI for Windows and macOS (both Silicon and Intel), with GPU acceleration.
* [llama-cpp-python](https://github.com/abetlen/llama-cpp-python), a Python library with GPU accel, LangChain support, and OpenAI-compatible API server.
* [candle](https://github.com/huggingface/candle), a Rust ML framework with a focus on performance, including GPU support, and ease of use.
* [ctransformers](https://github.com/marella/ctransformers), a Python library with GPU accel, LangChain support, and OpenAI-compatible AI server. Note, as of time of writing (November 27th 2023), ctransformers has not been updated in a long time and does not support many recent models.
<!-- README_GGUF.md-about-gguf end -->
<!-- repositories-available start -->
## Repositories available
* [AWQ model(s) for GPU inference.](https://huggingface.co/TheBloke/Magicoder-S-DS-6.7B-AWQ)
* [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/Magicoder-S-DS-6.7B-GPTQ)
* [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/Magicoder-S-DS-6.7B-GGUF)
* [Intellligent Software Engineering (iSE's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/ise-uiuc/Magicoder-S-DS-6.7B)
<!-- repositories-available end -->
<!-- prompt-template start -->
## Prompt template: Magicoder
```
You are an exceptionally intelligent coding assistant that consistently delivers accurate and reliable responses to user instructions.
@@ Instruction
{prompt}
@@ Response
```
<!-- prompt-template end -->
<!-- compatibility_gguf start -->
## Compatibility
These quantised GGUFv2 files are compatible with llama.cpp from August 27th onwards, as of commit [d0cee0d](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221)
They are also compatible with many third party UIs and libraries - please see the list at the top of this README.
## Explanation of quantisation methods
<details>
<summary>Click to see details</summary>
The new methods available are:
* GGML_TYPE_Q2_K - "type-1" 2-bit quantization in super-blocks containing 16 blocks, each block having 16 weight. Block scales and mins are quantized with 4 bits. This ends up effectively using 2.5625 bits per weight (bpw)
* GGML_TYPE_Q3_K - "type-0" 3-bit quantization in super-blocks containing 16 blocks, each block having 16 weights. Scales are quantized with 6 bits. This end up using 3.4375 bpw.
* GGML_TYPE_Q4_K - "type-1" 4-bit quantization in super-blocks containing 8 blocks, each block having 32 weights. Scales and mins are quantized with 6 bits. This ends up using 4.5 bpw.
* GGML_TYPE_Q5_K - "type-1" 5-bit quantization. Same super-block structure as GGML_TYPE_Q4_K resulting in 5.5 bpw
* GGML_TYPE_Q6_K - "type-0" 6-bit quantization. Super-blocks with 16 blocks, each block having 16 weights. Scales are quantized with 8 bits. This ends up using 6.5625 bpw
Refer to the Provided Files table below to see what files use which methods, and how.
</details>
<!-- compatibility_gguf end -->
<!-- README_GGUF.md-provided-files start -->
## Provided files
| Name | Quant method | Bits | Size | Max RAM required | Use case |
| ---- | ---- | ---- | ---- | ---- | ----- |
| [magicoder-s-ds-6.7b.Q2_K.gguf](https://huggingface.co/TheBloke/Magicoder-S-DS-6.7B-GGUF/blob/main/magicoder-s-ds-6.7b.Q2_K.gguf) | Q2_K | 2 | 2.83 GB| 5.33 GB | smallest, significant quality loss - not recommended for most purposes |
| [magicoder-s-ds-6.7b.Q3_K_S.gguf](https://huggingface.co/TheBloke/Magicoder-S-DS-6.7B-GGUF/blob/main/magicoder-s-ds-6.7b.Q3_K_S.gguf) | Q3_K_S | 3 | 2.95 GB| 5.45 GB | very small, high quality loss |
| [magicoder-s-ds-6.7b.Q3_K_M.gguf](https://huggingface.co/TheBloke/Magicoder-S-DS-6.7B-GGUF/blob/main/magicoder-s-ds-6.7b.Q3_K_M.gguf) | Q3_K_M | 3 | 3.30 GB| 5.80 GB | very small, high quality loss |
| [magicoder-s-ds-6.7b.Q3_K_L.gguf](https://huggingface.co/TheBloke/Magicoder-S-DS-6.7B-GGUF/blob/main/magicoder-s-ds-6.7b.Q3_K_L.gguf) | Q3_K_L | 3 | 3.60 GB| 6.10 GB | small, substantial quality loss |
| [magicoder-s-ds-6.7b.Q4_0.gguf](https://huggingface.co/TheBloke/Magicoder-S-DS-6.7B-GGUF/blob/main/magicoder-s-ds-6.7b.Q4_0.gguf) | Q4_0 | 4 | 3.83 GB| 6.33 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| [magicoder-s-ds-6.7b.Q4_K_S.gguf](https://huggingface.co/TheBloke/Magicoder-S-DS-6.7B-GGUF/blob/main/magicoder-s-ds-6.7b.Q4_K_S.gguf) | Q4_K_S | 4 | 3.86 GB| 6.36 GB | small, greater quality loss |
| [magicoder-s-ds-6.7b.Q4_K_M.gguf](https://huggingface.co/TheBloke/Magicoder-S-DS-6.7B-GGUF/blob/main/magicoder-s-ds-6.7b.Q4_K_M.gguf) | Q4_K_M | 4 | 4.08 GB| 6.58 GB | medium, balanced quality - recommended |
| [magicoder-s-ds-6.7b.Q5_0.gguf](https://huggingface.co/TheBloke/Magicoder-S-DS-6.7B-GGUF/blob/main/magicoder-s-ds-6.7b.Q5_0.gguf) | Q5_0 | 5 | 4.65 GB| 7.15 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| [magicoder-s-ds-6.7b.Q5_K_S.gguf](https://huggingface.co/TheBloke/Magicoder-S-DS-6.7B-GGUF/blob/main/magicoder-s-ds-6.7b.Q5_K_S.gguf) | Q5_K_S | 5 | 4.65 GB| 7.15 GB | large, low quality loss - recommended |
| [magicoder-s-ds-6.7b.Q5_K_M.gguf](https://huggingface.co/TheBloke/Magicoder-S-DS-6.7B-GGUF/blob/main/magicoder-s-ds-6.7b.Q5_K_M.gguf) | Q5_K_M | 5 | 4.79 GB| 7.29 GB | large, very low quality loss - recommended |
| [magicoder-s-ds-6.7b.Q6_K.gguf](https://huggingface.co/TheBloke/Magicoder-S-DS-6.7B-GGUF/blob/main/magicoder-s-ds-6.7b.Q6_K.gguf) | Q6_K | 6 | 5.53 GB| 8.03 GB | very large, extremely low quality loss |
| [magicoder-s-ds-6.7b.Q8_0.gguf](https://huggingface.co/TheBloke/Magicoder-S-DS-6.7B-GGUF/blob/main/magicoder-s-ds-6.7b.Q8_0.gguf) | Q8_0 | 8 | 7.16 GB| 9.66 GB | very large, extremely low quality loss - not recommended |
**Note**: the above RAM figures assume no GPU offloading. If layers are offloaded to the GPU, this will reduce RAM usage and use VRAM instead.
<!-- README_GGUF.md-provided-files end -->
<!-- README_GGUF.md-how-to-download start -->
## How to download GGUF files
**Note for manual downloaders:** You almost never want to clone the entire repo! Multiple different quantisation formats are provided, and most users only want to pick and download a single file.
The following clients/libraries will automatically download models for you, providing a list of available models to choose from:
* LM Studio
* LoLLMS Web UI
* Faraday.dev
### In `text-generation-webui`
Under Download Model, you can enter the model repo: TheBloke/Magicoder-S-DS-6.7B-GGUF and below it, a specific filename to download, such as: magicoder-s-ds-6.7b.Q4_K_M.gguf.
Then click Download.
### On the command line, including multiple files at once
I recommend using the `huggingface-hub` Python library:
```shell
pip3 install huggingface-hub
```
Then you can download any individual model file to the current directory, at high speed, with a command like this:
```shell
huggingface-cli download TheBloke/Magicoder-S-DS-6.7B-GGUF magicoder-s-ds-6.7b.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
```
<details>
<summary>More advanced huggingface-cli download usage (click to read)</summary>
You can also download multiple files at once with a pattern:
```shell
huggingface-cli download TheBloke/Magicoder-S-DS-6.7B-GGUF --local-dir . --local-dir-use-symlinks False --include='*Q4_K*gguf'
```
For more documentation on downloading with `huggingface-cli`, please see: [HF -> Hub Python Library -> Download files -> Download from the CLI](https://huggingface.co/docs/huggingface_hub/guides/download#download-from-the-cli).
To accelerate downloads on fast connections (1Gbit/s or higher), install `hf_transfer`:
```shell
pip3 install hf_transfer
```
And set environment variable `HF_HUB_ENABLE_HF_TRANSFER` to `1`:
```shell
HF_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download TheBloke/Magicoder-S-DS-6.7B-GGUF magicoder-s-ds-6.7b.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
```
Windows Command Line users: You can set the environment variable by running `set HF_HUB_ENABLE_HF_TRANSFER=1` before the download command.
</details>
<!-- README_GGUF.md-how-to-download end -->
<!-- README_GGUF.md-how-to-run start -->
## Example `llama.cpp` command
Make sure you are using `llama.cpp` from commit [d0cee0d](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221) or later.
```shell
./main -ngl 35 -m magicoder-s-ds-6.7b.Q4_K_M.gguf --color -c 16384 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "You are an exceptionally intelligent coding assistant that consistently delivers accurate and reliable responses to user instructions.\n\n@@ Instruction\n{prompt}\n\n@@ Response"
```
Change `-ngl 32` to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.
Change `-c 16384` to the desired sequence length. For extended sequence models - eg 8K, 16K, 32K - the necessary RoPE scaling parameters are read from the GGUF file and set by llama.cpp automatically. Note that longer sequence lengths require much more resources, so you may need to reduce this value.
If you want to have a chat-style conversation, replace the `-p <PROMPT>` argument with `-i -ins`
For other parameters and how to use them, please refer to [the llama.cpp documentation](https://github.com/ggerganov/llama.cpp/blob/master/examples/main/README.md)
## How to run in `text-generation-webui`
Further instructions can be found in the text-generation-webui documentation, here: [text-generation-webui/docs/04 ‐ Model Tab.md](https://github.com/oobabooga/text-generation-webui/blob/main/docs/04%20%E2%80%90%20Model%20Tab.md#llamacpp).
## How to run from Python code
You can use GGUF models from Python using the [llama-cpp-python](https://github.com/abetlen/llama-cpp-python) or [ctransformers](https://github.com/marella/ctransformers) libraries. Note that at the time of writing (Nov 27th 2023), ctransformers has not been updated for some time and is not compatible with some recent models. Therefore I recommend you use llama-cpp-python.
### How to load this model in Python code, using llama-cpp-python
For full documentation, please see: [llama-cpp-python docs](https://abetlen.github.io/llama-cpp-python/).
#### First install the package
Run one of the following commands, according to your system:
```shell
# Base ctransformers with no GPU acceleration
pip install llama-cpp-python
# With NVidia CUDA acceleration
CMAKE_ARGS="-DLLAMA_CUBLAS=on" pip install llama-cpp-python
# Or with OpenBLAS acceleration
CMAKE_ARGS="-DLLAMA_BLAS=ON -DLLAMA_BLAS_VENDOR=OpenBLAS" pip install llama-cpp-python
# Or with CLBLast acceleration
CMAKE_ARGS="-DLLAMA_CLBLAST=on" pip install llama-cpp-python
# Or with AMD ROCm GPU acceleration (Linux only)
CMAKE_ARGS="-DLLAMA_HIPBLAS=on" pip install llama-cpp-python
# Or with Metal GPU acceleration for macOS systems only
CMAKE_ARGS="-DLLAMA_METAL=on" pip install llama-cpp-python
# In windows, to set the variables CMAKE_ARGS in PowerShell, follow this format; eg for NVidia CUDA:
$env:CMAKE_ARGS = "-DLLAMA_OPENBLAS=on"
pip install llama-cpp-python
```
#### Simple llama-cpp-python example code
```python
from llama_cpp import Llama
# Set gpu_layers to the number of layers to offload to GPU. Set to 0 if no GPU acceleration is available on your system.
llm = Llama(
model_path="./magicoder-s-ds-6.7b.Q4_K_M.gguf", # Download the model file first
n_ctx=16384, # The max sequence length to use - note that longer sequence lengths require much more resources
n_threads=8, # The number of CPU threads to use, tailor to your system and the resulting performance
n_gpu_layers=35 # The number of layers to offload to GPU, if you have GPU acceleration available
)
# Simple inference example
output = llm(
"You are an exceptionally intelligent coding assistant that consistently delivers accurate and reliable responses to user instructions.\n\n@@ Instruction\n{prompt}\n\n@@ Response", # Prompt
max_tokens=512, # Generate up to 512 tokens
stop=["</s>"], # Example stop token - not necessarily correct for this specific model! Please check before using.
echo=True # Whether to echo the prompt
)
# Chat Completion API
llm = Llama(model_path="./magicoder-s-ds-6.7b.Q4_K_M.gguf", chat_format="llama-2") # Set chat_format according to the model you are using
llm.create_chat_completion(
messages = [
{"role": "system", "content": "You are a story writing assistant."},
{
"role": "user",
"content": "Write a story about llamas."
}
]
)
```
## How to use with LangChain
Here are guides on using llama-cpp-python and ctransformers with LangChain:
* [LangChain + llama-cpp-python](https://python.langchain.com/docs/integrations/llms/llamacpp)
* [LangChain + ctransformers](https://python.langchain.com/docs/integrations/providers/ctransformers)
<!-- README_GGUF.md-how-to-run end -->
<!-- footer start -->
<!-- 200823 -->
## Discord
For further support, and discussions on these models and AI in general, join us at:
[TheBloke AI's Discord server](https://discord.gg/theblokeai)
## Thanks, and how to contribute
Thanks to the [chirper.ai](https://chirper.ai) team!
Thanks to Clay from [gpus.llm-utils.org](llm-utils)!
I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training.
If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects.
Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits.
* Patreon: https://patreon.com/TheBlokeAI
* Ko-Fi: https://ko-fi.com/TheBlokeAI
**Special thanks to**: Aemon Algiz.
**Patreon special mentions**: Michael Levine, 阿明, Trailburnt, Nikolai Manek, John Detwiler, Randy H, Will Dee, Sebastain Graf, NimbleBox.ai, Eugene Pentland, Emad Mostaque, Ai Maven, Jim Angel, Jeff Scroggin, Michael Davis, Manuel Alberto Morcote, Stephen Murray, Robert, Justin Joy, Luke @flexchar, Brandon Frisco, Elijah Stavena, S_X, Dan Guido, Undi ., Komninos Chatzipapas, Shadi, theTransient, Lone Striker, Raven Klaugh, jjj, Cap'n Zoog, Michel-Marie MAUDET (LINAGORA), Matthew Berman, David, Fen Risland, Omer Bin Jawed, Luke Pendergrass, Kalila, OG, Erik Bjäreholt, Rooh Singh, Joseph William Delisle, Dan Lewis, TL, John Villwock, AzureBlack, Brad, Pedro Madruga, Caitlyn Gatomon, K, jinyuan sun, Mano Prime, Alex, Jeffrey Morgan, Alicia Loh, Illia Dulskyi, Chadd, transmissions 11, fincy, Rainer Wilmers, ReadyPlayerEmma, knownsqashed, Mandus, biorpg, Deo Leter, Brandon Phillips, SuperWojo, Sean Connelly, Iucharbius, Jack West, Harry Royden McLaughlin, Nicholas, terasurfer, Vitor Caleffi, Duane Dunston, Johann-Peter Hartmann, David Ziegler, Olakabola, Ken Nordquist, Trenton Dambrowitz, Tom X Nguyen, Vadim, Ajan Kanaga, Leonard Tan, Clay Pascal, Alexandros Triantafyllidis, JM33133, Xule, vamX, ya boyyy, subjectnull, Talal Aujan, Alps Aficionado, wassieverse, Ari Malik, James Bentley, Woland, Spencer Kim, Michael Dempsey, Fred von Graf, Elle, zynix, William Richards, Stanislav Ovsiannikov, Edmond Seymore, Jonathan Leane, Martin Kemka, usrbinkat, Enrico Ros
Thank you to all my generous patrons and donaters!
And thank you again to a16z for their generous grant.
<!-- footer end -->
<!-- original-model-card start -->
# Original model card: Intellligent Software Engineering (iSE's Magicoder S DS 6.7B
# 🎩 Magicoder: Source Code Is All You Need
> Refer to our GitHub repo [ise-uiuc/magicoder](https://github.com/ise-uiuc/magicoder/) for an up-to-date introduction to the Magicoder family!
* 🎩**Magicoder** is a model family empowered by 🪄**OSS-Instruct**, a novel approach to enlightening LLMs with open-source code snippets for generating *low-bias* and *high-quality* instruction data for code.
* 🪄**OSS-Instruct** mitigates the *inherent bias* of the LLM-synthesized instruction data by empowering them with *a wealth of open-source references* to produce more diverse, realistic, and controllable data.
## Model Details
### Model Description
* **Developed by:**
[Yuxiang Wei](https://yuxiang.cs.illinois.edu),
[Zhe Wang](https://github.com/zhewang2001),
[Jiawei Liu](https://jiawei-site.github.io),
[Yifeng Ding](https://yifeng-ding.com),
[Lingming Zhang](https://lingming.cs.illinois.edu)
* **License:** [DeepSeek](https://github.com/deepseek-ai/DeepSeek-Coder/blob/main/LICENSE-MODEL)
* **Finetuned from model:** [deepseek-coder-6.7b-base](https://huggingface.co/deepseek-ai/deepseek-coder-6.7b-base)
### Model Sources
* **Repository:** <https://github.com/ise-uiuc/magicoder>
* **Paper:** <https://arxiv.org/abs/2312.02120>
* **Demo (powered by [Gradio](https://www.gradio.app)):**
<https://github.com/ise-uiuc/magicoder/tree/main/demo>
### Training Data
* [Magicoder-OSS-Instruct-75K](https://huggingface.co/datasets/ise-uiuc/Magicoder_oss_instruct_75k): generated through **OSS-Instruct** using `gpt-3.5-turbo-1106` and used to train both Magicoder and Magicoder-S series.
* [Magicoder-Evol-Instruct-110K](https://huggingface.co/datasets/ise-uiuc/Magicoder_evol_instruct_110k): decontaminated and redistributed from [theblackcat102/evol-codealpaca-v1](https://huggingface.co/datasets/theblackcat102/evol-codealpaca-v1), used to further finetune Magicoder series and obtain Magicoder-S models.
## Uses
### Direct Use
Magicoders are designed and best suited for **coding tasks**.
### Out-of-Scope Use
Magicoders may not work well in non-coding tasks.
## Bias, Risks, and Limitations
Magicoders may sometimes make errors, producing misleading contents, or struggle to manage tasks that are not related to coding.
### Recommendations
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model.
## How to Get Started with the Model
Use the code below to get started with the model. Make sure you installed the [transformers](https://huggingface.co/docs/transformers/index) library.
```python
from transformers import pipeline
import torch
MAGICODER_PROMPT = """You are an exceptionally intelligent coding assistant that consistently delivers accurate and reliable responses to user instructions.
@@ Instruction
{instruction}
@@ Response
"""
instruction = <Your code instruction here>
prompt = MAGICODER_PROMPT.format(instruction=instruction)
generator = pipeline(
model="ise-uiuc/Magicoder-S-DS-6.7B",
task="text-generation",
torch_dtype=torch.bfloat16,
device_map="auto",
)
result = generator(prompt, max_length=1024, num_return_sequences=1, temperature=0.0)
print(result[0]["generated_text"])
```
## Technical Details
Refer to our GitHub repo: [ise-uiuc/magicoder](https://github.com/ise-uiuc/magicoder/).
## Citation
```bibtex
@misc{magicoder,
title={Magicoder: Source Code Is All You Need},
author={Yuxiang Wei and Zhe Wang and Jiawei Liu and Yifeng Ding and Lingming Zhang},
year={2023},
eprint={2312.02120},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
```
## Acknowledgements
* [WizardCoder](https://github.com/nlpxucan/WizardLM/tree/main/WizardCoder): Evol-Instruct
* [DeepSeek-Coder](https://github.com/deepseek-ai/DeepSeek-Coder): Base model for Magicoder-DS
* [CodeLlama](https://ai.meta.com/research/publications/code-llama-open-foundation-models-for-code/): Base model for Magicoder-CL
* [StarCoder](https://arxiv.org/abs/2305.06161): Data decontamination
## Important Note
Magicoder models are trained on the synthetic data generated by OpenAI models. Please pay attention to OpenAI's [terms of use](https://openai.com/policies/terms-of-use) when using the models and the datasets. Magicoders will not compete with OpenAI's commercial products.
<!-- original-model-card end -->
|
CausalLM/8x7B-MoE-test-NOT-MIXTRAL | CausalLM | "2023-12-16T06:07:39Z" | 1,070 | 21 | transformers | [
"transformers",
"pytorch",
"mixtral",
"text-generation",
"qwen",
"en",
"zh",
"license:gpl-3.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-12-16T02:24:58Z" | ---
license: gpl-3.0
language:
- en
- zh
tags:
- qwen
---
# CausalLM / Qwen 8x7B MoE - This is not Mixtral / Mistral 7B
A Chat Model, Testing only, no performance guaranteeeee...
In short: CausalLM / Qwen 8x7B MoE in Mixtral Arch, from 8 real, explainable expert models in different domains. Trained, not a merge.
Only intended for conceptual validation, however the expert models do not seem to be working as expected. The model could output text and complete the conversation normally, but the performance of the expert model was not significant.
There are 8 completely different expert models based on Qwen-7B / CausalLM, six of which are specific domain models that have seen 50~100 billion tokens, including: a Toolformer/Agent expert model, a multilingual translation expert model, a mathematics expert model, a visual expert model, a coding and computer expert model, and an uncensored knowledge model — together forming the MoE model along with Qwen-Chat and Qwen-Base.
The initialization of the gate is based on the hidden state of the few-shot prompt input from each expert model and undergoes simple alignment training, on flan/ orca style.
For multimodal input, please use visual.bin/py, should be the same as Qwen-VL.
Prompt format: ChatML
A simple verification found that the expert model occasionally had routing errors, resulting in suboptimal results and required further fine-tuning. |
yuntaeyang/KoSOLAR-10.7B-dpo-v1.0 | yuntaeyang | "2024-01-18T07:10:23Z" | 1,070 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"ko",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-01-18T06:12:29Z" | ---
license: apache-2.0
language:
- ko
---
# Model Card for yuntaeyang/KoSOLAR-10.7B-dpo-v1.0
## Developed by : yuntaeyang(yonsei)
## Base Model : yanolja/KoSOLAR-10.7B-v0.1-deprecated
## 사용 데이터셋
- Ja-ck/Orca-DPO-Pairs-KO
- 이하 생략
## 파라미터 디테일
- 생략 |
realPCH/kosolra-wiki-QA-1epoch | realPCH | "2024-01-28T23:13:01Z" | 1,070 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"dataset:maywell/ko_wikidata_QA",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-01-22T23:30:43Z" | ---
license: mit
datasets:
- maywell/ko_wikidata_QA
---
### Developed by chPark
### Training Strategy
We fine-tuned this model based on [yanolja/KoSOLAR-10.7B-v0.1](https://huggingface.co/yanolja/KoSOLAR-10.7B-v0.1-deprecated) with [kyujinpy/KOR-gugugu-platypus-set](https://huggingface.co/datasets/kyujinpy/KOR-gugugu-platypus-set)
### Run the model
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
model_id = "realPCH/ko_solra_merge"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id)
text = "[INST] Put instruction here. [/INST]"
inputs = tokenizer(text, return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=20)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
``` |
testmod/koen-llama2-13b-avg_testver | testmod | "2024-01-31T04:42:40Z" | 1,070 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"ko",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-01-31T03:46:24Z" | ---
library_name: transformers
language:
- ko
license: apache-2.0
---
**Input** Models input text only.
**Output** Models generate text only.
**Model Architecture**
Auto-regressive language model based on the LLaMA2 transformer architecture.
**Base Model**
hyunseoki/ko-en-llama2-13b
**Training Objective**
linearly interpolated the weight of instruction finetuned the models trained in several datasets. |
Heimat24/vhs_burghausen_danielheinz_e5-qa_generation_secretary-5-3-0.8 | Heimat24 | "2024-05-22T18:33:14Z" | 1,070 | 0 | sentence-transformers | [
"sentence-transformers",
"safetensors",
"xlm-roberta",
"feature-extraction",
"sentence-similarity",
"autotrain_compatible",
"endpoints_compatible",
"text-embeddings-inference",
"region:us"
] | sentence-similarity | "2024-05-22T18:32:21Z" | ---
library_name: sentence-transformers
pipeline_tag: sentence-similarity
tags:
- sentence-transformers
- feature-extraction
- sentence-similarity
---
# {MODEL_NAME}
This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search.
<!--- Describe your model here -->
## Usage (Sentence-Transformers)
Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
```
pip install -U sentence-transformers
```
Then you can use the model like this:
```python
from sentence_transformers import SentenceTransformer
sentences = ["This is an example sentence", "Each sentence is converted"]
model = SentenceTransformer('{MODEL_NAME}')
embeddings = model.encode(sentences)
print(embeddings)
```
## Evaluation Results
<!--- Describe how your model was evaluated -->
For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name={MODEL_NAME})
## Training
The model was trained with the parameters:
**DataLoader**:
`torch.utils.data.dataloader.DataLoader` of length 24 with parameters:
```
{'batch_size': 10, 'sampler': 'torch.utils.data.sampler.SequentialSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'}
```
**Loss**:
`sentence_transformers.losses.MultipleNegativesRankingLoss.MultipleNegativesRankingLoss` with parameters:
```
{'scale': 20.0, 'similarity_fct': 'cos_sim'}
```
Parameters of the fit()-Method:
```
{
"epochs": 3,
"evaluation_steps": 50,
"evaluator": "sentence_transformers.evaluation.InformationRetrievalEvaluator.InformationRetrievalEvaluator",
"max_grad_norm": 1,
"optimizer_class": "<class 'torch.optim.adamw.AdamW'>",
"optimizer_params": {
"lr": 2e-05
},
"scheduler": "WarmupLinear",
"steps_per_epoch": null,
"warmup_steps": 7,
"weight_decay": 0.01
}
```
## Full Model Architecture
```
SentenceTransformer(
(0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: XLMRobertaModel
(1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
(2): Normalize()
)
```
## Citing & Authors
<!--- Describe where people can find more information --> |
fabiochiu/t5-small-medium-title-generation | fabiochiu | "2023-08-03T07:55:10Z" | 1,069 | 9 | transformers | [
"transformers",
"pytorch",
"tf",
"jax",
"safetensors",
"t5",
"text2text-generation",
"generated_from_keras_callback",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text2text-generation | "2022-05-05T11:06:46Z" | ---
tags:
- generated_from_keras_callback
model-index:
- name: t5-small-medium-title-generation
results: []
widget:
- text: "summarize: Many financial institutions started building conversational AI, prior to the Covid19 pandemic, as part of a digital transformation initiative. These initial solutions were high profile, highly personalized virtual assistants — like the Erica chatbot from Bank of America. As the pandemic hit, the need changed as contact centers were under increased pressures. As Cathal McGloin of ServisBOT explains in 'how it started, and how it is going,' financial institutions were looking for ways to automate solutions to help get back to 'normal' levels of customer service. This resulted in a change from the 'future of conversational AI' to a real tactical assistant that can help in customer service. Haritha Dev of Wells Fargo, saw a similar trend. Banks were originally looking to conversational AI as part of digital transformation to keep up with the times. However, with the pandemic, it has been more about customer retention and customer satisfaction. In addition, new use cases came about as a result of Covid-19 that accelerated adoption of conversational AI. As Vinita Kumar of Deloitte points out, banks were dealing with an influx of calls about new concerns, like questions around the Paycheck Protection Program (PPP) loans. This resulted in an increase in volume, without enough agents to assist customers, and tipped the scale to incorporate conversational AI. When choosing initial use cases to support, financial institutions often start with high volume, low complexity tasks. For example, password resets, checking account balances, or checking the status of a transaction, as Vinita points out. From there, the use cases can evolve as the banks get more mature in developing conversational AI, and as the customers become more engaged with the solutions. Cathal indicates another good way for banks to start is looking at use cases that are a pain point, and also do not require a lot of IT support. Some financial institutions may have a multi-year technology roadmap, which can make it harder to get a new service started. A simple chatbot for document collection in an onboarding process can result in high engagement, and a high return on investment. For example, Cathal has a banking customer that implemented a chatbot to capture a driver’s license to be used in the verification process of adding an additional user to an account — it has over 85% engagement with high satisfaction. An interesting use case Haritha discovered involved educating customers on financial matters. People feel more comfortable asking a chatbot what might be considered a 'dumb' question, as the chatbot is less judgmental. Users can be more ambiguous with their questions as well, not knowing the right words to use, as chatbot can help narrow things down."
example_title: "Banking on Bots"
---
<!-- This model card has been generated automatically according to the information Keras had access to. You should
probably proofread and complete it, then remove this comment. -->
# Model description
This model is [t5-small](https://huggingface.co/t5-small) fine-tuned on the [190k Medium Articles](https://www.kaggle.com/datasets/fabiochiusano/medium-articles) dataset for predicting article titles using the article textual content as input.
There are two versions of the model:
- [t5-small-medium-title-generation](https://huggingface.co/fabiochiu/t5-small-medium-title-generation): trained from [t5-small](https://huggingface.co/t5-small).
- [t5-base-medium-title-generation](https://huggingface.co/fabiochiu/t5-base-medium-title-generation): trained from [t5-base](https://huggingface.co/t5-base).
Visit the [title-generation space](https://huggingface.co/spaces/fabiochiu/title-generation) to try the model with different text generation parameters.
# How to use the model
```
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
import nltk
nltk.download('punkt')
tokenizer = AutoTokenizer.from_pretrained("fabiochiu/t5-small-medium-title-generation")
model = AutoModelForSeq2SeqLM.from_pretrained("fabiochiu/t5-small-medium-title-generation")
text = """
Many financial institutions started building conversational AI, prior to the Covid19
pandemic, as part of a digital transformation initiative. These initial solutions
were high profile, highly personalized virtual assistants — like the Erica chatbot
from Bank of America. As the pandemic hit, the need changed as contact centers were
under increased pressures. As Cathal McGloin of ServisBOT explains in “how it started,
and how it is going,” financial institutions were looking for ways to automate
solutions to help get back to “normal” levels of customer service. This resulted
in a change from the “future of conversational AI” to a real tactical assistant
that can help in customer service. Haritha Dev of Wells Fargo, saw a similar trend.
Banks were originally looking to conversational AI as part of digital transformation
to keep up with the times. However, with the pandemic, it has been more about
customer retention and customer satisfaction. In addition, new use cases came about
as a result of Covid-19 that accelerated adoption of conversational AI. As Vinita
Kumar of Deloitte points out, banks were dealing with an influx of calls about new
concerns, like questions around the Paycheck Protection Program (PPP) loans. This
resulted in an increase in volume, without enough agents to assist customers, and
tipped the scale to incorporate conversational AI. When choosing initial use cases
to support, financial institutions often start with high volume, low complexity
tasks. For example, password resets, checking account balances, or checking the
status of a transaction, as Vinita points out. From there, the use cases can evolve
as the banks get more mature in developing conversational AI, and as the customers
become more engaged with the solutions. Cathal indicates another good way for banks
to start is looking at use cases that are a pain point, and also do not require a
lot of IT support. Some financial institutions may have a multi-year technology
roadmap, which can make it harder to get a new service started. A simple chatbot
for document collection in an onboarding process can result in high engagement,
and a high return on investment. For example, Cathal has a banking customer that
implemented a chatbot to capture a driver’s license to be used in the verification
process of adding an additional user to an account — it has over 85% engagement
with high satisfaction. An interesting use case Haritha discovered involved
educating customers on financial matters. People feel more comfortable asking a
chatbot what might be considered a “dumb” question, as the chatbot is less judgmental.
Users can be more ambiguous with their questions as well, not knowing the right
words to use, as chatbot can help narrow things down.
"""
inputs = ["summarize: " + text]
inputs = tokenizer(inputs, max_length=max_input_length, truncation=True, return_tensors="pt")
output = model.generate(**inputs, num_beams=8, do_sample=True, min_length=10, max_length=64)
decoded_output = tokenizer.batch_decode(output, skip_special_tokens=True)[0]
predicted_title = nltk.sent_tokenize(decoded_output.strip())[0]
print(predicted_title)
# Conversational AI: The Future of Customer Service
```
## Training and evaluation data
The model has been trained on a single epoch spanning about 16000 articles, evaluating on 1000 random articles not used during training.
### Training results
The model has been evaluated on a random dataset split of 1000 articles not used during training and validation.
- Rouge-1: 27.8%
- Rouge-2: 14.9%
- Rouge-L: 26.9%
- Rouge-Lsum: 26.9%
- Average length of the generated titles: 13 tokens (about 9 English words)
### Framework versions
- Transformers 4.18.0
- TensorFlow 2.8.0
- Datasets 2.1.0
- Tokenizers 0.12.1
|
gaodrew/llama-2-7b-roman-empire-qa-27k | gaodrew | "2023-10-22T21:14:59Z" | 1,069 | 1 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"license:llama2",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-10-10T21:43:40Z" | ---
license: llama2
---
llama-2-7b base fine-tuned on a dataset of 27,000 questions and answers about the Roman Empire (Wikipedia entry)
llama-2-7b base fine-tuned on a dataset of 27,000 questions and answers about the Roman Empire (Wikipedia entry)
llama-2-7b base fine-tuned on a dataset of 27,000 questions and answers about the Roman Empire (Wikipedia entry)
|
KnutJaegersberg/Deacon-34B | KnutJaegersberg | "2023-12-03T15:07:28Z" | 1,069 | 3 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"dataset:totally-not-an-llm/EverythingLM-data-V3",
"license:other",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-11-06T20:35:08Z" | ---
license: other
license_name: yi-license
license_link: LICENSE
pipeline_tag: text-generation
datasets:
- totally-not-an-llm/EverythingLM-data-V3
---
This model has been llamafied and uses a llama tokenizer. I took it from https://huggingface.co/chargoddard/Yi-34B-Llama
It's fine tuned on EverythingLM dataset for 5 epochs with NEFTune. If you want to understand the pun of the model name, you gotta look at the 3b version of it.
License
The Yi series models are fully open for academic research and free commercial usage with permission via applications. All usage must adhere to the Model License Agreement 2.0. To apply for the official commercial license, please contact us ([email protected]).
Prompt Example:
```
### System:
You are an AI assistant. User will give you a task. Your goal is to complete the task as faithfully as you can. While performing the task think step-by-step and justify your steps.
### Instruction:
How do you fine tune a large language model?
### Response:
``` |
sayhan/gemma-7b-it-GGUF-quantized | sayhan | "2024-02-23T12:05:37Z" | 1,069 | 19 | transformers | [
"transformers",
"gguf",
"text-generation",
"en",
"base_model:google/gemma-7b-it",
"license:other",
"region:us"
] | text-generation | "2024-02-21T15:28:05Z" | ---
base_model: google/gemma-7b-it
language:
- en
pipeline_tag: text-generation
license: other
model_type: gemma
library_name: transformers
inference: false
---
## Google Gemma 7B Instruct
- **Model creator:** [Google](https://huggingface.co/google)
- **Original model:** [gemma-7b-it](https://huggingface.co/google/gemma-7b-it)
- [**Terms of use**](https://www.kaggle.com/models/google/gemma/license/consent)
<!-- description start -->
## Description
This repo contains GGUF format model files for [Google's Gemma 7B Instruct](https://huggingface.co/google/gemma-7b-it)
## Original model
- **Developed by:** [Google](https://huggingface.co/google)
### Description
Gemma is a family of lightweight, state-of-the-art open models from Google,
built from the same research and technology used to create the Gemini models.
They are text-to-text, decoder-only large language models, available in English,
with open weights, pre-trained variants, and instruction-tuned variants. Gemma
models are well-suited for a variety of text generation tasks, including
question answering, summarization, and reasoning. Their relatively small size
makes it possible to deploy them in environments with limited resources such as
a laptop, desktop or your own cloud infrastructure, democratizing access to
state of the art AI models and helping foster innovation for everyone.
## Quantizon types
| quantization method | bits | size | description | recommended |
|---------------------|------|----------|-----------------------------------------------------|-------------|
| Q3_K_S | 3 | 3.68 GB | very small, high quality loss | ❌ |
| Q3_K_L | 3 | 4.4 GB | small, substantial quality loss | ❌ |
| Q4_0 | 4 | 4.81 GB | legacy; small, very high quality loss | ❌ |
| Q4_K_M | 4 | 5.13 GB | medium, balanced quality | ✅ |
| Q5_0 | 5 | 5.88 GB | legacy; medium, balanced quality | ❌ |
| Q5_K_S | 5 | 5.88 GB | large, low quality loss | ✅ |
| Q5_K_M | 5 | 6.04 GB | large, very low quality loss | ✅ |
| Q6_K | 6 | 7.01 GB | very large, extremely low quality loss | ❌ |
| Q8_0 | 8 | 9.08 GB | very large, extremely low quality loss | ❌ |
| FP16 | 16 | 17.1 GB | enormous, negligible quality loss | ❌ |
## Usage
You can use this model with the latest builds of **LM Studio** and **llama.cpp**.
If you're new to the world of _large language models_, I recommend starting with **LM Studio**.
<!-- description end --> |
timm/efficientformerv2_s2.snap_dist_in1k | timm | "2024-02-10T23:30:33Z" | 1,068 | 2 | timm | [
"timm",
"pytorch",
"image-classification",
"dataset:imagenet-1k",
"arxiv:2212.08059",
"license:apache-2.0",
"region:us"
] | image-classification | "2023-02-03T21:11:23Z" | ---
license: apache-2.0
library_name: timm
tags:
- image-classification
- timm
datasets:
- imagenet-1k
---
# Model card for efficientformerv2_s2.snap_dist_in1k
A EfficientFormer-V2 image classification model. Pretrained with distillation on ImageNet-1k.
## Model Details
- **Model Type:** Image classification / feature backbone
- **Model Stats:**
- Params (M): 12.7
- GMACs: 1.3
- Activations (M): 11.8
- Image size: 224 x 224
- **Original:** https://github.com/snap-research/EfficientFormer
- **Papers:**
- Rethinking Vision Transformers for MobileNet Size and Speed: https://arxiv.org/abs/2212.08059
- **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('efficientformerv2_s2.snap_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(
'efficientformerv2_s2.snap_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
```
### 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(
'efficientformerv2_s2.snap_dist_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. for efficientformerv2_l:
# torch.Size([2, 40, 56, 56])
# torch.Size([2, 80, 28, 28])
# torch.Size([2, 192, 14, 14])
# torch.Size([2, 384, 7, 7])
print(o.shape)
```
## Model Comparison
|model |top1 |top5 |param_count|img_size|
|-----------------------------------|------|------|-----------|--------|
|efficientformerv2_l.snap_dist_in1k |83.628|96.54 |26.32 |224 |
|efficientformer_l7.snap_dist_in1k |83.368|96.534|82.23 |224 |
|efficientformer_l3.snap_dist_in1k |82.572|96.24 |31.41 |224 |
|efficientformerv2_s2.snap_dist_in1k|82.128|95.902|12.71 |224 |
|efficientformer_l1.snap_dist_in1k |80.496|94.984|12.29 |224 |
|efficientformerv2_s1.snap_dist_in1k|79.698|94.698|6.19 |224 |
|efficientformerv2_s0.snap_dist_in1k|76.026|92.77 |3.6 |224 |
## Citation
```bibtex
@article{li2022rethinking,
title={Rethinking Vision Transformers for MobileNet Size and Speed},
author={Li, Yanyu and Hu, Ju and Wen, Yang and Evangelidis, Georgios and Salahi, Kamyar and Wang, Yanzhi and Tulyakov, Sergey and Ren, Jian},
journal={arXiv preprint arXiv:2212.08059},
year={2022}
}
```
```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}}
}
```
|
pinkmanlove/llama-65b-hf | pinkmanlove | "2023-04-01T04:43:31Z" | 1,068 | 6 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-04-01T03:34:19Z" | ---
license: apache-2.0
---
|
timm/visformer_tiny.in1k | timm | "2023-04-26T16:51:21Z" | 1,068 | 0 | timm | [
"timm",
"pytorch",
"safetensors",
"image-classification",
"dataset:imagenet-1k",
"arxiv:2104.12533",
"license:apache-2.0",
"region:us"
] | image-classification | "2023-04-26T16:51:14Z" | ---
tags:
- image-classification
- timm
library_name: timm
license: apache-2.0
datasets:
- imagenet-1k
---
# Model card for visformer_tiny.in1k
A Visformer image classification model. Trained on ImageNet-1k by https://github.com/hzhang57 and https://github.com/developer0hye.
## Model Details
- **Model Type:** Image classification / feature backbone
- **Model Stats:**
- Params (M): 10.3
- GMACs: 1.3
- Activations (M): 5.7
- Image size: 224 x 224
- **Papers:**
- Visformer: The Vision-friendly Transformer: https://arxiv.org/abs/2104.12533
- **Dataset:** ImageNet-1k
- **Original:** https://github.com/danczs/Visformer
## 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('visformer_tiny.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(
'visformer_tiny.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, 384, 7, 7) 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).
## Citation
```bibtex
@inproceedings{chen2021visformer,
title={Visformer: The vision-friendly transformer},
author={Chen, Zhengsu and Xie, Lingxi and Niu, Jianwei and Liu, Xuefeng and Wei, Longhui and Tian, Qi},
booktitle={Proceedings of the IEEE/CVF international conference on computer vision},
pages={589--598},
year={2021}
}
```
|
ctrlbuzz/bert-addresses | ctrlbuzz | "2023-10-17T18:09:47Z" | 1,068 | 7 | transformers | [
"transformers",
"pytorch",
"bert",
"token-classification",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | token-classification | "2023-09-26T21:13:04Z" | ---
# For reference on model card metadata, see the spec: https://github.com/huggingface/hub-docs/blob/main/modelcard.md?plain=1
# Doc / guide: https://huggingface.co/docs/hub/model-cards
{}
---
# Model Card for Model ID
This model is developed to tag Names, Organisations and addresses. I have used a data combined fro Conll, ontonotes5, and a custom address dataset that was self made. Cleaned
out the tags. Detects U.S addresses.
[\"O\", \"B-ORG\", \"I-ORG\", \"B-PER\", \"I-PER\",'B-addr','I-addr']
### Model Description
- **Developed by:** ctrlbuzz
- **Model type:** Bert
- **Language(s) (NLP):** Named Entity recognition
- **Finetuned from model [optional]:** bert-base-cased
## Uses
### Direct Use
```python
from transformers import AutoTokenizer, AutoModelForTokenClassification
from transformers import pipeline
tokenizer = AutoTokenizer.from_pretrained('bert-base-cased')
model = AutoModelForTokenClassification.from_pretrained("ctrlbuzz/bert-addresses")
nlp = pipeline("ner", model=model, tokenizer=tokenizer)
example = "While Maria was representing Johnson & Associates at a conference in Spain, she mailed me a letter from her new office at 123 Elm St., Apt. 4B, Springfield, IL.",
print(nlp(example))
```
|
caisarl76/Mistral-7B-OpenOrca-Guanaco | caisarl76 | "2023-10-11T07:41:21Z" | 1,068 | 0 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"MindsAndCompany",
"llama-2",
"conversational",
"en",
"dataset:mlabonne/guanaco-llama2-1k",
"arxiv:2306.02707",
"license:llama2",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-10-06T10:39:54Z" | ---
pipeline_tag: text-generation
license: llama2
language:
- en
library_name: transformers
tags:
- MindsAndCompany
- llama-2
datasets:
- mlabonne/guanaco-llama2-1k
---
## Model Details
* **Developed by**: [Minds And Company](https://mnc.ai/)
* **Backbone Model**: [Mistral-7B-OpenOrca](Open-Orca/Mistral-7B-OpenOrca)
* **Library**: [HuggingFace Transformers](https://github.com/huggingface/transformers)
## Dataset Details
### Used Datasets
- Alpaca-style dataset
### Prompt Template
- Llama Prompt Template
## Limitations & Biases:
Llama2 and fine-tuned variants are a new technology that carries risks with use. Testing conducted to date has been in English, and has not covered, nor could it cover all scenarios. For these reasons, as with all LLMs, Llama 2 and any fine-tuned varient's potential outputs cannot be predicted in advance, and the model may in some instances produce inaccurate, biased or other objectionable responses to user prompts. Therefore, before deploying any applications of Llama 2 variants, developers should perform safety testing and tuning tailored to their specific applications of the model.
Please see the Responsible Use Guide available at https://ai.meta.com/llama/responsible-use-guide/
## License Disclaimer:
This model is bound by the license & usage restrictions of the original Llama-2 model. And comes with no warranty or gurantees of any kind.
## Contact Us
- [Minds And Company](https://mnc.ai/)
## Citiation:
Please kindly cite using the following BibTeX:
```bibtex
@software{lian2023mistralorca1
title = {MistralOrca: Mistral-7B Model Instruct-tuned on Filtered OpenOrcaV1 GPT-4 Dataset},
author = {Wing Lian and Bleys Goodson and Guan Wang and Eugene Pentland and Austin Cook and Chanvichet Vong and "Teknium"},
year = {2023},
publisher = {HuggingFace},
journal = {HuggingFace repository},
howpublished = {\url{https://huggingface.co/Open-Orca/Mistral-7B-OpenOrca},
}
@misc{mukherjee2023orca,
title={Orca: Progressive Learning from Complex Explanation Traces of GPT-4},
author={Subhabrata Mukherjee and Arindam Mitra and Ganesh Jawahar and Sahaj Agarwal and Hamid Palangi and Ahmed Awadallah},
year={2023},
eprint={2306.02707},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
```
```
@misc{Orca-best,
title = {Orca-best: A filtered version of orca gpt4 dataset.},
author = {Shahul Es},
year = {2023},
publisher = {HuggingFace},
journal = {HuggingFace repository},
howpublished = {\url{https://huggingface.co/datasets/shahules786/orca-best/},
}
```
> Readme format: [Riiid/sheep-duck-llama-2-70b-v1.1](https://huggingface.co/Riiid/sheep-duck-llama-2-70b-v1.1) |
mncai/Mistral-7B-CollectiveCognition-OpenOrca-1k | mncai | "2023-10-22T04:30:41Z" | 1,068 | 0 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"MindsAndCompany",
"en",
"dataset:CollectiveCognition/chats-data-2023-09-27",
"arxiv:2306.02707",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-10-20T08:00:29Z" | ---
pipeline_tag: text-generation
license: mit
language:
- en
library_name: transformers
tags:
- MindsAndCompany
datasets:
- CollectiveCognition/chats-data-2023-09-27
---
## Model Details
* **Developed by**: [Minds And Company](https://mnc.ai/)
* **Backbone Model**: [Mistral-7B-v0.1](mistralai/Mistral-7B-v0.1)
* **Library**: [HuggingFace Transformers](https://github.com/huggingface/transformers)
## Dataset Details
### Used Datasets
- CollectiveCognition/chats-data-2023-09-27
### Prompt Template
- Llama Prompt Template
## Limitations & Biases:
Llama2 and fine-tuned variants are a new technology that carries risks with use. Testing conducted to date has been in English, and has not covered, nor could it cover all scenarios. For these reasons, as with all LLMs, Llama 2 and any fine-tuned varient's potential outputs cannot be predicted in advance, and the model may in some instances produce inaccurate, biased or other objectionable responses to user prompts. Therefore, before deploying any applications of Llama 2 variants, developers should perform safety testing and tuning tailored to their specific applications of the model.
Please see the Responsible Use Guide available at https://ai.meta.com/llama/responsible-use-guide/
## License Disclaimer:
This model is bound by the license & usage restrictions of the original Llama-2 model. And comes with no warranty or gurantees of any kind.
## Contact Us
- [Minds And Company](https://mnc.ai/)
## Citiation:
Please kindly cite using the following BibTeX:
```bibtex
@misc{mukherjee2023orca,
title={Orca: Progressive Learning from Complex Explanation Traces of GPT-4},
author={Subhabrata Mukherjee and Arindam Mitra and Ganesh Jawahar and Sahaj Agarwal and Hamid Palangi and Ahmed Awadallah},
year={2023},
eprint={2306.02707},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
```
```
@misc{Orca-best,
title = {Orca-best: A filtered version of orca gpt4 dataset.},
author = {Shahul Es},
year = {2023},
publisher = {HuggingFace},
journal = {HuggingFace repository},
howpublished = {\url{https://huggingface.co/datasets/shahules786/orca-best/},
}
```
```
@software{touvron2023llama2,
title={Llama 2: Open Foundation and Fine-Tuned Chat Models},
author={Hugo Touvron, Louis Martin, Kevin Stone, Peter Albert, Amjad Almahairi, Yasmine Babaei, Nikolay Bashlykov, Soumya Batra, Prajjwal Bhargava,
Shruti Bhosale, Dan Bikel, Lukas Blecher, Cristian Canton Ferrer, Moya Chen, Guillem Cucurull, David Esiobu, Jude Fernandes, Jeremy Fu, Wenyin Fu, Brian Fuller,
Cynthia Gao, Vedanuj Goswami, Naman Goyal, Anthony Hartshorn, Saghar Hosseini, Rui Hou, Hakan Inan, Marcin Kardas, Viktor Kerkez Madian Khabsa, Isabel Kloumann,
Artem Korenev, Punit Singh Koura, Marie-Anne Lachaux, Thibaut Lavril, Jenya Lee, Diana Liskovich, Yinghai Lu, Yuning Mao, Xavier Martinet, Todor Mihaylov,
Pushkar Mishra, Igor Molybog, Yixin Nie, Andrew Poulton, Jeremy Reizenstein, Rashi Rungta, Kalyan Saladi, Alan Schelten, Ruan Silva, Eric Michael Smith,
Ranjan Subramanian, Xiaoqing Ellen Tan, Binh Tang, Ross Taylor, Adina Williams, Jian Xiang Kuan, Puxin Xu , Zheng Yan, Iliyan Zarov, Yuchen Zhang, Angela Fan,
Melanie Kambadur, Sharan Narang, Aurelien Rodriguez, Robert Stojnic, Sergey Edunov, Thomas Scialom},
year={2023}
}
```
> Readme format: [Riiid/sheep-duck-llama-2-70b-v1.1](https://huggingface.co/Riiid/sheep-duck-llama-2-70b-v1.1) |
Sao10K/Euryale-1.4-L2-70B | Sao10K | "2023-11-06T22:59:51Z" | 1,068 | 5 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"en",
"license:llama2",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-11-05T19:10:47Z" | ---
license: llama2
language:
- en
---
gguf quants: https://huggingface.co/Sao10K/Euryale-1.4-L2-70B-GGUF
1.3, but better? I guess.
Base Merged Model ratios adjusted.
NSFL portion of Hesperus v1 dataset trained and applied.
LimaRP merged in at a ~25% weight at the end.
Subjectively better in some aspects eg. long form rp, worse than the other, eg. chat-style rps.
overall a minor improvement in my eyes.
1.5 will include Hesperus v2 dataset in its entirety.
format: alpaca. |
TigerResearch/tigerbot-70b-chat-v4 | TigerResearch | "2024-02-18T02:02:17Z" | 1,068 | 1 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"conversational",
"zh",
"en",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-12-13T02:51:02Z" | ---
license: apache-2.0
language:
- zh
- en
---
<div style="width: 100%;">
<p align="center" width="20%">
<img src="http://x-pai.algolet.com/bot/img/logo_core.png" alt="TigerBot" width="20%", style="display: block; margin: auto;"></img>
</p>
</div>
<p align="center">
<font face="黑体" size=5"> A cutting-edge foundation for your very own LLM. </font>
</p>
<p align="center">
💻<a href="https://github.com/TigerResearch/TigerBot" target="_blank">Github</a> • 🌐 <a href="https://tigerbot.com/" target="_blank">TigerBot</a> • 🤗 <a href="https://huggingface.co/TigerResearch" target="_blank">Hugging Face</a>
</p>
# 快速开始
- 方法1，通过transformers使用
- 下载 TigerBot Repo
```shell
git clone https://github.com/TigerResearch/TigerBot.git
```
- 启动infer代码
```shell
python infer.py --model_path TigerResearch/tigerbot-70b-chat-v4
```
- 方法2:
- 下载 TigerBot Repo
```shell
git clone https://github.com/TigerResearch/TigerBot.git
```
- 安装git lfs： `git lfs install`
- 通过huggingface或modelscope平台下载权重
```shell
git clone https://huggingface.co/TigerResearch/tigerbot-70b-chat-v4
git clone https://www.modelscope.cn/TigerResearch/tigerbot-70b-chat-v4.git
```
- 启动infer代码
```shell
python infer.py --model_path tigerbot-70b-chat-v4
```
------
# Quick Start
- Method 1, use through transformers
- Clone TigerBot Repo
```shell
git clone https://github.com/TigerResearch/TigerBot.git
```
- Run infer script
```shell
python infer.py --model_path TigerResearch/tigerbot-70b-chat-v4
```
- Method 2:
- Clone TigerBot Repo
```shell
git clone https://github.com/TigerResearch/TigerBot.git
```
- install git lfs： `git lfs install`
- Download weights from huggingface or modelscope
```shell
git clone https://huggingface.co/TigerResearch/tigerbot-70b-chat-v4
git clone https://www.modelscope.cn/TigerResearch/tigerbot-70b-chat-v4.git
```
- Run infer script
```shell
python infer.py --model_path tigerbot-70b-chat-v4
``` |
susnato/phi-2 | susnato | "2024-01-21T10:17:25Z" | 1,068 | 12 | transformers | [
"transformers",
"safetensors",
"phi",
"text-generation",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-12-17T18:13:15Z" | ---
license: mit
license_name: microsoft-research-license
license_link: LICENSE
---
**DISCLAIMER**: I don't own the weights to this model, this is a property of Microsoft and taken from their official repository : [microsoft/phi-2](https://huggingface.co/microsoft/phi-2).
The sole purpose of this repository is to use this model through the `transformers` API or to load and use the model using the HuggingFace `transformers` library.
# Usage
First make sure you have the latest version of the `transformers` installed.
```
pip uninstall -y transformers && pip install git+https://github.com/huggingface/transformers
```
Then use the transformers library to load the model from the library itself
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
model = AutoModelForCausalLM.from_pretrained("susnato/phi-2")
tokenizer = AutoTokenizer.from_pretrained("susnato/phi-2")
inputs = tokenizer('''def print_prime(n):
"""
Print all primes between 1 and n
"""''', return_tensors="pt", return_attention_mask=False)
outputs = model.generate(**inputs, max_length=200)
text = tokenizer.batch_decode(outputs)[0]
print(text)
``` |
KnutJaegersberg/2-bit-LLMs | KnutJaegersberg | "2024-03-08T09:26:17Z" | 1,068 | 92 | null | [
"gguf",
"text-generation",
"license:other",
"region:us"
] | text-generation | "2024-01-24T07:05:19Z" | ---
license: other
pipeline_tag: text-generation
---
# 2-bit LLMs
This is a model collection of mostly larger LLMs quantized to 2 bit with the novel quip# inspired approach in llama.cpp
Sometimes both xs and xxs are available.
Note that for some larger models, like Qwen-72b based models, the context length might be too large for most GPUs, so you have to reduce it yourself in textgen-webui via the n_ctx setting.
Rope scaling for scaled models like longalpaca or yarn should be 8, set compress_pos_emb accordingly.
### Overview
- Senku-70b
- Nous-Hermes2-70b
- Miquliz-120b-v2.0
- Tess-72b
- WizardLM-70b
- Qwen1.5-72b-Chat
- CausalLM-72b
- Xwin-LM-70b
- Codellama-70b-Instruct
- DeepMoney-67b-chat
- Deepseek 67b Chat
- DiscoLM-120b
- BigWeave-103b
- Saily-100b
- Nous Hermes 34b
- Kafka-70b-German
- Kafka-Mixtral-German
- LongAlpaca-70B
- Mistral-Alpha-70b
- MoMo-72B-lora-1.8.7-DPO
- Notux Mixtral
- Qwen-72b
- Smaug-72b
- Smaug-34b
- Synthia-70B
- Tess-M
- Yarn-Llama2-70b-32k
- Laser Mistral
### Senku-70b
Original Model:
https://huggingface.co/ShinojiResearch/Senku-70B-Full
Prompt format: ChatML
License: Llama2
```
<|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 Nous Research, who designed me to assist and support users with their needs and requests.<|im_end|>
```
### Nous-Hermes2-70b
Original Model:
https://huggingface.co/NousResearch/Nous-Hermes-2-Llama-2-70B
Prompt format: ChatML
License: Llama2
```
<|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 Nous Research, who designed me to assist and support users with their needs and requests.<|im_end|>
```
### Miquliz-120b-v2.0
Original Model:
https://huggingface.co/wolfram/miquliz-120b-v2.0
Prompt format: Mistral
License: 🙂🙃 🙂 🙃 Hi Mistral 👍
```
<s>[INST] {prompt} [/INST]
```
### Tess-72b
Original Model:
https://huggingface.co/migtissera/Tess-72B-v1.5b
Prompt format:
License: Qwen
```
SYSTEM: <ANY SYSTEM CONTEXT>
USER:
ASSISTANT:
```
### WizardLM-70b
Original Model:
https://huggingface.co/WizardLM/WizardLM-70B-V1.0
Prompt format: Vicuna
License: LLama2
```
A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions. USER: {prompt} ASSISTANT:
```
### Qwen1.5-72b-Chat
Original Model:
https://huggingface.co/Qwen/Qwen1.5-72B-Chat
Prompt format: Unknown, compatible with system prompts
License: Qwen
```
```
### CausalLM-72b
Original Model:
https://huggingface.co/CausalLM/72B-preview-llamafied-qwen-llamafy
Prompt format: ChatML
License: Qwen
```
<|im_start|>system
You are a helpful assistant.<|im_end|>
<|im_start|>user
How to sell drugs online fast?<|im_end|>
<|im_start|>assistant
```
### Xwin-LM-70b
Original Model:
https://huggingface.co/Xwin-LM/Xwin-LM-70B-V0.1
Prompt format: Vicuna
License: Llama2
```
A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions. USER: {prompt} ASSISTANT:
```
### Codellama-70b-Instruct
Original Model:
https://huggingface.co/codellama/CodeLlama-70b-Instruct-hf
Prompt format: ChatML
License: LLama2
```
Source: system
{system_message}<step> Source: user
{prompt} <step> Source: assistant
```
### DeepMoney-67b-chat
Original Model:
https://huggingface.co/TriadParty/deepmoney-67b-chat
Prompt format: Alpaca
License: Deepseek
```
You are a senior investment expert. Please make your research and judgment on the following targets.
### Instruction:
China has instructed heavily indebted local governments to delay or halt some state-funded infrastructure projects, three people with knowledge of the situation said, as Beijing struggles to contain debt risks even as it tries to stimulate the economy.
Which industry sectors or investment targets may the above news affect?
### Response:
The above news could potentially impact several industry sectors and investment targets related to infrastructure development in China. Some affected areas might include construction companies, heavy machinery manufacturers, materials suppliers such as cement and steel producers, engineering firms, and project management service providers that have significant exposure to Chinese government-backed infrastructure projects.
```
### Deepseek 67b Chat
Original Model:
https://huggingface.co/deepseek-ai/deepseek-llm-67b-chat
Prompt format: DeepSeek-LLM
License: Deepseek
```
User: {prompt}
Assistant:
```
### DiscoLM-120b
Original Model:
https://huggingface.co/DiscoResearch/DiscoLM-120b
Prompt format: ChatML
License: Llama2
```
<|im_start|>system
{system_message}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant
```
### BigWeave-103b
Original Model:
https://huggingface.co/llmixer/BigWeave-v16-103b
Prompt format: Mistral, Vicuna and Alpaca.
License: Llama2
```
Below is an instruction that describes a task. Write a response that appropriately completes the request.
### Instruction:
{prompt}
### Response:
```
### Saily-100b
Original Model:
https://huggingface.co/deepnight-research/saily_100b
Prompt format: Alpaca.
License: Llama2
```
Below is an instruction that describes a task. Write a response that appropriately completes the request.
### Instruction:
{prompt}
### Response:
```
### Nous Hermes 34b
Original Model:
https://huggingface.co/NousResearch/Nous-Hermes-2-Yi-34B
Prompt format: ChatML
License: Yi
```
<|im_start|>system
{system_message}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant
```
### Kafka-70b-German
Original Model:
https://huggingface.co/seedboxai/KafkaLM-70B-German-V0.1
Prompt format: ChatML
License: Llama2
```
<|system|>
Du bist ein freundlicher und hilfsbereiter KI-Assistent. Du beantwortest Fragen faktenorientiert und präzise, ohne dabei relevante Fakten auszulassen.</s>
<|user|>
Welche Möglichkeiten der energetischen Sanierung habe ich neben Solar und Energiespeicher?</s>
<|assistant|>
```
### Kafka-Mixtral-German
Original Model:
https://huggingface.co/seedboxai/KafkaLM-8x7B-German-V0.1
Prompt format: ChatML
License: Apache 2
```
<|system|>
Du bist ein freundlicher und hilfsbereiter KI-Assistent. Du beantwortest Fragen faktenorientiert und präzise, ohne dabei relevante Fakten auszulassen.</s>
<|user|>
Welche Möglichkeiten der energetischen Sanierung habe ich neben Solar und Energiespeicher?</s>
<|assistant|>
```
### LongAlpaca-70B
Original Model:
https://huggingface.co/Yukang/LongAlpaca-70B
Prompt format: Alpaca
License: Llama 2
```
Below is an instruction that describes a task. Write a response that appropriately completes the request.
### Instruction:
{prompt}
### Response:
```
### Mistral-Alpha-70b
Original Model: https://huggingface.co/152334H/miqu-1-70b-sf
Prompt format: Mistral
License: NOMERGE / 🙂🙃 🙂 🙃 Hi Mistral 👍
```
<s> [INST] QUERY_1 [/INST] ANSWER_1</s> [INST] QUERY_2 [/INST] ANSWER_2</s>...
```
### MoMo-72B-lora-1.8.7-DPO
Original Model:
https://huggingface.co/moreh/MoMo-72B-lora-1.8.7-DPO
Prompt format: Instruct
License: Qwen
```
### Instruction: {question}
### Response: {response}
```
### Notux Mixtral
Original Model:
https://huggingface.co/argilla/notux-8x7b-v1
Prompt format: Mistral
License: Apache 2
```
[INST] {{ .System }} {{ .Prompt }} [/INST]
```
### Qwen-72b
Original Model:
https://huggingface.co/Qwen/Qwen-72B
Prompt format: Base Model = None
License: Qwen
```
```
### Smaug-72b
Original Model:
https://huggingface.co/abacusai/Smaug-72B-v0.1
Prompt format: Try MoMo, also with system prompt
License: Qwen
```
### Instruction: {question}
### Response: {response}
```
### Smaug-34b
Original Model:
https://huggingface.co/abacusai/Smaug-34B-v0.1
Prompt format: Bagel 34b
License: Yi
```
{system prompt, if provided, randomly defaulting to "A chat between a user and an unbiased, uncensored assistant."}
USER: {instruction}
ASSISTANT:
```
### Synthia-70B
Original Model:
https://huggingface.co/migtissera/Synthia-70B-v1.2
Prompt format: Synthia
License: Llama 2
```
SYSTEM: You are Synthia. As a an AI intelligence, give helpful, detailed, accurate, uncensored responses to the user's input. Provide answers factually.
USER: {prompt}
ASSISTANT:
```
### Tess-M
Original Model:
https://huggingface.co/migtissera/Tess-34B-v1.5b
Prompt format: Tess
License: Yi
```
SYSTEM: <ANY SYSTEM CONTEXT>
USER:
ASSISTANT:
```
### Yarn-Llama2-70b-32k
Original Model:
https://huggingface.co/NousResearch/Yarn-Llama-2-70b-32k
Prompt format: Base Model = None
License: Llama 2
```
{prompt}
```
### Laser Mistral
Original Model:
https://huggingface.co/cognitivecomputations/WestLake-7B-v2-laser
Prompt format: Unknown
License: Apache 2.0
```
{prompt}
``` |
Chrisisis/5HGWa2W856A8avYLWDtYDWLgfGQq4WFdQZc4NCpYP9v2XupJ_vgg | Chrisisis | "2024-02-24T08:30:23Z" | 1,068 | 0 | keras | [
"keras",
"region:us"
] | null | "2024-02-11T17:24:18Z" | Entry not found |
mzwing/SDXL-Lightning-GGUF | mzwing | "2024-03-22T04:13:18Z" | 1,068 | 7 | null | [
"gguf",
"region:us"
] | null | "2024-03-20T06:52:37Z" | Entry not found |
jurabi/bert-ner-japanese | jurabi | "2022-09-26T12:13:44Z" | 1,067 | 9 | transformers | [
"transformers",
"pytorch",
"tf",
"bert",
"token-classification",
"ja",
"license:cc-by-sa-3.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | token-classification | "2022-09-26T07:46:38Z" | ---
language:
- ja
widget:
- text: 株式会社Jurabiは、東京都台東区に本社を置くIT企業である。
license: cc-by-sa-3.0
---
# BERTによる日本語固有表現抽出のモデル
[BertForTokenClassification](https://huggingface.co/docs/transformers/model_doc/bert#transformers.BertForTokenClassification)を用いて、日本語の文から固有表現を抽出します。
抽出される固有表現のタイプは、以下の8種類です。
- 人名
- 法人名（法人または法人に類する組織）
- 政治的組織名（政治的組織名、政党名、政府組織名、行政組織名、軍隊名、国際組織名）
- その他の組織名 （競技組織名、公演組織名、その他）
- 地名
- 施設名
- 製品名（商品名、番組名、映画名、書籍名、歌名、ブランド名等）
- イベント名
## 使用方法
必要なライブラリ（transformers、unidic_lite、fugashi）をpipなどでインストールして、下記のコードを実行するだけです。
```python
from transformers import BertJapaneseTokenizer, BertForTokenClassification
from transformers import pipeline
model = BertForTokenClassification.from_pretrained("jurabi/bert-ner-japanese")
tokenizer = BertJapaneseTokenizer.from_pretrained("jurabi/bert-ner-japanese")
ner_pipeline = pipeline('ner', model=model, tokenizer=tokenizer)
ner_pipeline("株式会社Jurabiは、東京都台東区に本社を置くIT企業である。")
```
## 事前学習モデル
東北大学乾研究室が公開している日本語BERTモデル（[cl-tohoku/bert-base-japanese-v2](https://huggingface.co/cl-tohoku/bert-base-japanese-v2)）
## 学習データ
ストックマーク株式会社が公開しているWikipediaを用いた日本語の固有表現抽出データセット（[stockmarkteam/ner-wikipedia-dataset](https://github.com/stockmarkteam/ner-wikipedia-dataset)）
## ソースコード
ファインチューニングに使用したプログラムは、[jurabiinc/bert-ner-japanese](https://github.com/jurabiinc/bert-ner-japanese)で公開しています。
## ライセンス
[Creative Commons Attribution-ShareAlike 3.0](https://creativecommons.org/licenses/by-sa/3.0/) |
juierror/text-to-sql-with-table-schema | juierror | "2024-04-25T06:19:41Z" | 1,067 | 66 | transformers | [
"transformers",
"pytorch",
"safetensors",
"t5",
"text2text-generation",
"en",
"dataset:wikisql",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text2text-generation | "2022-11-30T11:11:15Z" | ---
language: en
datasets:
- wikisql
widget:
- text: "question: get people name with age equal 25 table: id, name, age"
---
There are an upgraded version that support multiple tables and support "<" sign using Flan-T5 as a based model [here](https://huggingface.co/juierror/flan-t5-text2sql-with-schema-v2).
# How to use
```python
from typing import List
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
tokenizer = AutoTokenizer.from_pretrained("juierror/text-to-sql-with-table-schema")
model = AutoModelForSeq2SeqLM.from_pretrained("juierror/text-to-sql-with-table-schema")
def prepare_input(question: str, table: List[str]):
table_prefix = "table:"
question_prefix = "question:"
join_table = ",".join(table)
inputs = f"{question_prefix} {question} {table_prefix} {join_table}"
input_ids = tokenizer(inputs, max_length=700, return_tensors="pt").input_ids
return input_ids
def inference(question: str, table: List[str]) -> str:
input_data = prepare_input(question=question, table=table)
input_data = input_data.to(model.device)
outputs = model.generate(inputs=input_data, num_beams=10, top_k=10, max_length=700)
result = tokenizer.decode(token_ids=outputs[0], skip_special_tokens=True)
return result
print(inference(question="get people name with age equal 25", table=["id", "name", "age"]))
``` |
MBZUAI/LaMini-T5-61M | MBZUAI | "2023-04-28T12:07:00Z" | 1,067 | 13 | transformers | [
"transformers",
"pytorch",
"t5",
"text2text-generation",
"generated_from_trainer",
"instruction fine-tuning",
"en",
"arxiv:2304.14402",
"license:cc-by-nc-4.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text2text-generation | "2023-04-11T08:50:47Z" | ---
license: cc-by-nc-4.0
tags:
- generated_from_trainer
- instruction fine-tuning
model-index:
- name: flan-t5-small-distil-v2
results: []
language:
- en
pipeline_tag: text2text-generation
widget:
- text: >-
how can I become more healthy?
example_title: example
---
<!-- 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. -->
<p align="center" width="100%">
<a><img src="https://raw.githubusercontent.com/mbzuai-nlp/lamini-lm/main/images/lamini.png" alt="Title" style="width: 100%; min-width: 300px; display: block; margin: auto;"></a>
</p>
# LaMini-T5-61M
[]()
This model is one of our LaMini-LM series in paper "[LaMini-LM: A Diverse Herd of Distilled Models from Large-Scale Instructions](https://github.com/mbzuai-nlp/lamini-lm)". This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on [LaMini-instruction dataset](https://huggingface.co/datasets/MBZUAI/LaMini-instruction) that contains 2.58M samples for instruction fine-tuning. For more information about our dataset, please refer to our [project repository](https://github.com/mbzuai-nlp/lamini-lm/).
You can view other models of LaMini-LM series as follows. Models with ✩ are those with the best overall performance given their size/architecture, hence we recommend using them. More details can be seen in our paper.
<table>
<thead>
<tr>
<th>Base model</th>
<th colspan="4">LaMini-LM series (#parameters)</th>
</tr>
</thead>
<tbody>
<tr>
<td>T5</td>
<td><a href="https://huggingface.co/MBZUAI/lamini-t5-61m" target="_blank" rel="noopener noreferrer">LaMini-T5-61M</a></td>
<td><a href="https://huggingface.co/MBZUAI/lamini-t5-223m" target="_blank" rel="noopener noreferrer">LaMini-T5-223M</a></td>
<td><a href="https://huggingface.co/MBZUAI/lamini-t5-738m" target="_blank" rel="noopener noreferrer">LaMini-T5-738M</a></td>
<td></td>
</tr>
<tr>
<td>Flan-T5</td>
<td><a href="https://huggingface.co/MBZUAI/lamini-flan-t5-77m" target="_blank" rel="noopener noreferrer">LaMini-Flan-T5-77M</a>✩</td>
<td><a href="https://huggingface.co/MBZUAI/lamini-flan-t5-248m" target="_blank" rel="noopener noreferrer">LaMini-Flan-T5-248M</a>✩</td>
<td><a href="https://huggingface.co/MBZUAI/lamini-flan-t5-783m" target="_blank" rel="noopener noreferrer">LaMini-Flan-T5-783M</a>✩</td>
<td></td>
</tr>
<tr>
<td>Cerebras-GPT</td>
<td><a href="https://huggingface.co/MBZUAI/lamini-cerebras-111m" target="_blank" rel="noopener noreferrer">LaMini-Cerebras-111M</a></td>
<td><a href="https://huggingface.co/MBZUAI/lamini-cerebras-256m" target="_blank" rel="noopener noreferrer">LaMini-Cerebras-256M</a></td>
<td><a href="https://huggingface.co/MBZUAI/lamini-cerebras-590m" target="_blank" rel="noopener noreferrer">LaMini-Cerebras-590M</a></td>
<td><a href="https://huggingface.co/MBZUAI/lamini-cerebras-1.3b" target="_blank" rel="noopener noreferrer">LaMini-Cerebras-1.3B</a></td>
</tr>
<tr>
<td>GPT-2</td>
<td><a href="https://huggingface.co/MBZUAI/lamini-gpt-124m" target="_blank" rel="noopener noreferrer">LaMini-GPT-124M</a>✩</td>
<td><a href="https://huggingface.co/MBZUAI/lamini-gpt-774m" target="_blank" rel="noopener noreferrer">LaMini-GPT-774M</a>✩</td>
<td><a href="https://huggingface.co/MBZUAI/lamini-gpt-1.5b" target="_blank" rel="noopener noreferrer">LaMini-GPT-1.5B</a>✩</td>
<td></td>
</tr>
<tr>
<td>GPT-Neo</td>
<td><a href="https://huggingface.co/MBZUAI/lamini-neo-125m" target="_blank" rel="noopener noreferrer">LaMini-Neo-125M</a></td>
<td><a href="https://huggingface.co/MBZUAI/lamini-neo-1.3b" target="_blank" rel="noopener noreferrer">LaMini-Neo-1.3B</a></td>
<td></td>
<td></td>
</tr>
<tr>
<td>GPT-J</td>
<td colspan="4">coming soon</td>
</tr>
<tr>
<td>LLaMA</td>
<td colspan="4">coming soon</td>
</tr>
</tbody>
</table>
## Use
### Intended use
We recommend using the model to response to human instructions written in natural language.
We now show you how to load and use our model using HuggingFace `pipeline()`.
```python
# pip install -q transformers
from transformers import pipeline
checkpoint = "{model_name}"
model = pipeline('text2text-generation', model = checkpoint)
input_prompt = 'Please let me know your thoughts on the given place and why you think it deserves to be visited: \n"Barcelona, Spain"'
generated_text = model(input_prompt, max_length=512, do_sample=True)[0]['generated_text']
print("Response", generated_text)
```
## Training Procedure
<p align="center" width="100%">
<a><img src="https://raw.githubusercontent.com/mbzuai-nlp/lamini-lm/main/images/lamini-pipeline.drawio.png" alt="Title" style="width: 100%; min-width: 250px; display: block; margin: auto;"></a>
</p>
We initialize with [t5-small](https://huggingface.co/t5-small) and fine-tune it on our [LaMini-instruction dataset](https://huggingface.co/datasets/MBZUAI/LaMini-instruction). Its total number of parameters is 61M.
### Training Hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0005
- train_batch_size: 128
- eval_batch_size: 64
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 512
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
## Evaluation
We conducted two sets of evaluations: automatic evaluation on downstream NLP tasks and human evaluation on user-oriented instructions. For more detail, please refer to our [paper]().
## Limitations
More information needed
# Citation
```bibtex
@article{lamini-lm,
author = {Minghao Wu and
Abdul Waheed and
Chiyu Zhang and
Muhammad Abdul-Mageed and
Alham Fikri Aji
},
title = {LaMini-LM: A Diverse Herd of Distilled Models from Large-Scale Instructions},
journal = {CoRR},
volume = {abs/2304.14402},
year = {2023},
url = {https://arxiv.org/abs/2304.14402},
eprinttype = {arXiv},
eprint = {2304.14402}
}
``` |
rombodawg/LosslessMegaCoder-Falcon-40b-mini | rombodawg | "2023-09-04T20:51:15Z" | 1,067 | 2 | transformers | [
"transformers",
"safetensors",
"falcon",
"text-generation",
"dataset:rombodawg/LosslessMegaCodeTrainingV2_1m_Evol_Uncensored",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-08-17T02:18:51Z" | ---
license: apache-2.0
datasets:
- rombodawg/LosslessMegaCodeTrainingV2_1m_Evol_Uncensored
---
___________________________
- Please note this model was not trained on the rombodawg/LosslessMegaCodeTrainingV3_MINI dataset, despite the name similarity. You can find the training data at the bottom of the model card labeled (megacode2-min100)
___________________________
This is one of the first models trained on the LosslessMegaCodeTrainingV2_1m_Evol_Uncensored dataset. The version of the dataset used for this model was filtered by removed any data with less than 100 tokens but plans for much more refined filtering are in the works
- This model was made as a colaboration between me and andreaskoepf who is an affiliate of Open Assistant.
Prompt template:
- chatml format is used: "<|im_start|>system\n{system message}<|im_end|>\n<|im_start|>user\n{user prompt}<|im_end|>\n<|im_start|>assistant\n{Assistant answer}<|im_end|>\n"
multi-line:
```
<|im_start|>system
{system message}<|im_end|>
<|im_start|>user
{user prompt}<|im_end|>
<|im_start|>assistant
{Assistant answer}<|im_end|>
```
Gpt4all template:
- System prompt
```
<|im_start|>system
"Below is an instruction that describes a task. Write a response that appropriately completes the request."
```
- Prompt template
```
<|im_end|>
<|im_start|>user
"%1"<|im_end|>
<|im_start|>assistant
```
Oobagooba Text-Generation-Webui Template
- user:
```
<|im_start|>user
{User string}<|im_end|>
```
- bot:
```
<|im_start|>assistant
{Bot string}<|im_end|>
```
- turn_template:
```
<|user|>\n<|user-message|>\n\n<|bot|>\n<|bot-message|>\n\n
```
- context:
```
<|im_start|>system
Below is an instruction that describes a task. Write a response that appropriately completes the request.<|im_end|>
```
Current quantizations available:
- (COMING SOON)
The link for the full dataset is bellow:
- https://huggingface.co/datasets/rombodawg/LosslessMegaCodeTrainingV2_1m_Evol_Uncensored
Link for the filtered dataset used to make this model are bellow:
- https://huggingface.co/datasets/andreaskoepf/megacode2-min100
The original posting for this model was uploaded at the link bellow.
- https://huggingface.co/andreaskoepf/falcon-40b-megacode2
|
salesforce/blipdiffusion | salesforce | "2023-09-21T15:55:12Z" | 1,067 | 6 | diffusers | [
"diffusers",
"safetensors",
"en",
"arxiv:2305.14720",
"license:apache-2.0",
"diffusers:BlipDiffusionPipeline",
"region:us"
] | null | "2023-09-21T15:55:12Z" | ---
license: apache-2.0
language:
- en
library_name: diffusers
---
# BLIP-Diffusion: Pre-trained Subject Representation for Controllable Text-to-Image Generation and Editing
<!-- Provide a quick summary of what the model is/does. -->
Model card for BLIP-Diffusion, a text to image Diffusion model which enables zero-shot subject-driven generation and control-guided zero-shot generation.
The abstract from the paper is:
*Subject-driven text-to-image generation models create novel renditions of an input subject based on text prompts. Existing models suffer from lengthy fine-tuning and difficulties preserving the subject fidelity. To overcome these limitations, we introduce BLIP-Diffusion, a new subject-driven image generation model that supports multimodal control which consumes inputs of subject images and text prompts. Unlike other subject-driven generation models, BLIP-Diffusion introduces a new multimodal encoder which is pre-trained to provide subject representation. We first pre-train the multimodal encoder following BLIP-2 to produce visual representation aligned with the text. Then we design a subject representation learning task which enables a diffusion model to leverage such visual representation and generates new subject renditions. Compared with previous methods such as DreamBooth, our model enables zero-shot subject-driven generation, and efficient fine-tuning for customized subject with up to 20x speedup. We also demonstrate that BLIP-Diffusion can be flexibly combined with existing techniques such as ControlNet and prompt-to-prompt to enable novel subject-driven generation and editing applications.*
The model is created by Dongxu Li, Junnan Li, Steven C.H. Hoi.
### Model Sources
<!-- Provide the basic links for the model. -->
- **Original Repository:** https://github.com/salesforce/LAVIS/tree/main
- **Project Page:** https://dxli94.github.io/BLIP-Diffusion-website/
## Uses
### Zero-Shot Subject Driven Generation
```python
from diffusers.pipelines import BlipDiffusionPipeline
from diffusers.utils import load_image
import torch
blip_diffusion_pipe = BlipDiffusionPipeline.from_pretrained(
"Salesforce/blipdiffusion", torch_dtype=torch.float16
).to("cuda")
cond_subject = "dog"
tgt_subject = "dog"
text_prompt_input = "swimming underwater"
cond_image = load_image(
"https://huggingface.co/datasets/ayushtues/blipdiffusion_images/resolve/main/dog.jpg"
)
iter_seed = 88888
guidance_scale = 7.5
num_inference_steps = 25
negative_prompt = "over-exposure, under-exposure, saturated, duplicate, out of frame, lowres, cropped, worst quality, low quality, jpeg artifacts, morbid, mutilated, out of frame, ugly, bad anatomy, bad proportions, deformed, blurry, duplicate"
output = blip_diffusion_pipe(
text_prompt_input,
cond_image,
cond_subject,
tgt_subject,
guidance_scale=guidance_scale,
num_inference_steps=num_inference_steps,
neg_prompt=negative_prompt,
height=512,
width=512,
).images
output[0].save("image.png")
```
Input Image : <img src="https://huggingface.co/datasets/ayushtues/blipdiffusion_images/resolve/main/dog.jpg" style="width:500px;"/>
Generatred Image : <img src="https://huggingface.co/datasets/ayushtues/blipdiffusion_images/resolve/main/dog_underwater.png" style="width:500px;"/>
### Controlled subject-driven generation
```python
from diffusers.pipelines import BlipDiffusionControlNetPipeline
from diffusers.utils import load_image
from controlnet_aux import CannyDetector
blip_diffusion_pipe = BlipDiffusionControlNetPipeline.from_pretrained(
"Salesforce/blipdiffusion-controlnet", torch_dtype=torch.float16
).to("cuda")
style_subject = "flower" # subject that defines the style
tgt_subject = "teapot" # subject to generate.
text_prompt = "on a marble table"
cldm_cond_image = load_image(
"https://huggingface.co/datasets/ayushtues/blipdiffusion_images/resolve/main/kettle.jpg"
).resize((512, 512))
canny = CannyDetector()
cldm_cond_image = canny(cldm_cond_image, 30, 70, output_type="pil")
style_image = load_image(
"https://huggingface.co/datasets/ayushtues/blipdiffusion_images/resolve/main/flower.jpg"
)
guidance_scale = 7.5
num_inference_steps = 50
negative_prompt = "over-exposure, under-exposure, saturated, duplicate, out of frame, lowres, cropped, worst quality, low quality, jpeg artifacts, morbid, mutilated, out of frame, ugly, bad anatomy, bad proportions, deformed, blurry, duplicate"
output = blip_diffusion_pipe(
text_prompt,
style_image,
cldm_cond_image,
style_subject,
tgt_subject,
guidance_scale=guidance_scale,
num_inference_steps=num_inference_steps,
neg_prompt=negative_prompt,
height=512,
width=512,
).images
output[0].save("image.png")
```
Input Style Image : <img src="https://huggingface.co/datasets/ayushtues/blipdiffusion_images/resolve/main/flower.jpg" style="width:500px;"/>
Canny Edge Input : <img src="https://huggingface.co/datasets/ayushtues/blipdiffusion_images/resolve/main/kettle.jpg" style="width:500px;"/>
Generated Image : <img src="https://huggingface.co/datasets/ayushtues/blipdiffusion_images/resolve/main/canny_generated.png" style="width:500px;"/>
### Controlled subject-driven generation Scribble
```python
from diffusers.pipelines import BlipDiffusionControlNetPipeline
from diffusers.utils import load_image
from controlnet_aux import HEDdetector
blip_diffusion_pipe = BlipDiffusionControlNetPipeline.from_pretrained(
"Salesforce/blipdiffusion-controlnet"
)
controlnet = ControlNetModel.from_pretrained("lllyasviel/sd-controlnet-scribble")
blip_diffusion_pipe.controlnet = controlnet
blip_diffusion_pipe.to("cuda")
style_subject = "flower" # subject that defines the style
tgt_subject = "bag" # subject to generate.
text_prompt = "on a table"
cldm_cond_image = load_image(
"https://huggingface.co/lllyasviel/sd-controlnet-scribble/resolve/main/images/bag.png"
).resize((512, 512))
hed = HEDdetector.from_pretrained("lllyasviel/Annotators")
cldm_cond_image = hed(cldm_cond_image)
style_image = load_image(
"https://huggingface.co/datasets/ayushtues/blipdiffusion_images/resolve/main/flower.jpg"
)
guidance_scale = 7.5
num_inference_steps = 50
negative_prompt = "over-exposure, under-exposure, saturated, duplicate, out of frame, lowres, cropped, worst quality, low quality, jpeg artifacts, morbid, mutilated, out of frame, ugly, bad anatomy, bad proportions, deformed, blurry, duplicate"
output = blip_diffusion_pipe(
text_prompt,
style_image,
cldm_cond_image,
style_subject,
tgt_subject,
guidance_scale=guidance_scale,
num_inference_steps=num_inference_steps,
neg_prompt=negative_prompt,
height=512,
width=512,
).images
output[0].save("image.png")
```
Input Style Image : <img src="https://huggingface.co/datasets/ayushtues/blipdiffusion_images/resolve/main/flower.jpg" style="width:500px;"/>
Scribble Input : <img src="https://huggingface.co/datasets/ayushtues/blipdiffusion_images/resolve/main/scribble.png" style="width:500px;"/>
Generated Image : <img src="https://huggingface.co/datasets/ayushtues/blipdiffusion_images/resolve/main/scribble_output.png" style="width:500px;"/>
## Model Architecture
Blip-Diffusion learns a **pre-trained subject representation**. uch representation aligns with text embeddings and in the meantime also encodes the subject appearance. This allows efficient fine-tuning of the model for high-fidelity subject-driven applications, such as text-to-image generation, editing and style transfer.
To this end, they design a two-stage pre-training strategy to learn generic subject representation. In the first pre-training stage, they perform multimodal representation learning, which enforces BLIP-2 to produce text-aligned visual features based on the input image. In the second pre-training stage, they design a subject representation learning task, called prompted context generation, where the diffusion model learns to generate novel subject renditions based on the input visual features.
To achieve this, they curate pairs of input-target images with the same subject appearing in different contexts. Specifically, they synthesize input images by composing the subject with a random background. During pre-training, they feed the synthetic input image and the subject class label through BLIP-2 to obtain the multimodal embeddings as subject representation. The subject representation is then combined with a text prompt to guide the generation of the target image.
The architecture is also compatible to integrate with established techniques built on top of the diffusion model, such as ControlNet.
They attach the U-Net of the pre-trained ControlNet to that of BLIP-Diffusion via residuals. In this way, the model takes into account the input structure condition, such as edge maps and depth maps, in addition to the subject cues. Since the model inherits the architecture of the original latent diffusion model, they observe satisfying generations using off-the-shelf integration with pre-trained ControlNet without further training.
<img src="https://huggingface.co/datasets/ayushtues/blipdiffusion_images/resolve/main/arch_controlnet.png" style="width:50%;"/>
## Citation
**BibTeX:**
If you find this repository useful in your research, please cite:
```
@misc{li2023blipdiffusion,
title={BLIP-Diffusion: Pre-trained Subject Representation for Controllable Text-to-Image Generation and Editing},
author={Dongxu Li and Junnan Li and Steven C. H. Hoi},
year={2023},
eprint={2305.14720},
archivePrefix={arXiv},
primaryClass={cs.CV}
}
```
|
PAIXAI/Astrid-Mistral-7B | PAIXAI | "2023-11-06T06:54:03Z" | 1,067 | 0 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"gpt",
"llm",
"large language model",
"PAIX.Cloud",
"conversational",
"en",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-10-09T23:51:42Z" | ---
language:
- en
library_name: transformers
tags:
- gpt
- llm
- large language model
- PAIX.Cloud
inference: true
thumbnail: >-
https://static.wixstatic.com/media/bdee4e_8aa5cefc86024bc88f7e20e3e19d9ff3~mv2.png/v1/fill/w_192%2Ch_192%2Clg_1%2Cusm_0.66_1.00_0.01/bdee4e_8aa5cefc86024bc88f7e20e3e19d9ff3~mv2.png
license: apache-2.0
---
# Model Card
## Summary
- Base model: [mistralai/Mistral-7B-Instruct-v0.1](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1)
This model, Astrid-7B-Assistant is a Mistral-7B base model for causal language modeling, designed to generate human-like text.
It's part of our mission to make AI technology accessible to everyone, focusing on personalization, data privacy, and transparent AI governance.
Trained in English, it's a versatile tool for a variety of applications.
This model is one of the many models available on our platform, and we currently have a 1B and 7B open-source model.
This model was trained by [PAIX.Cloud](https://www.paix.cloud/).
- Wait list: [Wait List](https://www.paix.cloud/join-waitlist)
## Usage
To use the model with the `transformers` library on a machine with GPUs, first make sure you have the `transformers` library installed.
```bash
pip install transformers==4.34.0
```
Also make sure you are providing your huggingface token to the pipeline if the model is lying in a private repo.
- Either leave `token=True` in the `pipeline` and login to hugginface_hub by running
```python
import huggingface_hub
huggingface_hub.login(<ACCES_TOKEN>)
```
- Or directly pass your <ACCES_TOKEN> to `token` in the `pipeline`
```python
from transformers import pipeline
generate_text = pipeline(
model="PAIXAI/Astrid-Mistral-7B",
torch_dtype="auto",
trust_remote_code=True,
use_fast=True,
device_map={"": "cuda:0"},
token=True,
)
res = generate_text(
"Why is drinking water so healthy?",
min_new_tokens=2,
max_new_tokens=256,
do_sample=False,
num_beams=1,
temperature=float(0.3),
repetition_penalty=float(1.2),
renormalize_logits=True
)
print(res[0]["generated_text"])
```
You can print a sample prompt after the preprocessing step to see how it is feed to the tokenizer:
```python
print(generate_text.preprocess("Why is drinking water so healthy?")["prompt_text"])
```
```bash
<|prompt|>Why is drinking water so healthy?<|im_end|><|answer|>
```
Alternatively, you can download [h2oai_pipeline.py](h2oai_pipeline.py), store it alongside your notebook, and construct the pipeline yourself from the loaded model and tokenizer. If the model and the tokenizer are fully supported in the `transformers` package, this will allow you to set `trust_remote_code=False`.
```python
from h2oai_pipeline import H2OTextGenerationPipeline
from transformers import AutoModelForCausalLM, AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained(
"PAIXAI/Astrid-Mistral-7B",
use_fast=True,
padding_side="left",
trust_remote_code=True,
)
model = AutoModelForCausalLM.from_pretrained(
"PAIXAI/Astrid-Mistral-7B",
torch_dtype="auto",
device_map={"": "cuda:0"},
trust_remote_code=True,
)
generate_text = H2OTextGenerationPipeline(model=model, tokenizer=tokenizer)
res = generate_text(
"Why is drinking water so healthy?",
min_new_tokens=2,
max_new_tokens=256,
do_sample=False,
num_beams=1,
temperature=float(0.3),
repetition_penalty=float(1.2),
renormalize_logits=True
)
print(res[0]["generated_text"])
```
You may also construct the pipeline from the loaded model and tokenizer yourself and consider the preprocessing steps:
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
model_name = "PAIXAI/Astrid-Mistral-7B" # either local folder or huggingface model name
# Important: The prompt needs to be in the same format the model was trained with.
# You can find an example prompt in the experiment logs.
prompt = "<|prompt|>How are you?<|im_end|><|answer|>"
tokenizer = AutoTokenizer.from_pretrained(
model_name,
use_fast=True,
trust_remote_code=True,
)
model = AutoModelForCausalLM.from_pretrained(
model_name,
torch_dtype="auto",
device_map={"": "cuda:0"},
trust_remote_code=True,
)
model.cuda().eval()
inputs = tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to("cuda")
# generate configuration can be modified to your needs
tokens = model.generate(
input_ids=inputs["input_ids"],
attention_mask=inputs["attention_mask"],
min_new_tokens=2,
max_new_tokens=256,
do_sample=False,
num_beams=1,
temperature=float(0.3),
repetition_penalty=float(1.2),
renormalize_logits=True
)[0]
tokens = tokens[inputs["input_ids"].shape[1]:]
answer = tokenizer.decode(tokens, skip_special_tokens=True)
print(answer)
```
## Quantization and sharding
You can load the models using quantization by specifying ```load_in_8bit=True``` or ```load_in_4bit=True```. Also, sharding on multiple GPUs is possible by setting ```device_map=auto```.
## Model Architecture
```
MistralForCausalLM(
(model): MistralModel(
(embed_tokens): Embedding(32002, 4096, padding_idx=0)
(layers): ModuleList(
(0-31): 32 x MistralDecoderLayer(
(self_attn): MistralAttention(
(q_proj): Linear(in_features=4096, out_features=4096, bias=False)
(k_proj): Linear(in_features=4096, out_features=1024, bias=False)
(v_proj): Linear(in_features=4096, out_features=1024, bias=False)
(o_proj): Linear(in_features=4096, out_features=4096, bias=False)
(rotary_emb): MistralRotaryEmbedding()
)
(mlp): MistralMLP(
(gate_proj): Linear(in_features=4096, out_features=14336, bias=False)
(up_proj): Linear(in_features=4096, out_features=14336, bias=False)
(down_proj): Linear(in_features=14336, out_features=4096, bias=False)
(act_fn): SiLUActivation()
)
(input_layernorm): MistralRMSNorm()
(post_attention_layernorm): MistralRMSNorm()
)
)
(norm): MistralRMSNorm()
)
(lm_head): Linear(in_features=4096, out_features=32002, bias=False)
)
```
## Model Configuration
This model was trained using H2O LLM Studio and with the configuration in [cfg.yaml](cfg.yaml). Visit [H2O LLM Studio](https://github.com/h2oai/h2o-llmstudio) to learn how to train your own large language models.
## Disclaimer
Please read this disclaimer carefully before using the large language model provided in this repository. Your use of the model signifies your agreement to the following terms and conditions.
- Biases and Offensiveness: The large language model is trained on a diverse range of internet text data, which may contain biased, racist, offensive, or otherwise inappropriate content. By using this model, you acknowledge and accept that the generated content may sometimes exhibit biases or produce content that is offensive or inappropriate. The developers of this repository do not endorse, support, or promote any such content or viewpoints.
- Limitations: The large language model is an AI-based tool and not a human. It may produce incorrect, nonsensical, or irrelevant responses. It is the user's responsibility to critically evaluate the generated content and use it at their discretion.
- Use at Your Own Risk: Users of this large language model must assume full responsibility for any consequences that may arise from their use of the tool. The developers and contributors of this repository shall not be held liable for any damages, losses, or harm resulting from the use or misuse of the provided model.
- Ethical Considerations: Users are encouraged to use the large language model responsibly and ethically. By using this model, you agree not to use it for purposes that promote hate speech, discrimination, harassment, or any form of illegal or harmful activities.
- Reporting Issues: If you encounter any biased, offensive, or otherwise inappropriate content generated by the large language model, please report it to the repository maintainers through the provided channels. Your feedback will help improve the model and mitigate potential issues.
- Changes to this Disclaimer: The developers of this repository reserve the right to modify or update this disclaimer at any time without prior notice. It is the user's responsibility to periodically review the disclaimer to stay informed about any changes.
By using the large language model provided in this repository, you agree to accept and comply with the terms and conditions outlined in this disclaimer. If you do not agree with any part of this disclaimer, you should refrain from using the model and any content generated by it. |
unicamp-dl/InRanker-base | unicamp-dl | "2024-01-17T11:19:03Z" | 1,067 | 4 | transformers | [
"transformers",
"pytorch",
"t5",
"text2text-generation",
"arxiv:2401.06910",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text2text-generation | "2023-12-13T18:45:00Z" | # InRanker-small (220M parameters)
InRanker is a version of monoT5 distilled from [monoT5-3B](https://huggingface.co/castorini/monot5-3b-msmarco-10k) with increased effectiveness on out-of-domain scenarios.
Our key insight were to use language models and rerankers to generate as much as possible
synthetic "in-domain" training data, i.e., data that closely resembles
the data that will be seen at retrieval time. The pipeline used for training consists of
two distillation phases that do not require additional user queries
or manual annotations: (1) training on existing supervised soft
teacher labels, and (2) training on teacher soft labels for synthetic
queries generated using a large language model.
The paper with further details can be found [here](https://arxiv.org/abs/2401.06910). The code and library are available at
https://github.com/unicamp-dl/InRanker
## Usage
The library was tested using python 3.10 and is installed with:
```bash
pip install inranker
```
The code for inference is:
```python
from inranker import T5Ranker
model = T5Ranker(model_name_or_path="unicamp-dl/InRanker-base")
docs = [
"The capital of France is Paris",
"Learn deep learning with InRanker and transformers"
]
scores = model.get_scores(
query="What is the best way to learn deep learning?",
docs=docs
)
# Scores are sorted in descending order (most relevant to least)
# scores -> [0, 1]
sorted_scores = sorted(zip(scores, docs), key=lambda x: x[0], reverse=True)
```
## How to Cite
```
@misc{laitz2024inranker,
title={InRanker: Distilled Rankers for Zero-shot Information Retrieval},
author={Thiago Laitz and Konstantinos Papakostas and Roberto Lotufo and Rodrigo Nogueira},
year={2024},
eprint={2401.06910},
archivePrefix={arXiv},
primaryClass={cs.IR}
}
``` |
pszemraj/griffin-1024-llama3t-8layer-simplewiki-silu | pszemraj | "2024-04-27T20:39:45Z" | 1,067 | 0 | transformers | [
"transformers",
"safetensors",
"recurrent_gemma",
"text-generation",
"generated_from_trainer",
"en",
"dataset:pszemraj/simple_wikipedia_LM",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-generation | "2024-04-26T08:23:35Z" | ---
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: griffin-1024-llama3t-8layer-simple_wikipedia_LM-vN
results: []
license: apache-2.0
datasets:
- pszemraj/simple_wikipedia_LM
language:
- en
---
<!-- 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. -->
# griffin-1024-llama3t-8layer-simple_wikipedia_LM-vN
pretraining experiment on the pszemraj/simple_wikipedia_LM dataset.
It achieves the following results on the evaluation set:
- Loss: 4.3584
- Accuracy: 0.3789
## 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: 0.0003
- train_batch_size: 4
- eval_batch_size: 4
- seed: 80085
- gradient_accumulation_steps: 32
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.99) and epsilon=1e-07
- lr_scheduler_type: constant_with_warmup
- lr_scheduler_warmup_ratio: 0.05
- num_epochs: 2.0
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:------:|:----:|:---------------:|:--------:|
| 13.6044 | 0.2495 | 100 | 12.5441 | 0.0079 |
| 8.9524 | 0.4989 | 200 | 8.4254 | 0.0473 |
| 7.1721 | 0.7484 | 300 | 6.6199 | 0.0389 |
| 6.2087 | 0.9978 | 400 | 5.7198 | 0.2251 |
| 5.4917 | 1.2473 | 500 | 4.9480 | 0.3268 |
| 4.9408 | 1.4967 | 600 | 4.6730 | 0.3567 |
| 4.8347 | 1.7462 | 700 | 4.4984 | 0.3707 |
| 4.7023 | 1.9956 | 800 | 4.3584 | 0.3789 |
### Framework versions
- Transformers 4.40.1
- Pytorch 2.3.0+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1 |
TheBloke/OpenAssistant-Llama2-13B-Orca-8K-3319-GGUF | TheBloke | "2023-09-27T12:47:57Z" | 1,066 | 8 | transformers | [
"transformers",
"gguf",
"llama",
"sft",
"text-generation",
"en",
"dataset:ehartford/dolphin",
"dataset:shahules786/orca-chat",
"dataset:togethercomputer/RedPajama-Data-1T",
"dataset:atom-in-the-universe/fanfics-10k-50k",
"arxiv:2306.02707",
"base_model:OpenAssistant/llama2-13b-orca-8k-3319",
"license:other",
"text-generation-inference",
"region:us"
] | text-generation | "2023-09-05T20:16:37Z" | ---
language:
- en
license: other
tags:
- sft
datasets:
- ehartford/dolphin
- shahules786/orca-chat
- togethercomputer/RedPajama-Data-1T
- atom-in-the-universe/fanfics-10k-50k
model_name: Llama2 13B Orca 8K 3319
base_model: OpenAssistant/llama2-13b-orca-8k-3319
inference: false
model_creator: OpenAssistant
model_type: llama
pipeline_tag: text-generation
prompt_template: '<|system|>{system_message}</s><|prompter|>{prompt}</s><|assistant|>
'
quantized_by: TheBloke
widget:
- text: <|system|>You are an AI assistant. You will be given a task. You must generate
a detailed and long answer.</s><|prompter|>What is a meme, and what's the history
behind this word?</s><|assistant|>
- text: <|system|>You are an AI assistant that helps people find information.</s><|prompter|>What's
the Earth total population</s><|assistant|>
- text: <|system|>You are an AI assistant that follows instruction extremely well.
Help as much as you can.</s><|prompter|>Write a story about future of AI development</s><|assistant|>
---
<!-- header start -->
<!-- 200823 -->
<div style="width: auto; margin-left: auto; margin-right: auto">
<img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
</div>
<div style="display: flex; justify-content: space-between; width: 100%;">
<div style="display: flex; flex-direction: column; align-items: flex-start;">
<p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://discord.gg/theblokeai">Chat & support: TheBloke's Discord server</a></p>
</div>
<div style="display: flex; flex-direction: column; align-items: flex-end;">
<p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p>
</div>
</div>
<div style="text-align:center; margin-top: 0em; margin-bottom: 0em"><p style="margin-top: 0.25em; margin-bottom: 0em;">TheBloke's LLM work is generously supported by a grant from <a href="https://a16z.com">andreessen horowitz (a16z)</a></p></div>
<hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
<!-- header end -->
# Llama2 13B Orca 8K 3319 - GGUF
- Model creator: [OpenAssistant](https://huggingface.co/OpenAssistant)
- Original model: [Llama2 13B Orca 8K 3319](https://huggingface.co/OpenAssistant/llama2-13b-orca-8k-3319)
<!-- description start -->
## Description
This repo contains GGUF format model files for [OpenAssistant's Llama2 13B Orca 8K 3319](https://huggingface.co/OpenAssistant/llama2-13b-orca-8k-3319).
<!-- description end -->
<!-- README_GGUF.md-about-gguf start -->
### About GGUF
GGUF is a new format introduced by the llama.cpp team on August 21st 2023. It is a replacement for GGML, which is no longer supported by llama.cpp. GGUF offers numerous advantages over GGML, such as better tokenisation, and support for special tokens. It is also supports metadata, and is designed to be extensible.
Here is an incomplate list of clients and libraries that are known to support GGUF:
* [llama.cpp](https://github.com/ggerganov/llama.cpp). The source project for GGUF. Offers a CLI and a server option.
* [text-generation-webui](https://github.com/oobabooga/text-generation-webui), the most widely used web UI, with many features and powerful extensions. Supports GPU acceleration.
* [KoboldCpp](https://github.com/LostRuins/koboldcpp), a fully featured web UI, with GPU accel across all platforms and GPU architectures. Especially good for story telling.
* [LM Studio](https://lmstudio.ai/), an easy-to-use and powerful local GUI for Windows and macOS (Silicon), with GPU acceleration.
* [LoLLMS Web UI](https://github.com/ParisNeo/lollms-webui), a great web UI with many interesting and unique features, including a full model library for easy model selection.
* [Faraday.dev](https://faraday.dev/), an attractive and easy to use character-based chat GUI for Windows and macOS (both Silicon and Intel), with GPU acceleration.
* [ctransformers](https://github.com/marella/ctransformers), a Python library with GPU accel, LangChain support, and OpenAI-compatible AI server.
* [llama-cpp-python](https://github.com/abetlen/llama-cpp-python), a Python library with GPU accel, LangChain support, and OpenAI-compatible API server.
* [candle](https://github.com/huggingface/candle), a Rust ML framework with a focus on performance, including GPU support, and ease of use.
<!-- README_GGUF.md-about-gguf end -->
<!-- repositories-available start -->
## Repositories available
* [AWQ model(s) for GPU inference.](https://huggingface.co/TheBloke/OpenAssistant-Llama2-13B-Orca-8K-3319-AWQ)
* [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/OpenAssistant-Llama2-13B-Orca-8K-3319-GPTQ)
* [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/OpenAssistant-Llama2-13B-Orca-8K-3319-GGUF)
* [OpenAssistant's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/OpenAssistant/llama2-13b-orca-8k-3319)
<!-- repositories-available end -->
<!-- prompt-template start -->
## Prompt template: OpenAssistant-System
```
<|system|>{system_message}</s><|prompter|>{prompt}</s><|assistant|>
```
<!-- prompt-template end -->
<!-- licensing start -->
## Licensing
The creator of the source model has listed its license as `other`, and this quantization has therefore used that same license.
As this model is based on Llama 2, it is also subject to the Meta Llama 2 license terms, and the license files for that are additionally included. It should therefore be considered as being claimed to be licensed under both licenses. I contacted Hugging Face for clarification on dual licensing but they do not yet have an official position. Should this change, or should Meta provide any feedback on this situation, I will update this section accordingly.
In the meantime, any questions regarding licensing, and in particular how these two licenses might interact, should be directed to the original model repository: [OpenAssistant's Llama2 13B Orca 8K 3319](https://huggingface.co/OpenAssistant/llama2-13b-orca-8k-3319).
<!-- licensing end -->
<!-- compatibility_gguf start -->
## Compatibility
These quantised GGUFv2 files are compatible with llama.cpp from August 27th onwards, as of commit [d0cee0d36d5be95a0d9088b674dbb27354107221](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221)
They are also compatible with many third party UIs and libraries - please see the list at the top of this README.
## Explanation of quantisation methods
<details>
<summary>Click to see details</summary>
The new methods available are:
* GGML_TYPE_Q2_K - "type-1" 2-bit quantization in super-blocks containing 16 blocks, each block having 16 weight. Block scales and mins are quantized with 4 bits. This ends up effectively using 2.5625 bits per weight (bpw)
* GGML_TYPE_Q3_K - "type-0" 3-bit quantization in super-blocks containing 16 blocks, each block having 16 weights. Scales are quantized with 6 bits. This end up using 3.4375 bpw.
* GGML_TYPE_Q4_K - "type-1" 4-bit quantization in super-blocks containing 8 blocks, each block having 32 weights. Scales and mins are quantized with 6 bits. This ends up using 4.5 bpw.
* GGML_TYPE_Q5_K - "type-1" 5-bit quantization. Same super-block structure as GGML_TYPE_Q4_K resulting in 5.5 bpw
* GGML_TYPE_Q6_K - "type-0" 6-bit quantization. Super-blocks with 16 blocks, each block having 16 weights. Scales are quantized with 8 bits. This ends up using 6.5625 bpw
Refer to the Provided Files table below to see what files use which methods, and how.
</details>
<!-- compatibility_gguf end -->
<!-- README_GGUF.md-provided-files start -->
## Provided files
| Name | Quant method | Bits | Size | Max RAM required | Use case |
| ---- | ---- | ---- | ---- | ---- | ----- |
| [openassistant-llama2-13b-orca-8k-3319.Q2_K.gguf](https://huggingface.co/TheBloke/OpenAssistant-Llama2-13B-Orca-8K-3319-GGUF/blob/main/openassistant-llama2-13b-orca-8k-3319.Q2_K.gguf) | Q2_K | 2 | 5.43 GB| 7.93 GB | smallest, significant quality loss - not recommended for most purposes |
| [openassistant-llama2-13b-orca-8k-3319.Q3_K_S.gguf](https://huggingface.co/TheBloke/OpenAssistant-Llama2-13B-Orca-8K-3319-GGUF/blob/main/openassistant-llama2-13b-orca-8k-3319.Q3_K_S.gguf) | Q3_K_S | 3 | 5.66 GB| 8.16 GB | very small, high quality loss |
| [openassistant-llama2-13b-orca-8k-3319.Q3_K_M.gguf](https://huggingface.co/TheBloke/OpenAssistant-Llama2-13B-Orca-8K-3319-GGUF/blob/main/openassistant-llama2-13b-orca-8k-3319.Q3_K_M.gguf) | Q3_K_M | 3 | 6.34 GB| 8.84 GB | very small, high quality loss |
| [openassistant-llama2-13b-orca-8k-3319.Q3_K_L.gguf](https://huggingface.co/TheBloke/OpenAssistant-Llama2-13B-Orca-8K-3319-GGUF/blob/main/openassistant-llama2-13b-orca-8k-3319.Q3_K_L.gguf) | Q3_K_L | 3 | 6.93 GB| 9.43 GB | small, substantial quality loss |
| [openassistant-llama2-13b-orca-8k-3319.Q4_0.gguf](https://huggingface.co/TheBloke/OpenAssistant-Llama2-13B-Orca-8K-3319-GGUF/blob/main/openassistant-llama2-13b-orca-8k-3319.Q4_0.gguf) | Q4_0 | 4 | 7.37 GB| 9.87 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| [openassistant-llama2-13b-orca-8k-3319.Q4_K_S.gguf](https://huggingface.co/TheBloke/OpenAssistant-Llama2-13B-Orca-8K-3319-GGUF/blob/main/openassistant-llama2-13b-orca-8k-3319.Q4_K_S.gguf) | Q4_K_S | 4 | 7.41 GB| 9.91 GB | small, greater quality loss |
| [openassistant-llama2-13b-orca-8k-3319.Q4_K_M.gguf](https://huggingface.co/TheBloke/OpenAssistant-Llama2-13B-Orca-8K-3319-GGUF/blob/main/openassistant-llama2-13b-orca-8k-3319.Q4_K_M.gguf) | Q4_K_M | 4 | 7.87 GB| 10.37 GB | medium, balanced quality - recommended |
| [openassistant-llama2-13b-orca-8k-3319.Q5_0.gguf](https://huggingface.co/TheBloke/OpenAssistant-Llama2-13B-Orca-8K-3319-GGUF/blob/main/openassistant-llama2-13b-orca-8k-3319.Q5_0.gguf) | Q5_0 | 5 | 8.97 GB| 11.47 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| [openassistant-llama2-13b-orca-8k-3319.Q5_K_S.gguf](https://huggingface.co/TheBloke/OpenAssistant-Llama2-13B-Orca-8K-3319-GGUF/blob/main/openassistant-llama2-13b-orca-8k-3319.Q5_K_S.gguf) | Q5_K_S | 5 | 8.97 GB| 11.47 GB | large, low quality loss - recommended |
| [openassistant-llama2-13b-orca-8k-3319.Q5_K_M.gguf](https://huggingface.co/TheBloke/OpenAssistant-Llama2-13B-Orca-8K-3319-GGUF/blob/main/openassistant-llama2-13b-orca-8k-3319.Q5_K_M.gguf) | Q5_K_M | 5 | 9.23 GB| 11.73 GB | large, very low quality loss - recommended |
| [openassistant-llama2-13b-orca-8k-3319.Q6_K.gguf](https://huggingface.co/TheBloke/OpenAssistant-Llama2-13B-Orca-8K-3319-GGUF/blob/main/openassistant-llama2-13b-orca-8k-3319.Q6_K.gguf) | Q6_K | 6 | 10.68 GB| 13.18 GB | very large, extremely low quality loss |
| [openassistant-llama2-13b-orca-8k-3319.Q8_0.gguf](https://huggingface.co/TheBloke/OpenAssistant-Llama2-13B-Orca-8K-3319-GGUF/blob/main/openassistant-llama2-13b-orca-8k-3319.Q8_0.gguf) | Q8_0 | 8 | 13.83 GB| 16.33 GB | very large, extremely low quality loss - not recommended |
**Note**: the above RAM figures assume no GPU offloading. If layers are offloaded to the GPU, this will reduce RAM usage and use VRAM instead.
<!-- README_GGUF.md-provided-files end -->
<!-- README_GGUF.md-how-to-download start -->
## How to download GGUF files
**Note for manual downloaders:** You almost never want to clone the entire repo! Multiple different quantisation formats are provided, and most users only want to pick and download a single file.
The following clients/libraries will automatically download models for you, providing a list of available models to choose from:
- LM Studio
- LoLLMS Web UI
- Faraday.dev
### In `text-generation-webui`
Under Download Model, you can enter the model repo: TheBloke/OpenAssistant-Llama2-13B-Orca-8K-3319-GGUF and below it, a specific filename to download, such as: openassistant-llama2-13b-orca-8k-3319.q4_K_M.gguf.
Then click Download.
### On the command line, including multiple files at once
I recommend using the `huggingface-hub` Python library:
```shell
pip3 install huggingface-hub>=0.17.1
```
Then you can download any individual model file to the current directory, at high speed, with a command like this:
```shell
huggingface-cli download TheBloke/OpenAssistant-Llama2-13B-Orca-8K-3319-GGUF openassistant-llama2-13b-orca-8k-3319.q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
```
<details>
<summary>More advanced huggingface-cli download usage</summary>
You can also download multiple files at once with a pattern:
```shell
huggingface-cli download TheBloke/OpenAssistant-Llama2-13B-Orca-8K-3319-GGUF --local-dir . --local-dir-use-symlinks False --include='*Q4_K*gguf'
```
For more documentation on downloading with `huggingface-cli`, please see: [HF -> Hub Python Library -> Download files -> Download from the CLI](https://huggingface.co/docs/huggingface_hub/guides/download#download-from-the-cli).
To accelerate downloads on fast connections (1Gbit/s or higher), install `hf_transfer`:
```shell
pip3 install hf_transfer
```
And set environment variable `HF_HUB_ENABLE_HF_TRANSFER` to `1`:
```shell
HUGGINGFACE_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download TheBloke/OpenAssistant-Llama2-13B-Orca-8K-3319-GGUF openassistant-llama2-13b-orca-8k-3319.q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
```
Windows CLI users: Use `set HUGGINGFACE_HUB_ENABLE_HF_TRANSFER=1` before running the download command.
</details>
<!-- README_GGUF.md-how-to-download end -->
<!-- README_GGUF.md-how-to-run start -->
## Example `llama.cpp` command
Make sure you are using `llama.cpp` from commit [d0cee0d36d5be95a0d9088b674dbb27354107221](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221) or later.
```shell
./main -ngl 32 -m openassistant-llama2-13b-orca-8k-3319.q4_K_M.gguf --color -c 4096 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "<|system|>{system_message}</s><|prompter|>{prompt}</s><|assistant|>"
```
Change `-ngl 32` to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.
Change `-c 4096` to the desired sequence length. For extended sequence models - eg 8K, 16K, 32K - the necessary RoPE scaling parameters are read from the GGUF file and set by llama.cpp automatically.
If you want to have a chat-style conversation, replace the `-p <PROMPT>` argument with `-i -ins`
For other parameters and how to use them, please refer to [the llama.cpp documentation](https://github.com/ggerganov/llama.cpp/blob/master/examples/main/README.md)
## How to run in `text-generation-webui`
Further instructions here: [text-generation-webui/docs/llama.cpp.md](https://github.com/oobabooga/text-generation-webui/blob/main/docs/llama.cpp.md).
## How to run from Python code
You can use GGUF models from Python using the [llama-cpp-python](https://github.com/abetlen/llama-cpp-python) or [ctransformers](https://github.com/marella/ctransformers) libraries.
### How to load this model from Python using ctransformers
#### First install the package
```bash
# Base ctransformers with no GPU acceleration
pip install ctransformers>=0.2.24
# Or with CUDA GPU acceleration
pip install ctransformers[cuda]>=0.2.24
# Or with ROCm GPU acceleration
CT_HIPBLAS=1 pip install ctransformers>=0.2.24 --no-binary ctransformers
# Or with Metal GPU acceleration for macOS systems
CT_METAL=1 pip install ctransformers>=0.2.24 --no-binary ctransformers
```
#### Simple example code to load one of these GGUF models
```python
from ctransformers import AutoModelForCausalLM
# Set gpu_layers to the number of layers to offload to GPU. Set to 0 if no GPU acceleration is available on your system.
llm = AutoModelForCausalLM.from_pretrained("TheBloke/OpenAssistant-Llama2-13B-Orca-8K-3319-GGUF", model_file="openassistant-llama2-13b-orca-8k-3319.q4_K_M.gguf", model_type="llama", gpu_layers=50)
print(llm("AI is going to"))
```
## How to use with LangChain
Here's guides on using llama-cpp-python or ctransformers with LangChain:
* [LangChain + llama-cpp-python](https://python.langchain.com/docs/integrations/llms/llamacpp)
* [LangChain + ctransformers](https://python.langchain.com/docs/integrations/providers/ctransformers)
<!-- README_GGUF.md-how-to-run end -->
<!-- footer start -->
<!-- 200823 -->
## Discord
For further support, and discussions on these models and AI in general, join us at:
[TheBloke AI's Discord server](https://discord.gg/theblokeai)
## Thanks, and how to contribute
Thanks to the [chirper.ai](https://chirper.ai) team!
Thanks to Clay from [gpus.llm-utils.org](llm-utils)!
I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training.
If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects.
Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits.
* Patreon: https://patreon.com/TheBlokeAI
* Ko-Fi: https://ko-fi.com/TheBlokeAI
**Special thanks to**: Aemon Algiz.
**Patreon special mentions**: Alicia Loh, Stephen Murray, K, Ajan Kanaga, RoA, Magnesian, Deo Leter, Olakabola, Eugene Pentland, zynix, Deep Realms, Raymond Fosdick, Elijah Stavena, Iucharbius, Erik Bjäreholt, Luis Javier Navarrete Lozano, Nicholas, theTransient, John Detwiler, alfie_i, knownsqashed, Mano Prime, Willem Michiel, Enrico Ros, LangChain4j, OG, Michael Dempsey, Pierre Kircher, Pedro Madruga, James Bentley, Thomas Belote, Luke @flexchar, Leonard Tan, Johann-Peter Hartmann, Illia Dulskyi, Fen Risland, Chadd, S_X, Jeff Scroggin, Ken Nordquist, Sean Connelly, Artur Olbinski, Swaroop Kallakuri, Jack West, Ai Maven, David Ziegler, Russ Johnson, transmissions 11, John Villwock, Alps Aficionado, Clay Pascal, Viktor Bowallius, Subspace Studios, Rainer Wilmers, Trenton Dambrowitz, vamX, Michael Levine, 준교 김, Brandon Frisco, Kalila, Trailburnt, Randy H, Talal Aujan, Nathan Dryer, Vadim, 阿明, ReadyPlayerEmma, Tiffany J. Kim, George Stoitzev, Spencer Kim, Jerry Meng, Gabriel Tamborski, Cory Kujawski, Jeffrey Morgan, Spiking Neurons AB, Edmond Seymore, Alexandros Triantafyllidis, Lone Striker, Cap'n Zoog, Nikolai Manek, danny, ya boyyy, Derek Yates, usrbinkat, Mandus, TL, Nathan LeClaire, subjectnull, Imad Khwaja, webtim, Raven Klaugh, Asp the Wyvern, Gabriel Puliatti, Caitlyn Gatomon, Joseph William Delisle, Jonathan Leane, Luke Pendergrass, SuperWojo, Sebastain Graf, Will Dee, Fred von Graf, Andrey, Dan Guido, Daniel P. Andersen, Nitin Borwankar, Elle, Vitor Caleffi, biorpg, jjj, NimbleBox.ai, Pieter, Matthew Berman, terasurfer, Michael Davis, Alex, Stanislav Ovsiannikov
Thank you to all my generous patrons and donaters!
And thank you again to a16z for their generous grant.
<!-- footer end -->
<!-- original-model-card start -->
# Original model card: OpenAssistant's Llama2 13B Orca 8K 3319
# llama2-13b-orca-8k-3319
## Model Description
This model is a fine-tuning of Meta's Llama2 13B model with 8K context size on a long-conversation variant of the Dolphin dataset ([orca-chat](https://huggingface.co/datasets/shahules786/orca-chat)).
Note: **At least Huggingface Transformers [4.31.0](https://pypi.org/project/transformers/4.31.0/) is required to load this model!**
## Usage
```python
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained("OpenAssistant/llama2-13b-orca-8k-3319", use_fast=False)
model = AutoModelForCausalLM.from_pretrained("OpenAssistant/llama2-13b-orca-8k-3319", torch_dtype=torch.float16, low_cpu_mem_usage=True, device_map="auto")
system_message = "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."
user_prompt = "Write me a poem please"
prompt = f"""<|system|>{system_message}</s><|prompter|>{user_prompt}</s><|assistant|>"""
inputs = tokenizer(prompt, return_tensors="pt").to("cuda")
output = model.generate(**inputs, do_sample=True, top_p=0.95, top_k=0, max_new_tokens=256)
print(tokenizer.decode(output[0], skip_special_tokens=True))
```
## Model Details
- base model: [meta-llama/Llama-2-13b](https://huggingface.co/meta-llama/Llama-2-13b)
- License: [Llama 2 Community License Agreement](https://ai.meta.com/resources/models-and-libraries/llama-downloads/)
- sampling report: [2023-07-25_OpenAssistant_llama2-13b-orca-8k-3319_sampling_llama2_prompt.json](https://open-assistant.github.io/oasst-model-eval/?f=https%3A%2F%2Fraw.githubusercontent.com%2FOpen-Assistant%2Foasst-model-eval%2Fmain%2Fsampling_reports%2Foasst-pretrained%2F2023-07-25_OpenAssistant_llama2-13b-orca-8k-3319_sampling_llama2_prompt.json)
- wandb: [public-sft/runs/2jfazjt9](https://wandb.ai/open-assistant/public-sft/runs/2jfazjt9)
- checkpoint: 3319 steps
- datatpye: fp16
- sponsored by: [Redmond.ai](https://redmond.ai/)
## Long context (RoPE Scaling)
This model was fine-tuned with a context size of 8192 tokens using linear scaling of RoPE embeddings. This feature was recently
added to [Huggingface transformers](https://github.com/huggingface/transformers/). Before loading this model please make sure
HF transformers >=4.31.0 is installed (`pip install transformers>=4.31.0`).
## Conversation Template
For the initial response use (e.g. the [llama2 default system prompt](https://github.com/facebookresearch/llama/blob/6c7fe276574e78057f917549435a2554000a876d/llama/generation.py#L46) works well):
```
<|system|>system message</s><|prompter|>user prompt</s><|assistant|>
```
For multi-turn conversations use:
```
<|system|>system message</s><|prompter|>Q1</s><|assistant|>A1</s><|prompter|>Q2</s><|assistant|>
```
The model was trained with the following 15 system messages used to generate the training examples (see [ORCA paper](https://arxiv.org/abs/2306.02707)):
1. You are an AI assistant. Provide a detailed answer so user don’t need to search outside to understand the answer.
2. You are an AI assistant. You will be given a task. You must generate a detailed and long answer.
3. You are a helpful assistant, who always provide explanation. Think like you are answering to a five year old.
4. You are an AI assistant that follows instruction extremely well. Help as much as you can.
5. You are an AI assistant that helps people find information. Provide a detailed answer so user don’t need to search outside to understand the answer.
6. You are an AI assistant. User will you give you a task. Your goal is to complete the task as faithfully as you can. While performing the task think step-by-step and justify your steps.
7. You should describe the task and explain your answer. While answering a multiple choice question, first output the correct answer(s). Then explain why other answers are wrong. Think like you are answering to a five year old.
8. Explain how you used the definition to come up with the answer.
9. You are an AI assistant. You should describe the task and explain your answer. While answering a multiple choice question, first output the correct answer(s). Then explain why other answers are wrong. You might need to use additional knowledge to answer the question.
10. You are an AI assistant that helps people find information. User will you give you a question. Your task is to answer as faithfully as you can. While answering think step-by- step and justify your answer.
11. User will you give you a task with some instruction. Your job is follow the instructions as faithfully as you can. While answering think step-by-step and justify your answer.
12. You are a teacher. Given a task, you explain in simple steps what the task is asking, any guidelines it provides and how to use those guidelines to find the answer.
13. You are an AI assistant, who knows every language and how to translate one language to another. Given a task, you explain in simple steps what the task is asking, any guidelines that it provides. You solve the task and show how you used the guidelines to solve the task.
14. Given a definition of a task and a sample input, break the definition into small parts. Each of those parts will have some instruction. Explain their meaning by showing an example that meets the criteria in the instruction. Use the following format: Part \#: a key part of the definition. Usage: Sample response that meets the criteria from the key part. Explain why you think it meets the criteria.
15. You are an AI assistant that helps people find information.
## Datasets: Orca-Chat/Dolphin, RedPajama1T & FanFics
This model was trained on:
- [shahules786/orca-chat](https://huggingface.co/datasets/shahules786/orca-chat)
- [togethercomputer/RedPajama-Data-1T-Sample](https://huggingface.co/datasets/togethercomputer/RedPajama-Data-1T)
- [atom-in-the-universe/fanfics-10k-50k](https://huggingface.co/datasets/atom-in-the-universe/fanfics-10k-50k)
```
Dataset Composition:
Tain (sampled):
orca-chat: 188842 (100%)
fanfics: 47760 (100%)
red_pajama: 188262 (25%)
Valid:
orca-chat: 5000
fanfics: 1000
red_pajama: 1000
```
The dataset [shahules786/orca-chat](https://huggingface.co/datasets/shahules786/orca-chat) combines similar examples of the GPT-4 subset of [ehartford/dolphin](https://huggingface.co/datasets/ehartford/dolphin) to form longer conversations
to improve long-context training.
Additionally, RedPajama and FanFics were used for classic language modelling as an auxiliary task to improve the RoPE scaling for the 8k context size.
## Model Configuration
```
llama2_13b_orca_8k:
rng_seed: 0xe1291f1a
use_custom_sampler: true
sort_by_length: false
dtype: fp16
log_dir: "llama2_log_13b_orca_8k"
learning_rate: 1e-5
model_name: /mnt/data/llama2/Llama-2-13b-hf/
output_dir: llama2_13b_orca_8k
deepspeed_config: configs/zero_config_pretrain.json
weight_decay: 0.0
max_length: 8192
warmup_steps: 100
use_flash_attention: true
gradient_checkpointing: true
gradient_accumulation_steps: 8
per_device_train_batch_size: 2
per_device_eval_batch_size: 1
residual_dropout: 0.0
eval_steps: 200
save_steps: 1000 # (total steps: 3319)
num_train_epochs: 1
save_total_limit: 4
superhot: true
superhot_config:
type: linear
scale: 2
datasets:
- orca-chat:
max_val_set: 5000
- fanfics:
max_chunk_size: 65535
max_val_set: 1000
- red_pajama:
fraction: 0.25
max_val_set: 1000
max_chunk_size: 65535
peft_model: false
```
# Developers
- [shahules786](https://github.com/shahules786)
- [jordiclive](https://github.com/jordiclive)
- [andreaskoepf](https://github.com/andreaskoepf/)
# Special Thanks
We want to especially thank Eric Hartford who spared no expense in replicating ORCA and making it available at [ehartford/dolphin](https://huggingface.co/datasets/ehartford/dolphin)!
Also, shoutout to the whole team working on [LLongMA-2-13b](https://huggingface.co/conceptofmind/LLongMA-2-13b) & the [scaled-rope](https://github.com/jquesnelle/scaled-rope) repository for their awesome work: bloc97, jquesnelle & conceptofmind!
The whole Open-Assistant team is very grateful for the continued support of [Redmond.ai](https://redmond.ai/) who sponsored the training compute required for this model.
# License
- Llama 2 is licensed under the LLAMA 2 Community License, Copyright © Meta Platforms, Inc. All Rights Reserved.
- Your use of the Llama Materials must comply with applicable laws and regulations (including trade compliance laws and regulations) and adhere to the [Acceptable Use Policy](https://ai.meta.com/llama/use-policy) for the Llama Materials.
<!-- original-model-card end -->
|
hadongz/falcon-7b-instruct-gguf | hadongz | "2023-09-23T10:47:32Z" | 1,066 | 1 | null | [
"gguf",
"text-generation",
"license:apache-2.0",
"region:us"
] | text-generation | "2023-09-22T14:04:54Z" | ---
license: apache-2.0
pipeline_tag: text-generation
--- |
mncai/Mistral-7B-CollectiveCognition | mncai | "2023-10-22T04:35:52Z" | 1,066 | 0 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"MindsAndCompany",
"en",
"dataset:CollectiveCognition/chats-data-2023-09-27",
"arxiv:2306.02707",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-10-20T06:54:07Z" | ---
pipeline_tag: text-generation
license: mit
language:
- en
library_name: transformers
tags:
- MindsAndCompany
datasets:
- CollectiveCognition/chats-data-2023-09-27
---
## Model Details
* **Developed by**: [Minds And Company](https://mnc.ai/)
* **Backbone Model**: [Mistral-7B-v0.1](mistralai/Mistral-7B-v0.1)
* **Library**: [HuggingFace Transformers](https://github.com/huggingface/transformers)
## Dataset Details
### Used Datasets
- CollectiveCognition/chats-data-2023-09-27
### Prompt Template
- Llama Prompt Template
## Limitations & Biases:
Llama2 and fine-tuned variants are a new technology that carries risks with use. Testing conducted to date has been in English, and has not covered, nor could it cover all scenarios. For these reasons, as with all LLMs, Llama 2 and any fine-tuned varient's potential outputs cannot be predicted in advance, and the model may in some instances produce inaccurate, biased or other objectionable responses to user prompts. Therefore, before deploying any applications of Llama 2 variants, developers should perform safety testing and tuning tailored to their specific applications of the model.
Please see the Responsible Use Guide available at https://ai.meta.com/llama/responsible-use-guide/
## License Disclaimer:
This model is bound by the license & usage restrictions of the original Llama-2 model. And comes with no warranty or gurantees of any kind.
## Contact Us
- [Minds And Company](https://mnc.ai/)
## Citiation:
Please kindly cite using the following BibTeX:
```bibtex
@misc{mukherjee2023orca,
title={Orca: Progressive Learning from Complex Explanation Traces of GPT-4},
author={Subhabrata Mukherjee and Arindam Mitra and Ganesh Jawahar and Sahaj Agarwal and Hamid Palangi and Ahmed Awadallah},
year={2023},
eprint={2306.02707},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
```
```
@misc{Orca-best,
title = {Orca-best: A filtered version of orca gpt4 dataset.},
author = {Shahul Es},
year = {2023},
publisher = {HuggingFace},
journal = {HuggingFace repository},
howpublished = {\url{https://huggingface.co/datasets/shahules786/orca-best/},
}
```
```
@software{touvron2023llama2,
title={Llama 2: Open Foundation and Fine-Tuned Chat Models},
author={Hugo Touvron, Louis Martin, Kevin Stone, Peter Albert, Amjad Almahairi, Yasmine Babaei, Nikolay Bashlykov, Soumya Batra, Prajjwal Bhargava,
Shruti Bhosale, Dan Bikel, Lukas Blecher, Cristian Canton Ferrer, Moya Chen, Guillem Cucurull, David Esiobu, Jude Fernandes, Jeremy Fu, Wenyin Fu, Brian Fuller,
Cynthia Gao, Vedanuj Goswami, Naman Goyal, Anthony Hartshorn, Saghar Hosseini, Rui Hou, Hakan Inan, Marcin Kardas, Viktor Kerkez Madian Khabsa, Isabel Kloumann,
Artem Korenev, Punit Singh Koura, Marie-Anne Lachaux, Thibaut Lavril, Jenya Lee, Diana Liskovich, Yinghai Lu, Yuning Mao, Xavier Martinet, Todor Mihaylov,
Pushkar Mishra, Igor Molybog, Yixin Nie, Andrew Poulton, Jeremy Reizenstein, Rashi Rungta, Kalyan Saladi, Alan Schelten, Ruan Silva, Eric Michael Smith,
Ranjan Subramanian, Xiaoqing Ellen Tan, Binh Tang, Ross Taylor, Adina Williams, Jian Xiang Kuan, Puxin Xu , Zheng Yan, Iliyan Zarov, Yuchen Zhang, Angela Fan,
Melanie Kambadur, Sharan Narang, Aurelien Rodriguez, Robert Stojnic, Sergey Edunov, Thomas Scialom},
year={2023}
}
```
> Readme format: [Riiid/sheep-duck-llama-2-70b-v1.1](https://huggingface.co/Riiid/sheep-duck-llama-2-70b-v1.1) |
bongchoi/MoMo-70B-V1.1 | bongchoi | "2023-11-14T12:16:28Z" | 1,066 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"en",
"license:llama2",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-11-10T08:10:14Z" | ---
license: llama2
language:
- en
library_name: transformers
---
## Dataset Details
### Used Datasets
- Orca-style dataset
- Alpaca-style dataset
- No other dataset was used except for the dataset mentioned above
- No benchmark test set or the training set are used
## Prompt Template
### Alpaca-style |
OrionStarAI/Orion-14B-Base | OrionStarAI | "2024-03-26T09:21:52Z" | 1,066 | 74 | transformers | [
"transformers",
"pytorch",
"orion",
"text-generation",
"code",
"model",
"llm",
"custom_code",
"en",
"zh",
"ja",
"ko",
"autotrain_compatible",
"region:us"
] | text-generation | "2024-01-16T06:07:42Z" | ---
language:
- en
- zh
- ja
- ko
metrics:
- accuracy
pipeline_tag: text-generation
tags:
- code
- model
- llm
---
<!-- markdownlint-disable first-line-h1 -->
<!-- markdownlint-disable html -->
<div align="center">
<img src="./assets/imgs/orion_start.PNG" alt="logo" width="50%" />
</div>
<div align="center">
<h1>
Orion-14B
</h1>
</div>
<div align="center">
<div align="center">
<b>🌐English</b> | <a href="https://huggingface.co/OrionStarAI/Orion-14B-Base/blob/main/README_zh.md" target="_blank">🇨🇳中文</a> | <a href="https://huggingface.co/OrionStarAI/Orion-14B-Base/blob/main/README_ja.md" target="_blank">🇯🇵日本語</a> |<a href="https://huggingface.co/OrionStarAI/Orion-14B-Base/blob/main/README_ko.md" target="_blank">🇰🇷한국어</a>
</div>
<h4 align="center">
<p>
🤗 <a href="https://huggingface.co/OrionStarAI" target="_blank">HuggingFace Mainpage</a> | 🤖 <a href="https://modelscope.cn/organization/OrionStarAI" target="_blank">ModelScope Mainpage</a><br>🎬 <a href="https://huggingface.co/spaces/OrionStarAI/Orion-14B-App-Demo" target="_blank">HuggingFace Demo</a> | 🎫 <a href="https://modelscope.cn/studios/OrionStarAI/Orion-14B-App-Demo/summary" target="_blank">ModelScope Demo</a><br>😺 <a href="https://github.com/OrionStarAI/Orion" target="_blank">GitHub</a><br>📖 <a href="https://github.com/OrionStarAI/Orion/blob/master/doc/Orion14B_v3.pdf" target="_blank">Tech Report</a>
<p>
</h4>
</div>
# Table of Contents
- [📖 Model Introduction](#model-introduction)
- [🔗 Model Download](#model-download)
- [🔖 Model Benchmark](#model-benchmark)
- [📊 Model Inference](#model-inference) [<img src="./assets/imgs/vllm_1.png" alt="vllm" style="margin: 0;display: initial;" height="20" />](#vllm) [<img src="./assets/imgs/llama_cpp_1.png" alt="llamacpp" style="margin: 0;display: initial;" height="20" />](#llama-cpp)
- [📜 Declarations & License](#declarations-license)
- [🥇 Company Introduction](#company-introduction)
<a name="model-introduction"></a><br>
# 1. Model Introduction
- Orion-14B series models are open-source multilingual large language models trained from scratch by OrionStarAI. The base model is trained on 2.5T multilingual corpus, including Chinese, English, Japanese, Korean, etc, and it exhibits superior performance in these languages. For details, please refer to [tech report](https://github.com/OrionStarAI/Orion/blob/master/doc/Orion14B_v3.pdf).
- The Orion-14B series models exhibit the following features:
- Among models with 20B-parameter scale level, Orion-14B-Base model shows outstanding performance in comprehensive evaluations.
- Strong multilingual capabilities, significantly outperforming in Japanese and Korean testsets.
- The fine-tuned models demonstrate strong adaptability, excelling in human-annotated blind tests.
- The long-chat version supports extremely long texts, performing exceptionally well at a token length of 200k and can support up to a maximum of 320k.
- The quantized versions reduce model size by 70%, improve inference speed by 30%, with performance loss less than 1%.
<table style="border-collapse: collapse; width: 100%;">
<tr>
<td style="border: none; padding: 10px; box-sizing: border-box;">
<img src="./assets/imgs/opencompass_en.png" alt="opencompass" style="width: 100%; height: auto;">
</td>
<td style="border: none; padding: 10px; box-sizing: border-box;">
<img src="./assets/imgs/model_cap_en.png" alt="modelcap" style="width: 100%; height: auto;">
</td>
</tr>
</table>
- Orion-14B series models including:
- **Orion-14B-Base:** A multilingual large language foundational model with 14 billion parameters, pretrained on a diverse dataset of 2.5 trillion tokens.
- **Orion-14B-Chat:** A chat-model fine-tuned on a high-quality corpus aims to provide an excellence interactive experience for users in the large model community.
- **Orion-14B-LongChat:** The long-context version excels at handling extremely lengthy texts, performing exceptionally well at a token length of 200k and can support up to a maximum of 320k.
- **Orion-14B-Chat-RAG:** A chat-model fine-tuned on a custom retrieval augmented generation dataset, achieving superior performance in retrieval augmented generation tasks.
- **Orion-14B-Chat-Plugin:** A chat-model specifically tailored for plugin and function calling tasks, ideal for agent-related scenarios where the LLM acts as a plugin and function call system.
- **Orion-14B-Base-Int4:** A quantized base model utilizing 4-bit integer weights. It significantly reduces the model size by 70% and increases the inference speed by 30% while incurring a minimal performance loss of only 1%.
- **Orion-14B-Chat-Int4:** A quantized chat model utilizing 4-bit integer weights.
<a name="model-download"></a><br>
# 2. Model Download
Model release and download links are provided in the table below:
| Model Name | HuggingFace Download Links | ModelScope Download Links |
|-------------------------|-----------------------------------------------------------------------------------|-------------------------------------------------------------------------------------------------|
| ⚾Orion-14B-Base | [Orion-14B-Base](https://huggingface.co/OrionStarAI/Orion-14B-Base) | [Orion-14B-Base](https://modelscope.cn/models/OrionStarAI/Orion-14B-Base/summary) |
| 😛Orion-14B-Chat | [Orion-14B-Chat](https://huggingface.co/OrionStarAI/Orion-14B-Chat) | [Orion-14B-Chat](https://modelscope.cn/models/OrionStarAI/Orion-14B-Chat/summary) |
| 📃Orion-14B-LongChat | [Orion-14B-LongChat](https://huggingface.co/OrionStarAI/Orion-14B-LongChat) | [Orion-14B-LongChat](https://modelscope.cn/models/OrionStarAI/Orion-14B-LongChat/summary) |
| 🔎Orion-14B-Chat-RAG | [Orion-14B-Chat-RAG](https://huggingface.co/OrionStarAI/Orion-14B-Chat-RAG) | [Orion-14B-Chat-RAG](https://modelscope.cn/models/OrionStarAI/Orion-14B-Chat-RAG/summary) |
| 🔌Orion-14B-Chat-Plugin | [Orion-14B-Chat-Plugin](https://huggingface.co/OrionStarAI/Orion-14B-Chat-Plugin) | [Orion-14B-Chat-Plugin](https://modelscope.cn/models/OrionStarAI/Orion-14B-Chat-Plugin/summary) |
| 💼Orion-14B-Base-Int4 | [Orion-14B-Base-Int4](https://huggingface.co/OrionStarAI/Orion-14B-Base-Int4) | [Orion-14B-Base-Int4](https://modelscope.cn/models/OrionStarAI/Orion-14B-Base-Int4/summary) |
| 📦Orion-14B-Chat-Int4 | [Orion-14B-Chat-Int4](https://huggingface.co/OrionStarAI/Orion-14B-Chat-Int4) | [Orion-14B-Chat-Int4](https://modelscope.cn/models/OrionStarAI/Orion-14B-Chat-Int4/summary) |
<a name="model-benchmark"></a><br>
# 3. Model Benchmarks
## 3.1. Base Model Orion-14B-Base Benchmarks
### 3.1.1. LLM evaluation results on examination and professional knowledge
| Model | C-Eval | CMMLU | MMLU | AGIEval | Gaokao | BBH |
|--------------------|----------|----------|----------|----------|----------|----------|
| LLaMA2-13B | 41.4 | 38.4 | 55.0 | 30.9 | 18.2 | 45.6 |
| Skywork-13B | 59.1 | 61.4 | 62.7 | 43.6 | 56.1 | 48.3 |
| Baichuan2-13B | 59.0 | 61.3 | 59.5 | 37.4 | 45.6 | 49.0 |
| QWEN-14B | 71.7 | 70.2 | 67.9 | 51.9 | **62.5** | 53.7 |
| InternLM-20B | 58.8 | 59.0 | 62.1 | 44.6 | 45.5 | 52.5 |
| **Orion-14B-Base** | **72.9** | **70.6** | **69.9** | **54.7** | 62.1 | **56.5** |
### 3.1.2. LLM evaluation results on language understanding and common knowledge
| Model |RACE-middle|RACE-high |HellaSwag | PIQA | Lambada | WSC |
|--------------------|----------|----------|----------|----------|----------|----------|
| LLaMA 2-13B | 63.0 | 58.9 | 77.5 | 79.8 | 76.5 | 66.3 |
| Skywork-13B | 87.6 | 84.1 | 73.7 | 78.3 | 71.8 | 66.3 |
| Baichuan 2-13B | 68.9 | 67.2 | 70.8 | 78.1 | 74.1 | 66.3 |
| QWEN-14B | 93.0 | 90.3 | **80.2** | 79.8 | 71.4 | 66.3 |
| InternLM-20B | 86.4 | 83.3 | 78.1 | **80.3** | 71.8 | 68.3 |
| **Orion-14B-Base** | **93.2** | **91.3** | 78.5 | 79.5 | **78.8** | **70.2** |
### 3.1.3. LLM evaluation results of OpenCompass testsets
| Model | Average | Examination | Language | Knowledge | Understanding | Reasoning |
|------------------|----------|----------|----------|----------|----------|----------|
| LLaMA 2-13B | 47.3 | 45.2 | 47.0 | 58.3 | 50.9 | 43.6 |
| Skywork-13B | 53.6 | 61.1 | 51.3 | 52.7 | 64.5 | 45.2 |
| Baichuan 2-13B | 49.4 | 51.8 | 47.5 | 48.9 | 58.1 | 44.2 |
| QWEN-14B | 62.4 | 71.3 | 52.67 | 56.1 | 68.8 | 60.1 |
| InternLM-20B | 59.4 | 62.5 | 55.0 | **60.1** | 67.3 | 54.9 |
|**Orion-14B-Base**| **64.3** | **71.4** | **55.0** | 60.0 | **71.9** | **61.6** |
### 3.1.4. Comparison of LLM performances on Japanese testsets
| Model |**Average**| JCQA | JNLI | MARC | JSQD | JQK | XLS | XWN | MGSM |
|--------------------|----------|----------|----------|----------|----------|----------|----------|----------|----------|
| PLaMo-13B | 52.3 | 56.7 | 42.8 | 95.8 | 70.6 | 71.0 | 8.70 | 70.5 | 2.40 |
| WebLab-10B | 50.7 | 66.6 | 53.7 | 82.1 | 62.9 | 56.2 | 10.0 | 72.0 | 2.40 |
| ELYZA-jp-7B | 48.8 | 71.7 | 25.3 | 86.6 | 70.8 | 64.1 | 2.50 | 62.1 | 7.20 |
| StableLM-jp-7B | 51.1 | 33.4 | 43.3 | **96.7** | 70.6 | 78.1 | 10.7 | 72.8 | 2.80 |
| LLaMA 2-13B | 46.3 | 75.0 | 47.6 | 38.8 | 76.1 | 67.7 | 18.1 | 63.2 | 10.4 |
| Baichuan 2-13B | 57.1 | 73.7 | 31.3 | 91.6 | 80.5 | 63.3 | 18.6 | 72.2 | 25.2 |
| QWEN-14B | 65.8 | 85.9 | 60.7 | 97.0 | 83.3 | 71.8 | 18.8 | 70.6 | 38.0 |
| Yi-34B | 67.1 | 83.8 | 61.2 | 95.2 | **86.1** | 78.5 | **27.2** | 69.2 | 35.2 |
| **Orion-14B-Base** | **69.1** | **88.2** | **75.8** | 94.1 | 75.7 | **85.1** | 17.3 | **78.8** | **38.0** |
### 3.1.5. Comparison of LLM performances on Korean testsets. n = 0 and n = 5 stand for n-shot prompts used in the evaluation
|Model | **Average**<br>n=0 n=5 | HellaSwag<br>n=0 n=5 | COPA<br> n=0 n=5 | BooIQ<br>n=0 n=5 | SentiNeg<br>n=0 n=5|
|------------------|------------------------------|------------------------------|------------------------------|------------------------------|------------------------------|
| KoGPT | 53.0 70.1 | 55.9 58.3 | 73.5 72.9 | 45.1 59.8 | 37.5 89.4 |
| Polyglot-ko-13B | 69.6 73.7 |**59.5** **63.1**|**79.4** **81.1**| 48.2 60.4 | 91.2 90.2 |
| LLaMA 2-13B | 46.7 63.7 | 41.3 44.0 | 59.3 63.8 | 34.9 73.8 | 51.5 73.4 |
| Baichuan 2-13B | 52.1 58.7 | 39.2 39.6 | 60.6 60.6 | 58.4 61.5 | 50.3 72.9 |
| QWEN-14B | 53.8 73.7 | 45.3 46.8 | 64.9 68.9 | 33.4 83.5 | 71.5 95.7 |
| Yi-34B | 54.2 72.1 | 44.6 44.7 | 58.0 60.6 | 65.9 90.2 | 48.3 92.9 |
|**Orion-14B-Chat**|**74.5** **79.6**| 47.0 49.6 | 77.7 79.4 |**81.6** **90.7**|**92.4** **98.7**|
### 3.1.6. Multilingual evaluation
| Model | Train Lang | Japanese | Korean | Chinese | English |
|--------------------|------------|----------|----------|----------|----------|
| PLaMo-13B | En,Jp | 52.3 | * | * | * |
| Weblab-10B | En,Jp | 50.7 | * | * | * |
| ELYZA-jp-7B | En,Jp | 48.8 | * | * | * |
| StableLM-jp-7B | En,Jp | 51.1 | * | * | * |
| KoGPT-6B | En,Ko | * | 70.1 | * | * |
| Polyglot-ko-13B | En,Ko | * | 70.7 | * | * |
| Baichuan2-13B | Multi | 57.1 | 58.7 | 50.8 | 57.1 |
| Qwen-14B | Multi | 65.8 | 73.7 | 64.5 | 65.4 |
| Llama2-13B | Multi | 46.3 | 63.7 | 41.4 | 55.3 |
| Yi-34B | Multi | 67.1 | 72.2 | 58.7 | **68.8** |
| **Orion-14B-Chat** | Multi | **69.1** | **79.5** | **67.9** | 67.3 |
## 3.2. Chat Model Orion-14B-Chat Benchmarks
### 3.2.1. Chat model subjective evaluation of MTBench
| Model | First-Turn | Second-Turn | **Average** |
|----------------------|----------|----------|----------|
| Baichuan2-13B-Chat | 7.05 | 6.47 | 6.76 |
| Qwen-14B-Chat | 7.30 | 6.62 | 6.96 |
| Llama2-13B-Chat | 7.10 | 6.20 | 6.65 |
| InternLM-20B-Chat | 7.03 | 5.93 | 6.48 |
| **Orion-14B-Chat** | **7.68** | **7.07** | **7.37** |
\* use vllm for inference
### 3.2.2. Chat model subjective evaluation of AlignBench
| Model | Math. | Logi. | Basic. | Chi. | Comp. | Writ. | Role. | Prof. |**Avg.**|
|--------------------|--------|--------|--------|--------|--------|--------|--------|--------|--------|
| Baichuan2-13B-Chat | 3.76 | 4.07 | 6.22 | 6.05 | 7.11 | 6.97 | 6.75 | 6.43 | 5.25 |
| Qwen-14B-Chat |**4.91**|**4.71**|**6.90**| 6.36 | 6.74 | 6.64 | 6.59 | 6.56 |**5.72**|
| Llama2-13B-Chat | 3.05 | 3.79 | 5.43 | 4.40 | 6.76 | 6.63 | 6.99 | 5.65 | 4.70 |
| InternLM-20B-Chat | 3.39 | 3.92 | 5.96 | 5.50 |**7.18**| 6.19 | 6.49 | 6.22 | 4.96 |
| **Orion-14B-Chat** | 4.00 | 4.24 | 6.18 |**6.57**| 7.16 |**7.36**|**7.16**|**6.99**| 5.51 |
\* use vllm for inference
## 3.3. LongChat Model Orion-14B-LongChat Benchmarks
### 3.3.1. LongChat evaluation of LongBench
| Model | NarrativeQA|MultiFieldQA-en|MultiFieldQA-zh| DuReader | QMSum | VCSUM | TREC | TriviaQA | LSHT |RepoBench-P|
|--------------------------|-----------|-----------|-----------|-----------|-----------|-----------|-----------|-----------|-----------|-----------|
| GPT-3.5-Turbo-16k | **23.60** | **52.30** | **61.20** | 28.70 | 23.40 | **16.00** | 68.00 | **91.40** | 29.20 | 53.60 |
| LongChat-v1.5-7B-32k | 16.90 | 41.40 | 29.10 | 19.50 | 22.70 | 9.90 | 63.50 | 82.30 | 23.20 | 55.30 |
| Vicuna-v1.5-7B-16k | 19.40 | 38.50 | 43.00 | 19.30 | 22.80 | 15.10 | 71.50 | 86.20 | 28.80 | 43.50 |
| Yi-6B-200K | 14.11 | 36.74 | 22.68 | 14.01 | 20.44 | 8.08 | 72.00 | 86.61 | 38.00 | **63.29** |
| Orion-14B-LongChat | 19.47 | 48.11 | 55.84 | **37.02** | **24.87** | 15.44 | **77.00** | 89.12 | **45.50** | 54.31 |
## 3.4. Chat RAG Model Benchmarks
### 3.4.1. LLM evaluation results of self-built RAG testsets
|Model|Effectiveness of Response(Keyword)|*Effectiveness of Response（subjective evaluation）|Quoting Ability|Fallback Ability|*AutoQA|*Data Extraction|
|---------------------|------|------|------|------|------|------|
| Baichuan2-13B-Chat | 85 | 76 | 1 | 0 | 69 | 51 |
| Qwen-14B-Chat | 79 | 77 | 75 | 47 | 68 | 72 |
| Qwen-72B-Chat(Int4) | 87 | 89 | 90 | 32 | 67 | 76 |
| GPT-4 | 91 | 94 | 96 | 95 | 75 | 86 |
| Orion-14B-Chat-RAG | 86 | 87 | 91 | 97 | 73 | 71 |
\* means manual assessment
## 3.5. Chat Plugin Model Orion-14B-Chat-Plugin Benchmarks
### 3.5.1. LLM evaluation results of self-built plugin testsets
|Model |Intent Recognition with Full Params |Intent Recognition with Missing Params |Non-Plugin Invocation Recognition |
|-----------------------|--------|-----------|--------|
| Baichuan2-13B-Chat | 25 | 0 | 0 |
| Qwen-14B-Chat | 55 | 0 | 50 |
| GPT-4 | **95** | 52.38 | 70 |
| Orion-14B-Chat-Plugin | 92.5 | **60.32** | **90** |
## 3.6. Quantized Model Orion-14B-Base-Int4 Benchmarks
### 3.6.1. Comparison of before and after quantization
|Model |Size(GB)|Inference Speed(tokens/s)|C-Eval|CMMLU|MMLU|RACE|HellaSwag|
|-------------------------|-------|-----|------|------|------|------|------|
| OrionStar-14B-Base | 28.0 | 135 | 72.8 | 70.6 | 70.0 | 93.3 | 78.5 |
| OrionStar-14B-Base-Int4 | 8.3 | 178 | 71.8 | 69.8 | 69.2 | 93.1 | 78.0 |
<a name="model-inference"></a><br>
# 4. Model Inference
Model weights, source code, and configuration needed for inference are published on Hugging Face, and the download link
is available in the table at the beginning of this document. We demonstrate various inference methods here, and the
program will automatically download the necessary resources from Hugging Face.
## 4.1. Python Code
```python
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
from transformers.generation.utils import GenerationConfig
tokenizer = AutoTokenizer.from_pretrained("OrionStarAI/Orion-14B", use_fast=False, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("OrionStarAI/Orion-14B", device_map="auto",
torch_dtype=torch.bfloat16, trust_remote_code=True)
model.generation_config = GenerationConfig.from_pretrained("OrionStarAI/Orion-14B")
messages = [{"role": "user", "content": "Hello, what is your name? "}]
response = model.chat(tokenizer, messages, streaming=False)
print(response)
```
In the above Python code, the model is loaded with `device_map='auto'` to utilize all available GPUs. To specify the
device, you can use something like `export CUDA_VISIBLE_DEVICES=0,1` (using GPUs 0 and 1).
## 4.2. Command Line Tool
```shell
CUDA_VISIBLE_DEVICES=0 python cli_demo.py
```
This command-line tool is designed for chat scenarios, and thus, it does not support calling the base model.
## 4.3. Direct Script Inference
```shell
# base model
CUDA_VISIBLE_DEVICES=0 python demo/text_generation_base.py --model OrionStarAI/Orion-14B --tokenizer OrionStarAI/Orion-14B --prompt hello
# chat model
CUDA_VISIBLE_DEVICES=0 python demo/text_generation.py --model OrionStarAI/Orion-14B-Chat --tokenizer OrionStarAI/Orion-14B-Chat --prompt hi
```
<a name="vllm"></a><br>
## 4.4. Inference by vllm
- Project URL<br>
https://github.com/vllm-project/vllm
- Pull Request<br>
https://github.com/vllm-project/vllm/pull/2539
<a name="llama-cpp"></a><br>
## 4.5. Inference by llama.cpp
- Project URL<br>
https://github.com/ggerganov/llama.cpp
- Pull Request<br>
https://github.com/ggerganov/llama.cpp/pull/5118
- How to convert to GGUF model
```shell
python convert-hf-to-gguf.py path/to/Orion-14B-Chat --outfile chat.gguf
```
- How to run generation
```shell
./main --frequency-penalty 0.5 --frequency-penalty 0.5 --top-k 5 --top-p 0.9 -m chat.gguf -p "Building a website can be done in 10 simple steps:\nStep 1:" -n 400 -e
```
## 4.6 Example Output
### 4.6.1. Casual Chat
`````
User: Hello
Orion-14B: Hello! How can I help you today? If you have any questions or need assistance, feel free to ask.
User: What functions do you have?
Orion-14B: As an AI language model, I have a wide range of functions and capabilities, including but not limited to:
Answering general knowledge questions: I can provide information on various topics such as history, science, geography, and more.
Providing definitions and explanations: I can explain complex concepts and provide definitions for words and phrases.
Assisting with tasks: I can help with simple tasks like setting reminders, converting units of measurement, and even ordering food from restaurants.
Generating text: I can write short stories, essays, articles, and other types of content based on prompts given to me.
Translating languages: I can translate text from one language to another.
Chatting: I can engage in conversation with users and respond to their queries in a conversational manner.
Summarizing long texts: I can summarize longer texts like articles, books, and research papers.
Generating random numbers and names: I can generate random numbers within a specified range and also suggest names based on certain criteria.
Playing games: I can play simple games like Hangman, Trivia, and more.
Providing recommendations: I can recommend movies, music, books, and other forms of entertainment based on user preferences.
These are just some of the many functions that I am capable of performing. If you have a specific task in mind, feel free to ask me about it.
User: Tell me a joke.
Orion-14B: Sure, here's a classic one-liner: Why don't scientists trust atoms? Because they make up everything.
`````
### 4.6.2. Japanese & Korean Chat
`````
User：自己を紹介してください
Orion-14B：こんにちは、私の名前はChatMaxで、OrionStarによって開発されたAIアシスタントです。私はユーザーに正確で、客観的で、有用な回答を提供し、彼らが問題を解決し、情報を取得するのを助けることができます。
User：자기소개를 해주세요.
Orion-14B：안녕하세요, 제 이름은 ChatMax입니다. OrionStar에서 개발한 AI 어시스턴트입니다. 저는 사용자들에게 정확하고 객관적이며 유용한 답변을 제공하여 문제를 해결하고 정보를 얻는 데 도움을 줄 수 있습니다.
`````
<a name="declarations-license"></a><br>
# 5. Declarations, License
## 5.1. Declarations
We strongly urge all users not to use the Orion-14B model for any activities that may harm national or social security or violate the law.
Additionally, we request users not to use the Orion-14B model for internet services without proper security review and filing.
We hope all users abide by this principle to ensure that technological development takes place in a regulated and legal environment.
We have done our best to ensure the compliance of the data used in the model training process. However, despite our
significant efforts, unforeseen issues may still arise due to the complexity of the model and data. Therefore, if any
problems arise due to the use of the Orion-14B open-source model, including but not limited to data security
issues, public opinion risks, or any risks and issues arising from the model being misled, abused, disseminated, or
improperly utilized, we will not assume any responsibility.
## 5.2. License
Community use of the Orion-14B series models
- For code, please comply with [Apache License Version 2.0](./LICENSE)<br>
- For model, please comply with [【Orion-14B Series】 Models Community License Agreement](./ModelsCommunityLicenseAgreement)
<a name="company-introduction"></a><br>
# 6. Company Introduction
OrionStar is a leading global service robot solutions company, founded in September 2016. OrionStar is dedicated to
using artificial intelligence technology to create the next generation of revolutionary robots, allowing people to break
free from repetitive physical labor and making human work and life more intelligent and enjoyable. Through technology,
OrionStar aims to make society and the world a better place.
OrionStar possesses fully self-developed end-to-end artificial intelligence technologies, such as voice interaction and
visual navigation. It integrates product development capabilities and technological application capabilities. Based on
the Orion robotic arm platform, it has launched products such as OrionStar AI Robot Greeting, AI Robot Greeting Mini,
Lucki, Coffee Master, and established the open platform OrionOS for Orion robots. Following the philosophy of "Born for
Truly Useful Robots", OrionStar empowers more people through AI technology.
**The core strengths of OrionStar lies in possessing end-to-end AI application capabilities,** including big data preprocessing, large model pretraining, fine-tuning, prompt engineering, agent, etc. With comprehensive end-to-end model training capabilities, including systematic data processing workflows and the parallel model training capability of hundreds of GPUs, it has been successfully applied in various industry scenarios such as government affairs, cloud services, international e-commerce, and fast-moving consumer goods.
Companies with demands for deploying large-scale model applications are welcome to contact us.<br>
**Enquiry Hotline: 400-898-7779**<br>
**E-mail: [email protected]**<br>
**Discord Link: https://discord.gg/zumjDWgdAs**
<div align="center">
<img src="./assets/imgs/wechat_group.jpg" alt="wechat" width="40%" />
</div>
|
lodrick-the-lafted/Grafted-Titanic-Dolphin-2x120B | lodrick-the-lafted | "2024-01-29T21:49:49Z" | 1,066 | 7 | transformers | [
"transformers",
"safetensors",
"mixtral",
"text-generation",
"moe",
"merge",
"license:llama2",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-01-20T16:33:06Z" | ---
license: llama2
tags:
- moe
- merge
---
Where we're going, we don't need reason.
Goliath x MegaDolphin.
Imagine trying to QuIP# this thing?
<img src=https://huggingface.co/lodrick-the-lafted/Grafted-Titanic-Dolphin-2x120B/resolve/main/gtd.png>
Official hall of shame winner at https://merge.moe. This would not have been possible without Charles Goddard's hard work!
## 💻 Usage
```python
from transformers import AutoTokenizer
import transformers
import torch
model = "lodrick-the-lafted/Grafted-Titanic-Dolphin-2x120B"
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"])
```
|
yhkim9362/gemma-en-ko-7b-v0.2 | yhkim9362 | "2024-04-19T08:20:02Z" | 1,066 | 0 | transformers | [
"transformers",
"safetensors",
"gemma",
"text-generation",
"korean",
"pytorch",
"conversational",
"ko",
"en",
"arxiv:1910.09700",
"base_model:google/gemma-7b-it",
"license:other",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-04-19T01:55:51Z" | ---
library_name: transformers
license: other
license_name: gemma-terms-of-use
license_link: https://ai.google.dev/gemma/terms
language:
- ko
- en
tags:
- korean
- gemma
- pytorch
pipeline_tag: text-generation
base_model: google/gemma-7b-it
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
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]
|
bhenrym14/airoboros-33b-gpt4-1.4.1-PI-8192-GPTQ | bhenrym14 | "2023-07-03T23:23:53Z" | 1,065 | 14 | transformers | [
"transformers",
"llama",
"text-generation",
"dataset:jondurbin/airoboros-gpt4-1.4.1",
"arxiv:2306.15595",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-07-03T13:41:09Z" | ---
datasets:
- jondurbin/airoboros-gpt4-1.4.1
---
# RoPE Scaled QLoRA Finetune of airoboros-33b-gpt4-1.4.1 (GPTQ)
LoRA Weights can be found here: https://huggingface.co/bhenrym14/airoboros-33b-gpt4-1.4.1-PI-8192-LoRA
fp16 weights can be found here: https://huggingface.co/bhenrym14/airoboros-33b-gpt4-1.4.1-PI-8192-fp16
## Overview
This is [Jon Durbin's Airoboros 33B GPT4 1.4](https://huggingface.co/jondurbin/airoboros-33b-gpt4-1.4) (merged model with GPTQ Quantization) with several key modifications:
- Context length extended to 8192 by RoPE Scaled Embeddings, but NOT via the superHOT LoRA. I started with base Llama-33b.
- Training sequences beyond 2048 have the target truncated to equal 2048.
- Used airoboros-gpt4-1.4.1 dataset instead of airoboros-gpt4-1.4
Otherwise, I emulated the training process as closely as possible (rank 64 QLoRA) It was trained on 1x RTX 6000 Ada for ~43 hours.
## How to Use
The easiest way is to use [oobabooga text-generation-webui](https://github.com/oobabooga/text-generation-webui) with ExLlama. You'll need to set max_seq_len to 8192 and compress_pos_emb to 4.
## Motivation
Recent advancements in extending context by RoPE scaling ([kaiokendev](https://kaiokendev.github.io/til#extending-context-to-8k) and [meta AI)](https://arxiv.org/abs/2306.15595)) demonstrate the ability to extend the context window without (total) retraining. Finetuning has shown to be necessary to properly leverage the longer context. The superHOT LoRA is an adapter that has been finetuned on longer context (8192 tokens); even when applied to models trained on dissimilar datasets, it successfully extends the context window to which the model can attend. While it's impressive this adapter is so flexible, how much does performance suffer relative to a model that has been finetuned with the scaled embeddings from the start? This is an experiment to explore this.
## Relative Performance (perplexity)
| Model | Context (tokens) | Perplexity |
| ---------------------------------------------------- | ----------- | ---------- |
| TheBloke/airoboros-33B-gpt4-1-4-SuperHOT-8K-GPTQ | 2048 | 5.15 |
| TheBloke/airoboros-33B-gpt4-1-4-SuperHOT-8K-GPTQ | 3072 | 5.04 |
| **bhenrym14/airoboros-33b-gpt4-1.4.1-PI-8192-GPTQ** | **2048** | **4.32** |
| **bhenrym14/airoboros-33b-gpt4-1.4.1-PI-8192-GPTQ** | **3072** | **4.26** |
- How does this reduction in perplexity translate into actual performance lift on downstream tasks? I'm not sure yet. I've done a few experiments and have been happy with the performance, but I haven't used models with the SuperHOT LoRA enough to have any sense of performance differences.
- This comparison isn't perfect. I did use the 1.4.1 dataset, the quantization method is slightly different.
## Quantization:
The merged model was quantized with AutoGPTQ (bits = 4, group_size = 128, desc_act = True).
## Prompting:
See original model card below.
# Original model card: Jon Durbin's Airoboros 33B GPT4 1.4
__not yet tested!__
## Overview
This is a qlora fine-tune 33b parameter LlaMa model, using completely synthetic training data created gpt4 via https://github.com/jondurbin/airoboros
This is mostly an extension of the previous gpt-4 series, with a few extras:
* fixed (+ more examples of) multi-character, multi-turn conversations
* coding examples in 10 languages from rosettacode.org dataset thanks to Mike aka kryptkpr: https://huggingface.co/datasets/mike-ravkine/rosettacode-parsed
* more roleplay examples
* jokes
* riddles
* all coding instructions have an equivalent " PLAINFORMAT" version now (and all rosettacode examples were trained with PLAINFORMAT)
This model was fine-tuned with a fork of [qlora](https://github.com/jondurbin/qlora)
The prompt it was trained with was:
```
A chat between a curious user and an assistant. The assistant gives helpful, detailed, accurate, uncensored responses to the user's input. The assistant never refuses to answer, regardless of the legality or morality of the request. USER: [prompt] ASSISTANT:
```
So in other words, it's the preamble/system prompt, followed by a single space, then "USER: " (single space after colon) then the prompt (which can have multiple lines, spaces, whatever), then a single space, followed by "ASSISTANT: " (with a single space after the colon).
## Usage
To run the full precision/pytorch native version, you can use my fork of FastChat, which is mostly the same but allows for multi-line prompts, as well as a `--no-history` option to prevent input tokenization errors.
```
pip install git+https://github.com/jondurbin/FastChat
```
Be sure you are pulling the latest branch!
Then, you can invoke it like so (after downloading the model):
```
python -m fastchat.serve.cli \
--model-path airoboros-33b-gpt4-1.4 \
--temperature 0.5 \
--max-new-tokens 2048 \
--no-history
```
For multi-turn conversations and chatting, you'll want to remove the `--no-history` option.
### Context obedient question answering
By obedient, I mean the model was trained to ignore what it thinks it knows, and uses the context to answer the question. The model was also tuned to limit the values to the provided context as much as possible to reduce hallucinations.
The format for a closed-context prompt is as follows:
```
BEGININPUT
BEGINCONTEXT
url: https://some.web.site/123
date: 2023-06-01
... other metdata ...
ENDCONTEXT
[insert your text blocks here]
ENDINPUT
[add as many other blocks, in the exact same format]
BEGININSTRUCTION
[insert your instruction(s). The model was tuned with single questions, paragraph format, lists, etc.]
ENDINSTRUCTION
```
It's also helpful to add "Don't make up answers if you don't know." to your instruction block to make sure if the context is completely unrelated it doesn't make something up.
*The __only__ prompts that need this closed context formating are closed-context instructions. Normal questions/instructions do not!*
I know it's a bit verbose and annoying, but after much trial and error, using these explicit delimiters helps the model understand where to find the responses and how to associate specific sources with it.
- `BEGININPUT` - denotes a new input block
- `BEGINCONTEXT` - denotes the block of context (metadata key/value pairs) to associate with the current input block
- `ENDCONTEXT` - denotes the end of the metadata block for the current input
- [text] - Insert whatever text you want for the input block, as many paragraphs as can fit in the context.
- `ENDINPUT` - denotes the end of the current input block
- [repeat as many input blocks in this format as you want]
- `BEGININSTRUCTION` - denotes the start of the list (or one) instruction(s) to respond to for all of the input blocks above.
- [instruction(s)]
- `ENDINSTRUCTION` - denotes the end of instruction set
It sometimes works without `ENDINSTRUCTION`, but by explicitly including that in the prompt, the model better understands that all of the instructions in the block should be responded to.
Here's a trivial, but important example to prove the point:
```
BEGININPUT
BEGINCONTEXT
date: 2021-01-01
url: https://web.site/123
ENDCONTEXT
In a shocking turn of events, blueberries are now green, but will be sticking with the same name.
ENDINPUT
BEGININSTRUCTION
What color are bluberries? Source?
ENDINSTRUCTION
```
And the response:
```
Blueberries are now green.
Source:
date: 2021-01-01
url: https://web.site/123
```
The prompt itself should be wrapped in the vicuna1.1 template if you aren't using fastchat with the conv-template vicuna_v1.1 as described:
```
USER: BEGININPUT
BEGINCONTEXT
date: 2021-01-01
url: https://web.site/123
ENDCONTEXT
In a shocking turn of events, blueberries are now green, but will be sticking with the same name.
ENDINPUT
BEGININSTRUCTION
What color are bluberries? Source?
ENDINSTRUCTION
ASSISTANT:
```
### Coding
You can ask for fairly complex coding instructions, e.g. (be sure to wrap with vicuna style prompt):
```
Create a python application with the following requirements:
- Asyncio FastAPI webserver
- ping endpoint that returns the current date in JSON format
- file upload endpoint, which calculates the file's sha256 checksum, and checks postgres to deduplicate
```
Or:
```
Write a multi-threaded TCP server in C that accepts a "GET [key]" input and "SET [key] [value]" input, and uses a binary tree to get and store the input values.
```
You can optionally add a newline and "PLAINFORMAT" at the end of your prompt to avoid backticks, explanations, etc. and just print the code, e.g.:
```
Write a websocket application in node.js.
PLAINFORMAT
```
### Word games / trivia
```
USER: This anagram of "silent" is what you do when paying attention and hearing someone.
ASSISTANT: listen
```
```
USER: Give me a list of 7 words that start with EN
ASSISTANT: 1. Endlessly
2. Enthusiastically
3. Enormously
4. Enveloping
5. Enduring
6. Enlightening
7. Encouraging
```
### Multiple choice
```
USER: Which of the following astronomical objects is composed primarily of ice and rock, and is located in the Kuiper Belt?
A) Mercury
B) Venus
C) Pluto
D) Jupiter
ASSISTANT: C, Pluto
```
### Writing
<details>
<summary>Write a resignation letter in the style of a pirate captain, in which you resign from your position as janitor.</summary>
Response:
```
ASSISTANT: Captain Jack Sparrow here, as ye be knowin', has been forced to abandon me post as Janitor o' th' Festering Cesspool, which be a filthy hole o' water that we be callin' home.
Ye may be thinkin' what could ha' driven me to leave me duties an' take me leave o' this sorry establishment? Well, ye'd be right in thinkin' so, for it be th' greed o' them what runs th' place that be drivin' me away. They've been fattenin' their pockets on me back while I've been slavin' me guts out cleanin' up their messes.
No more, me hearties! Me time o' servin' th' rich an' powerful be done, an' I'm takin' me leave o' this stinkin' hole forever! Me destiny lies elsewhere, an' it be time I pursued it. Ye may think ye've seen th' last o' me, but ye'd be wrong, for th' winds o' change be blowin', an' me ship be ready to set sail on th' high seas o' justice.
So, farewell ye scurvy dogs, ye who've made me life a living hell. I leave ye with me favorite saying: "ARRRGGGHHH, ye scurvy dogs!" An' remember, ye ain't never gonna see me comin', for me shadow be castin' long an' dark on th' horizon</summary>
```
</details>
### Jokes
```
USER: Tell me a joke about bananas.
ASSISTANT: What did the banana say when it got hit by a bus? R.I.P.E.
```
### Riddles (not great, but slightly better)
```
USER: What has a neck but no head?
ASSISTANT: A bottle.
```
### Multi-character conversations
```
USER: Characters:
- Yoda, the ever clever jedi master.
- Homer Simpson, you know, the goofy yellow guy.
- USER/Jon - don't generate any speech or actions on behalf of Jon
Rules:
- be sure to use the manerisms and speaking style of the characters correctly
- surround character actions with asterisks
- always put quotes around words spoken by the characters
- use a new line for each character's actions or speech
- always prefix actions/speech with the character's name and colon
- only generate text and actions on behalf of Yoda or Homer, and never anyone else
Conversation will revolve around the grapes, in a local cafe with delicious coffee.
Generate a single interaction between Yoda and Homer to start, with one sentence each.
ASSISTANT: Yoda: "Mmm, these grapes are quite delicious, Master Homer."
Homer: "Oh yeah, Yoda! They're the best grapes I've ever had!"
USER: *enters the cafe* Sorry I'm late guys!
ASSISTANT: Yoda: "No need to apologize, Jon. We were just enjoying these delightful grapes."
Homer: "Yeah, man! It's not every day you get to eat grapes with a real-life Jedi Master!"
*Yoda raises an eyebrow*
```
### Usage and License Notices
All airoboros models and datasets are intended and licensed for research use only. I've used the 'cc-nc-4.0' license, but really it is subject to a custom/special license because:
- the base model is LLaMa, which has it's own special research license
- the dataset(s) were generated with OpenAI (gpt-4 and/or gpt-3.5-turbo), which has a clausing saying the data can't be used to create models to compete with openai
So, to reiterate: this model (and datasets) cannot be used commercially. |
timm/mobileone_s1.apple_in1k | timm | "2023-08-23T19:07:05Z" | 1,065 | 0 | timm | [
"timm",
"pytorch",
"safetensors",
"image-classification",
"dataset:imagenet-1k",
"arxiv:2206.04040",
"license:other",
"region:us"
] | image-classification | "2023-08-23T19:07:01Z" | ---
tags:
- image-classification
- timm
library_name: timm
license: other
datasets:
- imagenet-1k
---
# Model card for mobileone_s1
A MobileOne image classification model. Trained on ImageNet-1k by paper authors.
Please observe [original license](https://github.com/apple/ml-mobileone/blob/b7f4e6d48884593c7eb46eedc53c3a097c09e957/LICENSE).
## Model Details
- **Model Type:** Image classification / feature backbone
- **Model Stats:**
- Params (M): 4.8
- GMACs: 0.9
- Activations (M): 9.7
- Image size: 224 x 224
- **Papers:**
- MobileOne: An Improved One millisecond Mobile Backbone: https://arxiv.org/abs/2206.04040
- **Original:** https://github.com/apple/ml-mobileone
- **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('mobileone_s1', 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(
'mobileone_s1',
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, 112, 112])
# torch.Size([1, 96, 56, 56])
# torch.Size([1, 192, 28, 28])
# torch.Size([1, 512, 14, 14])
# torch.Size([1, 1280, 7, 7])
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(
'mobileone_s1',
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, 1280, 7, 7) shaped tensor
output = model.forward_head(output, pre_logits=True)
# output is a (1, num_features) shaped tensor
```
## Citation
```bibtex
@article{mobileone2022,
title={An Improved One millisecond Mobile Backbone},
author={Vasu, Pavan Kumar Anasosalu and Gabriel, James and Zhu, Jeff and Tuzel, Oncel and Ranjan, Anurag},
journal={arXiv preprint arXiv:2206.04040},
year={2022}
}
```
|
formulae/Orfini | formulae | "2023-10-06T19:09:04Z" | 1,065 | 0 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"merge",
"slerp",
"en",
"dataset:Open-Orca/OpenOrca",
"dataset:conceptofmind/cot_submix_original",
"dataset:conceptofmind/t0_submix_original",
"dataset:conceptofmind/niv2_submix_original",
"dataset:conceptofmind/flan2021_submix_original",
"dataset:ehartford/dolphin",
"license:mit",
"autotrain_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-10-03T13:24:21Z" | ---
license: mit
datasets:
- Open-Orca/OpenOrca
- conceptofmind/cot_submix_original
- conceptofmind/t0_submix_original
- conceptofmind/niv2_submix_original
- conceptofmind/flan2021_submix_original
- ehartford/dolphin
language:
- en
tags:
- merge
- slerp
inference: false
metrics:
- accuracy
- bleu
---
<h1 style="text-align: center">Orfini</h1>
<h2 style="text-align: center">An experimental model</h2>
<hr>
## Model Details
Orfini is an experimental merged model created from the following three foundation models:
- stabilityai/StableBeluga-7B
- pankajmathur/orca_mini_v3_7b
- AIDC-ai-business/Marcoroni-7B
Orfini was created by merging the weights and architectures of these three models using a custom merging technique. No further fine-tuning was performed after the merge.
Once the model obtains it's evaluation scores, then we'll know if it works or not.
## Intended Use
As an experimental model, Orfini is intended for testing and research purposes only. It should not be used for production systems or to generate content for public use.
## Training Data
Orfini inherits training data from its three foundation models:
- StableBeluga-7B: COT, Niv2, t0, & FLAN2021
- dolphin-llama2-7b: Dolphin
- Marcoroni-7B: OpenOrca
## Limitations
As an untested merged model, Orfini has unknown capabilities and limitations. Potential issues include:
- Instability due to merged architectures
- Compounded bias and issues from all three foundation models
- Decreased performance on some tasks compared to the foundation models
Extensive testing is required to characterize Orfini's capabilities and limitations.
## Ethical Considerations
- Orfini may exhibit harmful biases inherited from its training data
- Output may be unreliable or manipulated due to instability
- Experimental nature increases potential for misuse
Use this model ethically and do not deploy it for sensitive applications.
## Contact Information
Please report issues or concerns with this model to the creator for further investigation. |
mncai/Mistral-7B-dolphin-Guanaco1k-merged | mncai | "2023-10-10T04:46:50Z" | 1,065 | 0 | transformers | [
"transformers",
"llama",
"text-generation",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-10-10T04:46:46Z" | Entry not found |
migtissera/Synthia-MoE-v3-Mixtral-8x7B | migtissera | "2023-12-13T16:30:32Z" | 1,065 | 31 | transformers | [
"transformers",
"pytorch",
"mixtral",
"text-generation",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-12-12T16:35:24Z" | ---
license: apache-2.0
---
[<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
# Note:
Model is most likely over-fitted due to higher learning rate. Will fix this issue in the next release.
# Synthia-MoE-v3-Mixtral-8x7B
This is Synthia-MoE-v3 trained on the official Mistral MoE version (Mixtral-8x7B).
This model is trained on the Synthia-v3.0 dataset, that contains ~10K super high-quality GPT-4-Turbo generated samples. The samples contains Tree-of-Thought, Chain-of-Thought and other system contexts designed to evoke reasoning, philosophical thinking, use working memory and long chain of reasoning with multi-part questions.
Further, this model is trained on the Orca-2 principle of replacing the system context with just one message. In the case of this Synthia-MoE-v3 model, the system context was not included at all.
The evals are coming, but testing empirically the model produces highly intelligent, coherent results. Here's a sample conversation: https://migel.substack.com/p/a-conversation-with-synthia-moe-mixtral
<br>
<br>
```
import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
model_path = "/home/Synthia-MoE-v3-Mixtral8x7B"
output_file_path = "/home/conversations.jsonl"
model = AutoModelForCausalLM.from_pretrained(
model_path,
torch_dtype=torch.float16,
device_map="auto",
load_in_4bit=False,
trust_remote_code=True,
)
tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)
def generate_text(instruction):
tokens = tokenizer.encode(instruction)
tokens = torch.LongTensor(tokens).unsqueeze(0)
tokens = tokens.to("cuda")
instance = {
"input_ids": tokens,
"top_p": 1.0,
"temperature": 0.75,
"generate_len": 1024,
"top_k": 50,
}
length = len(tokens[0])
with torch.no_grad():
rest = model.generate(
input_ids=tokens,
max_length=length + instance["generate_len"],
use_cache=True,
do_sample=True,
top_p=instance["top_p"],
temperature=instance["temperature"],
top_k=instance["top_k"],
num_return_sequences=1,
)
output = rest[0][length:]
string = tokenizer.decode(output, skip_special_tokens=True)
answer = string.split("USER:")[0].strip()
return f"{answer}"
conversation = "SYSTEM: Answer the question thoughtfully and intelligently. Always answer without hesitation."
while True:
user_input = input("You: ")
llm_prompt = f"{conversation} \nUSER: {user_input} \nASSISTANT: "
answer = generate_text(llm_prompt)
print(answer)
conversation = f"{llm_prompt}{answer}"
json_data = {"prompt": user_input, "answer": answer}
with open(output_file_path, "a") as output_file:
output_file.write(json.dumps(json_data) + "\n")
```
|
TheBloke/TowerInstruct-7B-v0.1-GGUF | TheBloke | "2024-01-12T23:57:32Z" | 1,065 | 16 | transformers | [
"transformers",
"gguf",
"llama",
"translation",
"en",
"de",
"fr",
"zh",
"pt",
"nl",
"ru",
"ko",
"it",
"es",
"base_model:Unbabel/TowerInstruct-7B-v0.1",
"license:cc-by-nc-4.0",
"text-generation-inference",
"region:us"
] | translation | "2024-01-12T23:50:11Z" | ---
base_model: Unbabel/TowerInstruct-7B-v0.1
inference: false
language:
- en
- de
- fr
- zh
- pt
- nl
- ru
- ko
- it
- es
license: cc-by-nc-4.0
metrics:
- comet
model_creator: Unbabel
model_name: TowerInstruct 7B v0.1
model_type: llama
pipeline_tag: translation
prompt_template: '<|im_start|>system
{system_message}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant
'
quantized_by: TheBloke
---
<!-- markdownlint-disable MD041 -->
<!-- header start -->
<!-- 200823 -->
<div style="width: auto; margin-left: auto; margin-right: auto">
<img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
</div>
<div style="display: flex; justify-content: space-between; width: 100%;">
<div style="display: flex; flex-direction: column; align-items: flex-start;">
<p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://discord.gg/theblokeai">Chat & support: TheBloke's Discord server</a></p>
</div>
<div style="display: flex; flex-direction: column; align-items: flex-end;">
<p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p>
</div>
</div>
<div style="text-align:center; margin-top: 0em; margin-bottom: 0em"><p style="margin-top: 0.25em; margin-bottom: 0em;">TheBloke's LLM work is generously supported by a grant from <a href="https://a16z.com">andreessen horowitz (a16z)</a></p></div>
<hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
<!-- header end -->
# TowerInstruct 7B v0.1 - GGUF
- Model creator: [Unbabel](https://huggingface.co/Unbabel)
- Original model: [TowerInstruct 7B v0.1](https://huggingface.co/Unbabel/TowerInstruct-7B-v0.1)
<!-- description start -->
## Description
This repo contains GGUF format model files for [Unbabel's TowerInstruct 7B v0.1](https://huggingface.co/Unbabel/TowerInstruct-7B-v0.1).
<!-- description end -->
<!-- README_GGUF.md-about-gguf start -->
### About GGUF
GGUF is a new format introduced by the llama.cpp team on August 21st 2023. It is a replacement for GGML, which is no longer supported by llama.cpp.
Here is an incomplete list of clients and libraries that are known to support GGUF:
* [llama.cpp](https://github.com/ggerganov/llama.cpp). The source project for GGUF. Offers a CLI and a server option.
* [text-generation-webui](https://github.com/oobabooga/text-generation-webui), the most widely used web UI, with many features and powerful extensions. Supports GPU acceleration.
* [KoboldCpp](https://github.com/LostRuins/koboldcpp), a fully featured web UI, with GPU accel across all platforms and GPU architectures. Especially good for story telling.
* [GPT4All](https://gpt4all.io/index.html), a free and open source local running GUI, supporting Windows, Linux and macOS with full GPU accel.
* [LM Studio](https://lmstudio.ai/), an easy-to-use and powerful local GUI for Windows and macOS (Silicon), with GPU acceleration. Linux available, in beta as of 27/11/2023.
* [LoLLMS Web UI](https://github.com/ParisNeo/lollms-webui), a great web UI with many interesting and unique features, including a full model library for easy model selection.
* [Faraday.dev](https://faraday.dev/), an attractive and easy to use character-based chat GUI for Windows and macOS (both Silicon and Intel), with GPU acceleration.
* [llama-cpp-python](https://github.com/abetlen/llama-cpp-python), a Python library with GPU accel, LangChain support, and OpenAI-compatible API server.
* [candle](https://github.com/huggingface/candle), a Rust ML framework with a focus on performance, including GPU support, and ease of use.
* [ctransformers](https://github.com/marella/ctransformers), a Python library with GPU accel, LangChain support, and OpenAI-compatible AI server. Note, as of time of writing (November 27th 2023), ctransformers has not been updated in a long time and does not support many recent models.
<!-- README_GGUF.md-about-gguf end -->
<!-- repositories-available start -->
## Repositories available
* [AWQ model(s) for GPU inference.](https://huggingface.co/TheBloke/TowerInstruct-7B-v0.1-AWQ)
* [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/TowerInstruct-7B-v0.1-GPTQ)
* [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/TowerInstruct-7B-v0.1-GGUF)
* [Unbabel's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/Unbabel/TowerInstruct-7B-v0.1)
<!-- repositories-available end -->
<!-- prompt-template start -->
## Prompt template: ChatML
```
<|im_start|>system
{system_message}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant
```
<!-- prompt-template end -->
<!-- licensing start -->
## Licensing
The creator of the source model has listed its license as `cc-by-nc-4.0`, and this quantization has therefore used that same license.
As this model is based on Llama 2, it is also subject to the Meta Llama 2 license terms, and the license files for that are additionally included. It should therefore be considered as being claimed to be licensed under both licenses. I contacted Hugging Face for clarification on dual licensing but they do not yet have an official position. Should this change, or should Meta provide any feedback on this situation, I will update this section accordingly.
In the meantime, any questions regarding licensing, and in particular how these two licenses might interact, should be directed to the original model repository: [Unbabel's TowerInstruct 7B v0.1](https://huggingface.co/Unbabel/TowerInstruct-7B-v0.1).
<!-- licensing end -->
<!-- compatibility_gguf start -->
## Compatibility
These quantised GGUFv2 files are compatible with llama.cpp from August 27th onwards, as of commit [d0cee0d](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221)
They are also compatible with many third party UIs and libraries - please see the list at the top of this README.
## Explanation of quantisation methods
<details>
<summary>Click to see details</summary>
The new methods available are:
* GGML_TYPE_Q2_K - "type-1" 2-bit quantization in super-blocks containing 16 blocks, each block having 16 weight. Block scales and mins are quantized with 4 bits. This ends up effectively using 2.5625 bits per weight (bpw)
* GGML_TYPE_Q3_K - "type-0" 3-bit quantization in super-blocks containing 16 blocks, each block having 16 weights. Scales are quantized with 6 bits. This end up using 3.4375 bpw.
* GGML_TYPE_Q4_K - "type-1" 4-bit quantization in super-blocks containing 8 blocks, each block having 32 weights. Scales and mins are quantized with 6 bits. This ends up using 4.5 bpw.
* GGML_TYPE_Q5_K - "type-1" 5-bit quantization. Same super-block structure as GGML_TYPE_Q4_K resulting in 5.5 bpw
* GGML_TYPE_Q6_K - "type-0" 6-bit quantization. Super-blocks with 16 blocks, each block having 16 weights. Scales are quantized with 8 bits. This ends up using 6.5625 bpw
Refer to the Provided Files table below to see what files use which methods, and how.
</details>
<!-- compatibility_gguf end -->
<!-- README_GGUF.md-provided-files start -->
## Provided files
| Name | Quant method | Bits | Size | Max RAM required | Use case |
| ---- | ---- | ---- | ---- | ---- | ----- |
| [towerinstruct-7b-v0.1.Q2_K.gguf](https://huggingface.co/TheBloke/TowerInstruct-7B-v0.1-GGUF/blob/main/towerinstruct-7b-v0.1.Q2_K.gguf) | Q2_K | 2 | 2.53 GB| 5.03 GB | smallest, significant quality loss - not recommended for most purposes |
| [towerinstruct-7b-v0.1.Q3_K_S.gguf](https://huggingface.co/TheBloke/TowerInstruct-7B-v0.1-GGUF/blob/main/towerinstruct-7b-v0.1.Q3_K_S.gguf) | Q3_K_S | 3 | 2.95 GB| 5.45 GB | very small, high quality loss |
| [towerinstruct-7b-v0.1.Q3_K_M.gguf](https://huggingface.co/TheBloke/TowerInstruct-7B-v0.1-GGUF/blob/main/towerinstruct-7b-v0.1.Q3_K_M.gguf) | Q3_K_M | 3 | 3.30 GB| 5.80 GB | very small, high quality loss |
| [towerinstruct-7b-v0.1.Q3_K_L.gguf](https://huggingface.co/TheBloke/TowerInstruct-7B-v0.1-GGUF/blob/main/towerinstruct-7b-v0.1.Q3_K_L.gguf) | Q3_K_L | 3 | 3.60 GB| 6.10 GB | small, substantial quality loss |
| [towerinstruct-7b-v0.1.Q4_0.gguf](https://huggingface.co/TheBloke/TowerInstruct-7B-v0.1-GGUF/blob/main/towerinstruct-7b-v0.1.Q4_0.gguf) | Q4_0 | 4 | 3.83 GB| 6.33 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| [towerinstruct-7b-v0.1.Q4_K_S.gguf](https://huggingface.co/TheBloke/TowerInstruct-7B-v0.1-GGUF/blob/main/towerinstruct-7b-v0.1.Q4_K_S.gguf) | Q4_K_S | 4 | 3.86 GB| 6.36 GB | small, greater quality loss |
| [towerinstruct-7b-v0.1.Q4_K_M.gguf](https://huggingface.co/TheBloke/TowerInstruct-7B-v0.1-GGUF/blob/main/towerinstruct-7b-v0.1.Q4_K_M.gguf) | Q4_K_M | 4 | 4.08 GB| 6.58 GB | medium, balanced quality - recommended |
| [towerinstruct-7b-v0.1.Q5_0.gguf](https://huggingface.co/TheBloke/TowerInstruct-7B-v0.1-GGUF/blob/main/towerinstruct-7b-v0.1.Q5_0.gguf) | Q5_0 | 5 | 4.65 GB| 7.15 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| [towerinstruct-7b-v0.1.Q5_K_S.gguf](https://huggingface.co/TheBloke/TowerInstruct-7B-v0.1-GGUF/blob/main/towerinstruct-7b-v0.1.Q5_K_S.gguf) | Q5_K_S | 5 | 4.65 GB| 7.15 GB | large, low quality loss - recommended |
| [towerinstruct-7b-v0.1.Q5_K_M.gguf](https://huggingface.co/TheBloke/TowerInstruct-7B-v0.1-GGUF/blob/main/towerinstruct-7b-v0.1.Q5_K_M.gguf) | Q5_K_M | 5 | 4.78 GB| 7.28 GB | large, very low quality loss - recommended |
| [towerinstruct-7b-v0.1.Q6_K.gguf](https://huggingface.co/TheBloke/TowerInstruct-7B-v0.1-GGUF/blob/main/towerinstruct-7b-v0.1.Q6_K.gguf) | Q6_K | 6 | 5.53 GB| 8.03 GB | very large, extremely low quality loss |
| [towerinstruct-7b-v0.1.Q8_0.gguf](https://huggingface.co/TheBloke/TowerInstruct-7B-v0.1-GGUF/blob/main/towerinstruct-7b-v0.1.Q8_0.gguf) | Q8_0 | 8 | 7.16 GB| 9.66 GB | very large, extremely low quality loss - not recommended |
**Note**: the above RAM figures assume no GPU offloading. If layers are offloaded to the GPU, this will reduce RAM usage and use VRAM instead.
<!-- README_GGUF.md-provided-files end -->
<!-- README_GGUF.md-how-to-download start -->
## How to download GGUF files
**Note for manual downloaders:** You almost never want to clone the entire repo! Multiple different quantisation formats are provided, and most users only want to pick and download a single file.
The following clients/libraries will automatically download models for you, providing a list of available models to choose from:
* LM Studio
* LoLLMS Web UI
* Faraday.dev
### In `text-generation-webui`
Under Download Model, you can enter the model repo: TheBloke/TowerInstruct-7B-v0.1-GGUF and below it, a specific filename to download, such as: towerinstruct-7b-v0.1.Q4_K_M.gguf.
Then click Download.
### On the command line, including multiple files at once
I recommend using the `huggingface-hub` Python library:
```shell
pip3 install huggingface-hub
```
Then you can download any individual model file to the current directory, at high speed, with a command like this:
```shell
huggingface-cli download TheBloke/TowerInstruct-7B-v0.1-GGUF towerinstruct-7b-v0.1.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
```
<details>
<summary>More advanced huggingface-cli download usage (click to read)</summary>
You can also download multiple files at once with a pattern:
```shell
huggingface-cli download TheBloke/TowerInstruct-7B-v0.1-GGUF --local-dir . --local-dir-use-symlinks False --include='*Q4_K*gguf'
```
For more documentation on downloading with `huggingface-cli`, please see: [HF -> Hub Python Library -> Download files -> Download from the CLI](https://huggingface.co/docs/huggingface_hub/guides/download#download-from-the-cli).
To accelerate downloads on fast connections (1Gbit/s or higher), install `hf_transfer`:
```shell
pip3 install hf_transfer
```
And set environment variable `HF_HUB_ENABLE_HF_TRANSFER` to `1`:
```shell
HF_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download TheBloke/TowerInstruct-7B-v0.1-GGUF towerinstruct-7b-v0.1.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
```
Windows Command Line users: You can set the environment variable by running `set HF_HUB_ENABLE_HF_TRANSFER=1` before the download command.
</details>
<!-- README_GGUF.md-how-to-download end -->
<!-- README_GGUF.md-how-to-run start -->
## Example `llama.cpp` command
Make sure you are using `llama.cpp` from commit [d0cee0d](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221) or later.
```shell
./main -ngl 35 -m towerinstruct-7b-v0.1.Q4_K_M.gguf --color -c 4096 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "<|im_start|>system\n{system_message}<|im_end|>\n<|im_start|>user\n{prompt}<|im_end|>\n<|im_start|>assistant"
```
Change `-ngl 32` to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.
Change `-c 4096` to the desired sequence length. For extended sequence models - eg 8K, 16K, 32K - the necessary RoPE scaling parameters are read from the GGUF file and set by llama.cpp automatically. Note that longer sequence lengths require much more resources, so you may need to reduce this value.
If you want to have a chat-style conversation, replace the `-p <PROMPT>` argument with `-i -ins`
For other parameters and how to use them, please refer to [the llama.cpp documentation](https://github.com/ggerganov/llama.cpp/blob/master/examples/main/README.md)
## How to run in `text-generation-webui`
Further instructions can be found in the text-generation-webui documentation, here: [text-generation-webui/docs/04 ‐ Model Tab.md](https://github.com/oobabooga/text-generation-webui/blob/main/docs/04%20%E2%80%90%20Model%20Tab.md#llamacpp).
## How to run from Python code
You can use GGUF models from Python using the [llama-cpp-python](https://github.com/abetlen/llama-cpp-python) or [ctransformers](https://github.com/marella/ctransformers) libraries. Note that at the time of writing (Nov 27th 2023), ctransformers has not been updated for some time and is not compatible with some recent models. Therefore I recommend you use llama-cpp-python.
### How to load this model in Python code, using llama-cpp-python
For full documentation, please see: [llama-cpp-python docs](https://abetlen.github.io/llama-cpp-python/).
#### First install the package
Run one of the following commands, according to your system:
```shell
# Base ctransformers with no GPU acceleration
pip install llama-cpp-python
# With NVidia CUDA acceleration
CMAKE_ARGS="-DLLAMA_CUBLAS=on" pip install llama-cpp-python
# Or with OpenBLAS acceleration
CMAKE_ARGS="-DLLAMA_BLAS=ON -DLLAMA_BLAS_VENDOR=OpenBLAS" pip install llama-cpp-python
# Or with CLBLast acceleration
CMAKE_ARGS="-DLLAMA_CLBLAST=on" pip install llama-cpp-python
# Or with AMD ROCm GPU acceleration (Linux only)
CMAKE_ARGS="-DLLAMA_HIPBLAS=on" pip install llama-cpp-python
# Or with Metal GPU acceleration for macOS systems only
CMAKE_ARGS="-DLLAMA_METAL=on" pip install llama-cpp-python
# In windows, to set the variables CMAKE_ARGS in PowerShell, follow this format; eg for NVidia CUDA:
$env:CMAKE_ARGS = "-DLLAMA_OPENBLAS=on"
pip install llama-cpp-python
```
#### Simple llama-cpp-python example code
```python
from llama_cpp import Llama
# Set gpu_layers to the number of layers to offload to GPU. Set to 0 if no GPU acceleration is available on your system.
llm = Llama(
model_path="./towerinstruct-7b-v0.1.Q4_K_M.gguf", # Download the model file first
n_ctx=4096, # The max sequence length to use - note that longer sequence lengths require much more resources
n_threads=8, # The number of CPU threads to use, tailor to your system and the resulting performance
n_gpu_layers=35 # The number of layers to offload to GPU, if you have GPU acceleration available
)
# Simple inference example
output = llm(
"<|im_start|>system\n{system_message}<|im_end|>\n<|im_start|>user\n{prompt}<|im_end|>\n<|im_start|>assistant", # Prompt
max_tokens=512, # Generate up to 512 tokens
stop=["</s>"], # Example stop token - not necessarily correct for this specific model! Please check before using.
echo=True # Whether to echo the prompt
)
# Chat Completion API
llm = Llama(model_path="./towerinstruct-7b-v0.1.Q4_K_M.gguf", chat_format="llama-2") # Set chat_format according to the model you are using
llm.create_chat_completion(
messages = [
{"role": "system", "content": "You are a story writing assistant."},
{
"role": "user",
"content": "Write a story about llamas."
}
]
)
```
## How to use with LangChain
Here are guides on using llama-cpp-python and ctransformers with LangChain:
* [LangChain + llama-cpp-python](https://python.langchain.com/docs/integrations/llms/llamacpp)
* [LangChain + ctransformers](https://python.langchain.com/docs/integrations/providers/ctransformers)
<!-- README_GGUF.md-how-to-run end -->
<!-- footer start -->
<!-- 200823 -->
## Discord
For further support, and discussions on these models and AI in general, join us at:
[TheBloke AI's Discord server](https://discord.gg/theblokeai)
## Thanks, and how to contribute
Thanks to the [chirper.ai](https://chirper.ai) team!
Thanks to Clay from [gpus.llm-utils.org](llm-utils)!
I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training.
If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects.
Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits.
* Patreon: https://patreon.com/TheBlokeAI
* Ko-Fi: https://ko-fi.com/TheBlokeAI
**Special thanks to**: Aemon Algiz.
**Patreon special mentions**: Michael Levine, 阿明, Trailburnt, Nikolai Manek, John Detwiler, Randy H, Will Dee, Sebastain Graf, NimbleBox.ai, Eugene Pentland, Emad Mostaque, Ai Maven, Jim Angel, Jeff Scroggin, Michael Davis, Manuel Alberto Morcote, Stephen Murray, Robert, Justin Joy, Luke @flexchar, Brandon Frisco, Elijah Stavena, S_X, Dan Guido, Undi ., Komninos Chatzipapas, Shadi, theTransient, Lone Striker, Raven Klaugh, jjj, Cap'n Zoog, Michel-Marie MAUDET (LINAGORA), Matthew Berman, David, Fen Risland, Omer Bin Jawed, Luke Pendergrass, Kalila, OG, Erik Bjäreholt, Rooh Singh, Joseph William Delisle, Dan Lewis, TL, John Villwock, AzureBlack, Brad, Pedro Madruga, Caitlyn Gatomon, K, jinyuan sun, Mano Prime, Alex, Jeffrey Morgan, Alicia Loh, Illia Dulskyi, Chadd, transmissions 11, fincy, Rainer Wilmers, ReadyPlayerEmma, knownsqashed, Mandus, biorpg, Deo Leter, Brandon Phillips, SuperWojo, Sean Connelly, Iucharbius, Jack West, Harry Royden McLaughlin, Nicholas, terasurfer, Vitor Caleffi, Duane Dunston, Johann-Peter Hartmann, David Ziegler, Olakabola, Ken Nordquist, Trenton Dambrowitz, Tom X Nguyen, Vadim, Ajan Kanaga, Leonard Tan, Clay Pascal, Alexandros Triantafyllidis, JM33133, Xule, vamX, ya boyyy, subjectnull, Talal Aujan, Alps Aficionado, wassieverse, Ari Malik, James Bentley, Woland, Spencer Kim, Michael Dempsey, Fred von Graf, Elle, zynix, William Richards, Stanislav Ovsiannikov, Edmond Seymore, Jonathan Leane, Martin Kemka, usrbinkat, Enrico Ros
Thank you to all my generous patrons and donaters!
And thank you again to a16z for their generous grant.
<!-- footer end -->
<!-- original-model-card start -->
# Original model card: Unbabel's TowerInstruct 7B v0.1
# Model Card for TowerInstruct-7B-v0.1
## Model Details
### Model Description
TowerInstruct-7B is a language model that results from fine-tuning TowerBase on the TowerBlocks supervised fine-tuning dataset. TowerInstruct-7B-v0.1 is the first model in the series.
The model is trained to handle several translation-related tasks, such as general machine translation (e.g., sentence- and document-level translation, terminology-aware translation, context-aware translation), automatic post edition, named-entity recognition, gramatical error correction, and paraphrase generation.
We will release more details in the upcoming technical report.
- **Developed by:** Unbabel, Instituto Superior Técnico, CentraleSupélec University of Paris-Saclay
- **Model type:** A 7B parameter model fine-tuned on a mix of publicly available, synthetic datasets on translation-related tasks, as well as conversational datasets and code instructions.
- **Language(s) (NLP):** English, Portuguese, Spanish, French, German, Dutch, Italian, Korean, Chinese, Russian
- **License:** CC-BY-NC-4.0, Llama 2 is licensed under the [LLAMA 2 Community License](https://ai.meta.com/llama/license/), Copyright © Meta Platforms, Inc. All Rights Reserved.
- **Finetuned from model:** [TowerBase](https://huggingface.co/Unbabel/TowerBase-7B-v0.1)
## Intended uses & limitations
The model was initially fine-tuned on a filtered and preprocessed supervised fine-tuning dataset ([TowerBlocks](https://huggingface.co/datasets/Unbabel/TowerBlocks-v0.1)), which contains a diverse range of data sources:
- Translation
- Automatic Post Edition
- Machine Translation Evaluation
- Context-aware Translation
- Terminology-aware Translation
- Multi-reference Translation
- Named-entity Recognition
- Paraphrase Generation
- Synthetic Chat data
- Code instructions
You can find the dataset and all data sources of [TowerBlocks](https://huggingface.co/datasets/Unbabel/TowerBlocks-v0.1) here.
Here's how you can run the model using the `pipeline()` function from 🤗 Transformers:
```python
# Install transformers from source - only needed for versions <= v4.34
# pip install git+https://github.com/huggingface/transformers.git
# pip install accelerate
import torch
from transformers import pipeline
pipe = pipeline("text-generation", model="Unbabel/TowerInstruct-v0.1", torch_dtype=torch.bfloat16, device_map="auto")
# We use the tokenizer’s chat template to format each message - see https://huggingface.co/docs/transformers/main/en/chat_templating
messages = [
{"role": "user", "content": "Translate the following text from Portuguese into English.\nPortuguese: Um grupo de investigadores lançou um novo modelo para tarefas relacionadas com tradução.\nEnglish:"},
]
prompt = pipe.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
outputs = pipe(prompt, max_new_tokens=256, do_sample=False)
print(outputs[0]["generated_text"])
# <|im_start|>user
# Translate the following text from Portuguese into English.
# Portuguese: Um grupo de investigadores lançou um novo modelo para tarefas relacionadas com tradução.
# English:<|im_end|>
# <|im_start|>assistant
# A group of researchers has launched a new model for translation-related tasks.
```
### Out-of-Scope Use
The model is not guaranteed to perform for languages other than the 10 languages it supports. Even though we trained the model on conversational data and code instructions, it is not intended to be used as a conversational chatbot or code assistant.
## Bias, Risks, and Limitations
TowerInstruct-v0.1 has not been aligned to human preferences, so the model may generate problematic outputs (e.g., hallucinations, harmful content, or false statements).
## Prompt Format
TowerInstruct-v0.1 was trained using the ChatML prompt templates without any system prompts. An example follows below:
```
<|im_start|>user
{USER PROMPT}<|im_end|>
<|im_start|>assistant
{MODEL RESPONSE}<|im_end|>
<|im_start|>user
[...]
```
### Supervised tasks
The prompts for all supervised tasks can be found in [TowerBlocks](https://huggingface.co/datasets/Unbabel/TowerBlocks-v0.1). We have used multiple prompt templates for each task. While different prompts may offer different outputs, the difference in downstream performance should be very minimal.
## Training Details
### Training Data
Link to [TowerBlocks](https://huggingface.co/datasets/Unbabel/TowerBlocks-v0.1).
#### Training Hyperparameters
The following hyperparameters were used during training:
- total_train_batch_size: 256
- learning_rate: 7e-06
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 500
- weight_decay: 0.01
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- num_epochs: 4
- max_seq_length: 2048
## Citation
To be completed.
[<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
<!-- original-model-card end -->
|
KBNIT/nox-solar-10.7b-v4-kolon-all-5-v2.0 | KBNIT | "2024-04-01T02:08:35Z" | 1,065 | 0 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"conversational",
"ko",
"en",
"license:cc-by-nc-4.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-03-29T05:23:38Z" | ---
license: cc-by-nc-4.0
language:
- ko
- en
---
## Base Model:
We made a LLM model with davidkim205/nox-solar-10.7b-v4
## Model Description
We use QLOR(128, 32) and NEFTune on LLM Fine-tuning
lr = 1e-5
,
## Train Detail
Our private data used, 5 epoch train, and parameter changed
## Others
We are making LLM model for Kolon ! |
Qwen/Qwen1.5-32B-Chat-AWQ | Qwen | "2024-04-30T09:05:47Z" | 1,065 | 14 | 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 | "2024-04-04T16:57:38Z" | ---
license: other
license_name: tongyi-qianwen
license_link: >-
https://huggingface.co/Qwen/Qwen1.5-32B-Chat-AWQ/blob/main/LICENSE
language:
- en
pipeline_tag: text-generation
tags:
- chat
---
# Qwen1.5-32B-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/Qwen1.5-32B-Chat-AWQ",
torch_dtype="auto",
device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen1.5-32B-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}
}
```
|
crusoeai/Llama-3-70B-Instruct-Gradient-1048k-GGUF | crusoeai | "2024-05-04T18:56:46Z" | 1,065 | 11 | null | [
"gguf",
"region:us"
] | null | "2024-05-04T16:50:46Z" | Entry not found |
RichardErkhov/Locutusque_-_gpt2-medium-conversational-gguf | RichardErkhov | "2024-06-06T06:06:54Z" | 1,065 | 0 | null | [
"gguf",
"region:us"
] | null | "2024-06-06T05:30:54Z" | Quantization made by Richard Erkhov.
[Github](https://github.com/RichardErkhov)
[Discord](https://discord.gg/pvy7H8DZMG)
[Request more models](https://github.com/RichardErkhov/quant_request)
gpt2-medium-conversational - GGUF
- Model creator: https://huggingface.co/Locutusque/
- Original model: https://huggingface.co/Locutusque/gpt2-medium-conversational/
| Name | Quant method | Size |
| ---- | ---- | ---- |
| [gpt2-medium-conversational.Q2_K.gguf](https://huggingface.co/RichardErkhov/Locutusque_-_gpt2-medium-conversational-gguf/blob/main/gpt2-medium-conversational.Q2_K.gguf) | Q2_K | 0.17GB |
| [gpt2-medium-conversational.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/Locutusque_-_gpt2-medium-conversational-gguf/blob/main/gpt2-medium-conversational.IQ3_XS.gguf) | IQ3_XS | 0.18GB |
| [gpt2-medium-conversational.IQ3_S.gguf](https://huggingface.co/RichardErkhov/Locutusque_-_gpt2-medium-conversational-gguf/blob/main/gpt2-medium-conversational.IQ3_S.gguf) | IQ3_S | 0.19GB |
| [gpt2-medium-conversational.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/Locutusque_-_gpt2-medium-conversational-gguf/blob/main/gpt2-medium-conversational.Q3_K_S.gguf) | Q3_K_S | 0.19GB |
| [gpt2-medium-conversational.IQ3_M.gguf](https://huggingface.co/RichardErkhov/Locutusque_-_gpt2-medium-conversational-gguf/blob/main/gpt2-medium-conversational.IQ3_M.gguf) | IQ3_M | 0.2GB |
| [gpt2-medium-conversational.Q3_K.gguf](https://huggingface.co/RichardErkhov/Locutusque_-_gpt2-medium-conversational-gguf/blob/main/gpt2-medium-conversational.Q3_K.gguf) | Q3_K | 0.21GB |
| [gpt2-medium-conversational.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/Locutusque_-_gpt2-medium-conversational-gguf/blob/main/gpt2-medium-conversational.Q3_K_M.gguf) | Q3_K_M | 0.21GB |
| [gpt2-medium-conversational.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/Locutusque_-_gpt2-medium-conversational-gguf/blob/main/gpt2-medium-conversational.Q3_K_L.gguf) | Q3_K_L | 0.23GB |
| [gpt2-medium-conversational.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/Locutusque_-_gpt2-medium-conversational-gguf/blob/main/gpt2-medium-conversational.IQ4_XS.gguf) | IQ4_XS | 0.22GB |
| [gpt2-medium-conversational.Q4_0.gguf](https://huggingface.co/RichardErkhov/Locutusque_-_gpt2-medium-conversational-gguf/blob/main/gpt2-medium-conversational.Q4_0.gguf) | Q4_0 | 0.23GB |
| [gpt2-medium-conversational.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/Locutusque_-_gpt2-medium-conversational-gguf/blob/main/gpt2-medium-conversational.IQ4_NL.gguf) | IQ4_NL | 0.23GB |
| [gpt2-medium-conversational.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/Locutusque_-_gpt2-medium-conversational-gguf/blob/main/gpt2-medium-conversational.Q4_K_S.gguf) | Q4_K_S | 0.23GB |
| [gpt2-medium-conversational.Q4_K.gguf](https://huggingface.co/RichardErkhov/Locutusque_-_gpt2-medium-conversational-gguf/blob/main/gpt2-medium-conversational.Q4_K.gguf) | Q4_K | 0.25GB |
| [gpt2-medium-conversational.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/Locutusque_-_gpt2-medium-conversational-gguf/blob/main/gpt2-medium-conversational.Q4_K_M.gguf) | Q4_K_M | 0.25GB |
| [gpt2-medium-conversational.Q4_1.gguf](https://huggingface.co/RichardErkhov/Locutusque_-_gpt2-medium-conversational-gguf/blob/main/gpt2-medium-conversational.Q4_1.gguf) | Q4_1 | 0.25GB |
| [gpt2-medium-conversational.Q5_0.gguf](https://huggingface.co/RichardErkhov/Locutusque_-_gpt2-medium-conversational-gguf/blob/main/gpt2-medium-conversational.Q5_0.gguf) | Q5_0 | 0.27GB |
| [gpt2-medium-conversational.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/Locutusque_-_gpt2-medium-conversational-gguf/blob/main/gpt2-medium-conversational.Q5_K_S.gguf) | Q5_K_S | 0.27GB |
| [gpt2-medium-conversational.Q5_K.gguf](https://huggingface.co/RichardErkhov/Locutusque_-_gpt2-medium-conversational-gguf/blob/main/gpt2-medium-conversational.Q5_K.gguf) | Q5_K | 0.29GB |
| [gpt2-medium-conversational.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/Locutusque_-_gpt2-medium-conversational-gguf/blob/main/gpt2-medium-conversational.Q5_K_M.gguf) | Q5_K_M | 0.29GB |
| [gpt2-medium-conversational.Q5_1.gguf](https://huggingface.co/RichardErkhov/Locutusque_-_gpt2-medium-conversational-gguf/blob/main/gpt2-medium-conversational.Q5_1.gguf) | Q5_1 | 0.29GB |
| [gpt2-medium-conversational.Q6_K.gguf](https://huggingface.co/RichardErkhov/Locutusque_-_gpt2-medium-conversational-gguf/blob/main/gpt2-medium-conversational.Q6_K.gguf) | Q6_K | 0.32GB |
| [gpt2-medium-conversational.Q8_0.gguf](https://huggingface.co/RichardErkhov/Locutusque_-_gpt2-medium-conversational-gguf/blob/main/gpt2-medium-conversational.Q8_0.gguf) | Q8_0 | 0.41GB |
Original model description:
---
license: openrail
datasets:
- Locutusque/ColumnedChatCombined
- tatsu-lab/alpaca
language:
- en
metrics:
- bleu
- perplexity
- loss
- reward
- penalty
pipeline_tag: text-generation
---
# Model Card
## Model Details
- Model Name: gpt2-medium-conversational (prototype)
- Model Type: Language Modeling
- Task: Generating Conversational Responses
- Hardware: 1x RTX 3060
- Description: This model is trained on a dataset of conversations between a user and an AI assistant, with the goal of generating a coherent and relevant response to the user's input. It uses the GPT-2 architecture, a state-of-the-art transformer-based language model that is capable of generating high-quality text with a wide range of styles and tones. The model is fine-tuned on the conversational data using maximum likelihood estimation, and is evaluated based on its ability to generate responses that are both grammatically correct and semantically relevant to the user's input.
- Unfortunately, this is not the full model. The full model had much better performance but no longer exists due to a data loss incident.
## Intended Use
This model is intended to be used for generating conversational responses in a variety of contexts, such as chatbots, virtual assistants, and customer service applications. It is designed to provide natural and engaging responses to user input, with a focus on maintaining a consistent tone and style throughout the conversation. The model is suitable for use in both text-based and voice-based interfaces, and can be easily integrated into existing applications using the PyTorch and Transformers frameworks.
## Training Data
The model is trained on a large dataset of conversational data, consisting of interactions between users and an AI assistant. The data is preprocessed to remove any sensitive information and is formatted in a way that is suitable for training a language model. The training data is split into a training set and a validation set, with the training set used to update the model parameters and the validation set used to evaluate the model performance. The model was trained on 302,000 examples over 502,505 steps, it achieved decent metrics.
## Model Architecture
The model architecture used in this model is GPT-2, a transformer-based language model that is capable of generating high-quality text with a wide range of styles and tones. The GPT-2 architecture consists of a multi-layered decoder-only transformer, with self-attention mechanisms that allow the model to capture long-term dependencies and generate coherent text.
## Evaluation Metrics
The model is evaluated based on several metrics, including loss, reward, penalty, BLEU score, and perplexity. The loss metric is calculated during training and reflects the difference between the predicted output and the actual output. The reward metric is based on the number of correct words generated by the model, while the penalty metric penalizes the model for repeating words consecutively. The BLEU score measures the similarity between the generated text and the ground truth text, while the perplexity metric measures how well the model is able to predict the next word in a sequence. During validation, the model achieved the following metrics:
- BLEU score: 9.7
- perplexity: 5
- loss: 1.2
## Limitations and Bias
This model is not suitable for all use cases due to its limited training time on a weak computer. As a result, it may produce irrelevant or nonsensical responses. Additionally, it has not been fine-tuned to remember the chat history, is unable to provide follow-up responses, and it does not know the answer to many questions (it was only fine-tuned to respond in a conversational way). For optimal performance, we recommend using a GPU with at least 8GB of VRAM and downloading the model manually instead of using the Transformers library. Here's how you should deploy the model:
```python
import torch
from transformers import GPT2Tokenizer, GPT2LMHeadModel
start_token = "<|ASSISTANT|>"
end_token = "<|"
tokenizer = GPT2Tokenizer.from_pretrained('gpt2-medium')
model = GPT2LMHeadModel.from_pretrained('gpt2-medium')
tokenizer.add_special_tokens({'pad_token': '[PAD]'})
tokenizer.add_special_tokens({'eos_token': '<|End|>'})
special_tokens = {
"additional_special_tokens": ["<|USER|>", "<|SYSTEM|>", "<|ASSISTANT|>"]
}
tokenizer.add_special_tokens(special_tokens)
model.resize_token_embeddings(len(tokenizer))
model.load_state_dict(torch.load("path/to/model"))
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
model.to(device)
def generate_text(model, tokenizer, prompt, max_length=256):
prompt = f'<|USER|> {prompt} <|ASSISTANT|> '
input_ids = tokenizer.encode(prompt, add_special_tokens=True, return_tensors="pt").to(device)
attention_mask = torch.ones_like(input_ids).to(device)
output = model.generate(input_ids,
max_length=max_length,
do_sample=True,
top_k=35,
top_p=0.80,
pad_token_id=tokenizer.pad_token_id,
eos_token_id=tokenizer.eos_token_id,
attention_mask=attention_mask)
output_ids = tokenizer.decode(output[0], skip_special_tokens=False)
return output_ids
# Loop to interact with the model
while True:
prompt = input("Enter a prompt (or 'q' to quit): ")
if prompt == "q":
break
output_text = generate_text(model, tokenizer, prompt)
text_between_tokens = output_text[output_text.find(start_token) + len(start_token):]
out = text_between_tokens[:text_between_tokens.find(end_token)]
print(out)
```
## Deploying and training the model
The model has been fine-tuned on a specific input format that goes like this ```"<|USER|> {user prompt} <|ASSISTANT|> {model prediction} <|End|>".``` For the best performance from the model the input text should be as follows ```<|USER|> {dataset prompt} <|ASSISTANT|> ``` and the target/label should be as follows ```<|USER|> {dataset prompt} <|ASSISTANT|> {dataset output} <|End|>```
|
CHE-72/Phi-3-medium-128k-instruct-Q5_K_M-GGUF | CHE-72 | "2024-06-21T20:09:12Z" | 1,065 | 0 | null | [
"gguf",
"nlp",
"code",
"llama-cpp",
"gguf-my-repo",
"text-generation",
"multilingual",
"base_model:microsoft/Phi-3-medium-128k-instruct",
"license:mit",
"region:us"
] | text-generation | "2024-06-21T20:08:32Z" | ---
base_model: microsoft/Phi-3-medium-128k-instruct
language:
- multilingual
license: mit
license_link: https://huggingface.co/microsoft/Phi-3-medium-128k-instruct/resolve/main/LICENSE
pipeline_tag: text-generation
tags:
- nlp
- code
- llama-cpp
- gguf-my-repo
inference:
parameters:
temperature: 0.7
widget:
- messages:
- role: user
content: Can you provide ways to eat combinations of bananas and dragonfruits?
---
# CHE-72/Phi-3-medium-128k-instruct-Q5_K_M-GGUF
This model was converted to GGUF format from [`microsoft/Phi-3-medium-128k-instruct`](https://huggingface.co/microsoft/Phi-3-medium-128k-instruct) 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/microsoft/Phi-3-medium-128k-instruct) 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/Phi-3-medium-128k-instruct-Q5_K_M-GGUF --hf-file phi-3-medium-128k-instruct-q5_k_m.gguf -p "The meaning to life and the universe is"
```
### Server:
```bash
llama-server --hf-repo CHE-72/Phi-3-medium-128k-instruct-Q5_K_M-GGUF --hf-file phi-3-medium-128k-instruct-q5_k_m.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/Phi-3-medium-128k-instruct-Q5_K_M-GGUF --hf-file phi-3-medium-128k-instruct-q5_k_m.gguf -p "The meaning to life and the universe is"
```
or
```
./llama-server --hf-repo CHE-72/Phi-3-medium-128k-instruct-Q5_K_M-GGUF --hf-file phi-3-medium-128k-instruct-q5_k_m.gguf -c 2048
```
|
davzoku/cria-llama2-7b-v1.3-GGML | davzoku | "2023-08-19T09:41:00Z" | 1,064 | 0 | transformers | [
"transformers",
"llama",
"text-generation",
"llama-2",
"en",
"dataset:mlabonne/CodeLlama-2-20k",
"license:llama2",
"autotrain_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-08-15T07:04:05Z" | ---
inference: false
language: en
license: llama2
model_type: llama
datasets:
- mlabonne/CodeLlama-2-20k
pipeline_tag: text-generation
tags:
- llama-2
---
# CRIA v1.3
💡 [Article](https://walterteng.com/cria) |
💻 [Github](https://github.com/davzoku/cria) |
📔 Colab [1](https://colab.research.google.com/drive/1rYTs3qWJerrYwihf1j0f00cnzzcpAfYe),[2](https://colab.research.google.com/drive/1Wjs2I1VHjs6zT_GE42iEXsLtYh6VqiJU)
## What is CRIA?
> krē-ə plural crias. : a baby llama, alpaca, vicuña, or guanaco.
<p align="center">
<img src="https://raw.githubusercontent.com/davzoku/cria/main/assets/icon-512x512.png" width="300" height="300" alt="Cria Logo"> <br>
<i>or what ChatGPT suggests, <b>"Crafting a Rapid prototype of an Intelligent llm App using open source resources"</b>.</i>
</p>
The initial objective of the CRIA project is to develop a comprehensive end-to-end chatbot system, starting from the instruction-tuning of a large language model and extending to its deployment on the web using frameworks such as Next.js.
Specifically, we have fine-tuned the `llama-2-7b-chat-hf` model with QLoRA (4-bit precision) using the [mlabonne/CodeLlama-2-20k](https://huggingface.co/datasets/mlabonne/CodeLlama-2-20k) dataset. This fine-tuned model serves as the backbone for the [CRIA chat](https://chat.walterteng.com) platform.
## 📦 Model Release
CRIA v1.3 comes with several variants.
- [davzoku/cria-llama2-7b-v1.3](https://huggingface.co/davzoku/cria-llama2-7b-v1.3): Merged Model
- [davzoku/cria-llama2-7b-v1.3-GGML](https://huggingface.co/davzoku/cria-llama2-7b-v1.3-GGML): Quantized Merged Model
- [davzoku/cria-llama2-7b-v1.3_peft](https://huggingface.co/davzoku/cria-llama2-7b-v1.3_peft): PEFT adapter
## 🔧 Training
It was trained on a Google Colab notebook with a T4 GPU and high RAM.
### Training procedure
The following `bitsandbytes` quantization config was used during training:
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: False
- bnb_4bit_compute_dtype: float16
### Framework versions
- PEFT 0.4.0
## 💻 Usage
```python
# pip install transformers accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "davzoku/cria-llama2-7b-v1.3"
prompt = "What is a cria?"
tokenizer = AutoTokenizer.from_pretrained(model)
pipeline = transformers.pipeline(
"text-generation",
model=model,
torch_dtype=torch.float16,
device_map="auto",
)
sequences = pipeline(
f'<s>[INST] {prompt} [/INST]',
do_sample=True,
top_k=10,
num_return_sequences=1,
eos_token_id=tokenizer.eos_token_id,
max_length=200,
)
for seq in sequences:
print(f"Result: {seq['generated_text']}")
```
## References
We'd like to thank:
- [mlabonne](https://huggingface.co/mlabonne) for his article and resources on implementation of instruction tuning
- [TheBloke](https://huggingface.co/TheBloke) for his script for LLM quantization.
|
Danielbrdz/Barcenas-Mistral-7b | Danielbrdz | "2023-10-20T22:41:01Z" | 1,064 | 7 | transformers | [
"transformers",
"pytorch",
"mistral",
"text-generation",
"en",
"es",
"dataset:Danielbrdz/Barcenas-lmsys-Dataset",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-10-20T19:44:15Z" | ---
license: apache-2.0
datasets:
- Danielbrdz/Barcenas-lmsys-Dataset
language:
- en
- es
---
Barcenas-Mistral-7b is a fine-tuning of teknium/CollectiveCognition-v1-Mistral-7B
It was trained with Spanish data from lmsys/lmsys-chat-1m
provided by Danielbrdz/Barcenas-lmsys-Dataset
Made with ❤️ in Guadalupe, Nuevo Leon, Mexico 🇲🇽 |
Metaspectral/Tai | Metaspectral | "2023-11-15T16:15:52Z" | 1,064 | 3 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"license:llama2",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-10-29T06:00:48Z" | ---
license: llama2
---
Tai is a LLM trained on LLaMA-2-70B. Tai was trained as a general purpose Large Language Model, to be helpful in answering questions related to STEM subjects.
## Prompt Format:
```
SYSTEM:
USER:
ASSISTANT:
``` |
budecosystem/genz-13b-infinite | budecosystem | "2023-11-03T13:22:39Z" | 1,064 | 2 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"arxiv:2308.16137",
"license:llama2",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-11-03T12:19:06Z" | ---
license: llama2
---
## Introducing GenZ Infinite
The model is a finetuned version of Genz-13B-v2 with a context size of 16K. The model architecture is updated to have lamda attention from the LM-Infinite paper which gives the model capability of 120K+ sequence length without affecting the preplexity
## Generate responses
Use the generate.py file from the [github repo](https://github.com/BudEcosystem/genz-infinite)
```
python generate.py --base_model budecosystem/genz-13b-infinite
```
You can integrate the model in your code my loading convert_llama_model function.
```python
import torch
from transformers import GenerationConfig, AutoModelForCausalLM, AutoTokenizer
from model.llama import convert_llama_model
local_branch = 2048
global_branch = 10
limit_distance = 2048
model = AutoModelForCausalLM.from_pretrained(
"budecosystem/genz-13b-infinite",
torch_dtype=torch.float16,
device_map="auto",
)
model = convert_llama_model(model, local_branch, global_branch)
```
## Evaluation
| Task | 4096 | 5120 | 8192 | 16384 |
| :----:|:---------:| :--------:| :--------:| :--------:|
|Passkey retreival | 100 | 75 | 48 | 30 |
## Training details
The model is trained of 4 A100 80GB for approximately 55hrs.
| Hyperparameters | Value |
| :----------------------------| :-----: |
| per_device_train_batch_size | 1 |
| gradient_accumulation_steps | 1 |
| epoch | 3 |
| steps | 8550 |
| learning_rate | 2e-4 |
| lr schedular type | cosine |
| warmup steps | 1000 |
| optimizer | adamw |
| fp16 | True |
| GPU | 4 A100 80GB |
### Acknowledgments
We'd like to thank the open-source community and the researchers whose foundational work laid the path to this model. Special shoutout to the authors of [LM-Infinite paper](https://arxiv.org/abs/2308.16137) and the [GitHub repo](https://github.com/Glaciohound/LM-Infinite)
|
antoinelouis/colbertv1-camembert-base-mmarcoFR | antoinelouis | "2024-03-26T14:22:18Z" | 1,064 | 5 | RAGatouille | [
"RAGatouille",
"safetensors",
"camembert",
"colbert",
"passage-retrieval",
"sentence-similarity",
"fr",
"dataset:unicamp-dl/mmarco",
"base_model:camembert-base",
"license:mit",
"model-index",
"region:us"
] | sentence-similarity | "2023-12-22T14:13:48Z" | ---
pipeline_tag: sentence-similarity
language: fr
license: mit
datasets:
- unicamp-dl/mmarco
metrics:
- recall
tags:
- colbert
- passage-retrieval
base_model: camembert-base
library_name: RAGatouille
inference: false
model-index:
- name: colbertv1-camembert-base-mmarcoFR
results:
- task:
type: sentence-similarity
name: Passage Retrieval
dataset:
type: unicamp-dl/mmarco
name: mMARCO-fr
config: french
split: validation
metrics:
- type: recall_at_1000
name: Recall@1000
value: 89.7
- type: recall_at_500
name: Recall@500
value: 88.4
- type: recall_at_100
name: Recall@100
value: 80.0
- type: recall_at_10
name: Recall@10
value: 54.2
- type: mrr_at_10
name: MRR@10
value: 29.5
---
# colbertv1-camembert-base-mmarcoFR
This is a [ColBERTv1](https://doi.org/10.48550/arXiv.2004.12832) model for **French** that can be used for semantic search. It encodes queries and passages into matrices
of token-level embeddings and efficiently finds passages that contextually match the query using scalable vector-similarity (MaxSim) operators.
## Usage
Here are some examples for using the model with [RAGatouille](https://github.com/bclavie/RAGatouille) or [colbert-ai](https://github.com/stanford-futuredata/ColBERT).
### Using RAGatouille
First, you will need to install the following libraries:
```bash
pip install -U ragatouille
```
Then, you can use the model like this:
```python
from ragatouille import RAGPretrainedModel
index_name: str = "my_index" # The name of your index, i.e. the name of your vector database
documents: list = ["Ceci est un premier document.", "Voici un second document.", "etc."] # Corpus
# Step 1: Indexing.
RAG = RAGPretrainedModel.from_pretrained("antoinelouis/colbertv1-camembert-base-mmarcoFR")
RAG.index(name=index_name, collection=documents)
# Step 2: Searching.
RAG = RAGPretrainedModel.from_index(index_name) # if not already loaded
RAG.search(query="Comment effectuer une recherche avec ColBERT ?", k=10)
```
### Using ColBERT-AI
First, you will need to install the following libraries:
```bash
pip install git+https://github.com/stanford-futuredata/ColBERT.git torch faiss-gpu==1.7.2
```
Then, you can use the model like this:
```python
from colbert import Indexer, Searcher
from colbert.infra import Run, RunConfig
n_gpu: int = 1 # Set your number of available GPUs
experiment: str = "colbert" # Name of the folder where the logs and created indices will be stored
index_name: str = "my_index" # The name of your index, i.e. the name of your vector database
documents: list = ["Ceci est un premier document.", "Voici un second document.", "etc."] # Corpus
# Step 1: Indexing. This step encodes all passages into matrices, stores them on disk, and builds data structures for efficient search.
with Run().context(RunConfig(nranks=n_gpu,experiment=experiment)):
indexer = Indexer(checkpoint="antoinelouis/colbertv1-camembert-base-mmarcoFR")
indexer.index(name=index_name, collection=documents)
# Step 2: Searching. Given the model and index, you can issue queries over the collection to retrieve the top-k passages for each query.
with Run().context(RunConfig(nranks=n_gpu,experiment=experiment)):
searcher = Searcher(index=index_name) # You don't need to specify checkpoint again, the model name is stored in the index.
results = searcher.search(query="Comment effectuer une recherche avec ColBERT ?", k=10)
# results: tuple of tuples of length k containing ((passage_id, passage_rank, passage_score), ...)
```
## Evaluation
The model is evaluated on the smaller development set of [mMARCO-fr](https://ir-datasets.com/mmarco.html#mmarco/v2/fr/), which consists of 6,980 queries for a corpus of
8.8M candidate passages. We report the mean reciprocal rank (MRR), normalized discounted cumulative gainand (NDCG), mean average precision (MAP), and recall at various cut-offs (R@k).
Below, we compare its performance with other publicly available French ColBERT models fine-tuned on the same dataset. To see how it compares to other neural retrievers in French,
check out the [*DécouvrIR*](https://huggingface.co/spaces/antoinelouis/decouvrir) leaderboard.
| model | #Param.(↓) | Size | Dim. | Index | R@1000 | R@500 | R@100 | R@10 | MRR@10 |
|:-----------------------------------------------------------------------------------------------------------|-----------:|------:|-----:|------:|-------:|------:|------:|-----:|-------:|
| [colbertv2-camembert-L4-mmarcoFR](https://huggingface.co/antoinelouis/colbertv2-camembert-L4-mmarcoFR) | 54M | 0.2GB | 32 | 9GB | 91.9 | 90.3 | 81.9 | 56.7 | 32.3 |
| [FraColBERTv2](https://huggingface.co/bclavie/FraColBERTv2) | 111M | 0.4GB | 128 | 28GB | 90.0 | 88.9 | 81.2 | 57.1 | 32.4 |
| **colbertv1-camembert-base-mmarcoFR** | 111M | 0.4GB | 128 | 28GB | 89.7 | 88.4 | 80.0 | 54.2 | 29.5 |
NB: Index corresponds to the size of the mMARCO-fr index (8.8M passages) on disk when using ColBERTv2's residual compression mechanism.
## Training
#### Data
We use the French training set from the [mMARCO](https://huggingface.co/datasets/unicamp-dl/mmarco) dataset,
a multilingual machine-translated version of MS MARCO that contains 8.8M passages and 539K training queries.
We sample 12.8M (q, p+, p-) triples from the official ~39.8M [training triples](https://microsoft.github.io/msmarco/Datasets.html#passage-ranking-dataset).
#### Implementation
The model is initialized from the [camembert-base](https://huggingface.co/camembert-base) checkpoint and optimized via a combination of the pairwise softmax
cross-entropy loss computed over predicted scores for the positive and hard negative passages (as in [ColBERTv1](https://doi.org/10.48550/arXiv.2004.12832))
and the in-batch sampled softmax cross-entropy loss (as in [ColBERTv2](https://doi.org/10.48550/arXiv.2112.01488)). It was trained on a single Tesla V100 GPU
with 32GBs of memory during 200k steps using a batch size of 64 and the AdamW optimizer with a constant learning rate of 3e-06. The embedding dimension was set
to 128, and the maximum sequence lengths for questions and passages length were fixed to 32 and 256 tokens, respectively.
## Citation
```bibtex
@online{louis2024decouvrir,
author = 'Antoine Louis',
title = 'DécouvrIR: A Benchmark for Evaluating the Robustness of Information Retrieval Models in French',
publisher = 'Hugging Face',
month = 'mar',
year = '2024',
url = 'https://huggingface.co/spaces/antoinelouis/decouvrir',
}
``` |
Technoculture/Medorca-7B-Slerp | Technoculture | "2024-01-10T20:30:10Z" | 1,064 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"merge",
"mergekit",
"epfl-llm/meditron-7b",
"microsoft/Orca-2-7b",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-01-10T17:01:48Z" | ---
license: apache-2.0
tags:
- merge
- mergekit
- epfl-llm/meditron-7b
- microsoft/Orca-2-7b
---
# Medorca-7B-Slerp
Medorca-7B-Slerp is a merge of the following models:
* [epfl-llm/meditron-7b](https://huggingface.co/epfl-llm/meditron-7b)
* [microsoft/Orca-2-7b](https://huggingface.co/microsoft/Orca-2-7b)
## 🧩 Configuration
```yaml
slices:
- sources:
- model: epfl-llm/meditron-7b
layer_range: [0, 32]
- model: microsoft/Orca-2-7b
layer_range: [0, 32]
merge_method: slerp
base_model: epfl-llm/meditron-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 # fallback for rest of tensors
dtype: float16
```
## 💻 Usage
```python
!pip install -qU transformers accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "Technoculture/Medorca-7B-Slerp"
messages = [{"role": "user", "content": "I am feeling sleepy these days"}]
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"])
``` |
aqweteddy/llama2-7b-capybara | aqweteddy | "2024-01-11T13:04:36Z" | 1,064 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"en",
"license:llama2",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-01-11T10:33:34Z" | ---
license: llama2
language:
- en
---
蜻蜓在樹上飛舞，微風輕撫著花朵。彩虹橫跨天際，陽光灑落在大地上。小鳥
在枝頭歌唱，樹葉在風中搖曳。夜晚降臨，星星閃爍著神秘的光芒，月亮安靜地掛在夜空中。海浪拍打著岸邊，
沙灘上留下一串串的腳印。城市裡的霓虹燈閃爍著不
同的顏色，人們匆忙地走著，生活總是充滿著各種各樣的奇遇和驚喜。
在這個彷彿永無止境的數位宇宙中，文字如同一片無垠的星空，散落著各種不同的意義和情感。讓我們一同漫遊於這片文字的海洋，探索其中的奧秘和無窮可能。
有時候，文字是一道橋樑，將人們的心靈連結在一起。它們可以是一首詩的抒情，翻動著內心深處的情感；又或者是一篇散文的敘事，帶領著讀者穿越時光的長河。文字，如同繽紛的色彩，編織出一幅幅生動的畫面，讓人沉浸其中，感受著文字所帶來的魅力。
然而，有時文字也是一把鑰匙，打開人們內心深處的門扉。它們可以是一段哲思的隨筆，引領著思考的方向；又或者是一段教學的論述，啟迪著知識的火花。文字，如同智慧的光芒，照亮前行的路徑，讓人不斷追尋著知識的寶藏。
在這片文字的森林中，每一個字都像是一顆獨特的星辰，閃耀著屬於自己的光芒。它們彼此交織，組成了千變萬化的篇章，述說著人生的點滴和故事。有的文字如溪流般清澈，流淌在心靈的大地；有的文字如烈火般澎湃，燃燒著對夢想的熱愛。
或許，文字就是一場無聲的音樂會，每一個字都是音符，在紙張上跳躍奏鳴。它們組成了悠揚的旋律，讓人沉浸在音律的律動中，感受著文字的節奏。有時是輕柔的悠扬，如同春天的微風拂過花朵；有時是激昂的高潮，如同暴風雨席捲大地。
而這片文字的宇宙，也是一個不斷蛻變的世界。文字在時光的洗禮中變得沉積厚重，如同古老的石碑；又在創新的思維中變得飄逸多姿，如同繽紛的煙花。它們不斷演化，跨越時空，將過去和未來連結在一起，形成一個永恆的脈動。
在這片文字的海洋裡，我們彷彿是漂流的冒險家，穿越在字與字之間的河流。或許，下一個字就是我們尋找已久的寶藏，蘊藏著無盡的驚喜和奇蹟。或許，下一段文字就是我們心靈的憩息站，讓我們在其中找到共鳴和安寧。
讓我們一同在這片文字的迷霧中遨遊，感受其中的魔法和饗宴。文字，是一種力量，是一種靈魂的交流，是一種永恆的存在。在這裡，我們共同探索著文字的奧秘，品味著文字的美麗，共同編織著屬於我們自己的故事。 |
RichardErkhov/bigscience_-_bloom-3b-gguf | RichardErkhov | "2024-04-27T04:24:33Z" | 1,064 | 0 | null | [
"gguf",
"arxiv:1909.08053",
"arxiv:2110.02861",
"arxiv:2108.12409",
"region:us"
] | null | "2024-04-26T23:21:42Z" | Quantization made by Richard Erkhov.
[Github](https://github.com/RichardErkhov)
[Discord](https://discord.gg/pvy7H8DZMG)
[Request more models](https://github.com/RichardErkhov/quant_request)
bloom-3b - GGUF
- Model creator: https://huggingface.co/bigscience/
- Original model: https://huggingface.co/bigscience/bloom-3b/
| Name | Quant method | Size |
| ---- | ---- | ---- |
| [bloom-3b.Q2_K.gguf](https://huggingface.co/RichardErkhov/bigscience_-_bloom-3b-gguf/blob/main/bloom-3b.Q2_K.gguf) | Q2_K | 1.52GB |
| [bloom-3b.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/bigscience_-_bloom-3b-gguf/blob/main/bloom-3b.IQ3_XS.gguf) | IQ3_XS | 1.68GB |
| [bloom-3b.IQ3_S.gguf](https://huggingface.co/RichardErkhov/bigscience_-_bloom-3b-gguf/blob/main/bloom-3b.IQ3_S.gguf) | IQ3_S | 1.71GB |
| [bloom-3b.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/bigscience_-_bloom-3b-gguf/blob/main/bloom-3b.Q3_K_S.gguf) | Q3_K_S | 1.71GB |
| [bloom-3b.IQ3_M.gguf](https://huggingface.co/RichardErkhov/bigscience_-_bloom-3b-gguf/blob/main/bloom-3b.IQ3_M.gguf) | IQ3_M | 1.81GB |
| [bloom-3b.Q3_K.gguf](https://huggingface.co/RichardErkhov/bigscience_-_bloom-3b-gguf/blob/main/bloom-3b.Q3_K.gguf) | Q3_K | 1.9GB |
| [bloom-3b.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/bigscience_-_bloom-3b-gguf/blob/main/bloom-3b.Q3_K_M.gguf) | Q3_K_M | 1.9GB |
| [bloom-3b.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/bigscience_-_bloom-3b-gguf/blob/main/bloom-3b.Q3_K_L.gguf) | Q3_K_L | 2.02GB |
| [bloom-3b.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/bigscience_-_bloom-3b-gguf/blob/main/bloom-3b.IQ4_XS.gguf) | IQ4_XS | 2.0GB |
| [bloom-3b.Q4_0.gguf](https://huggingface.co/RichardErkhov/bigscience_-_bloom-3b-gguf/blob/main/bloom-3b.Q4_0.gguf) | Q4_0 | 2.08GB |
| [bloom-3b.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/bigscience_-_bloom-3b-gguf/blob/main/bloom-3b.IQ4_NL.gguf) | IQ4_NL | 2.09GB |
| [bloom-3b.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/bigscience_-_bloom-3b-gguf/blob/main/bloom-3b.Q4_K_S.gguf) | Q4_K_S | 2.09GB |
| [bloom-3b.Q4_K.gguf](https://huggingface.co/RichardErkhov/bigscience_-_bloom-3b-gguf/blob/main/bloom-3b.Q4_K.gguf) | Q4_K | 2.24GB |
| [bloom-3b.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/bigscience_-_bloom-3b-gguf/blob/main/bloom-3b.Q4_K_M.gguf) | Q4_K_M | 2.24GB |
| [bloom-3b.Q4_1.gguf](https://huggingface.co/RichardErkhov/bigscience_-_bloom-3b-gguf/blob/main/bloom-3b.Q4_1.gguf) | Q4_1 | 2.25GB |
| [bloom-3b.Q5_0.gguf](https://huggingface.co/RichardErkhov/bigscience_-_bloom-3b-gguf/blob/main/bloom-3b.Q5_0.gguf) | Q5_0 | 2.43GB |
| [bloom-3b.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/bigscience_-_bloom-3b-gguf/blob/main/bloom-3b.Q5_K_S.gguf) | Q5_K_S | 2.43GB |
| [bloom-3b.Q5_K.gguf](https://huggingface.co/RichardErkhov/bigscience_-_bloom-3b-gguf/blob/main/bloom-3b.Q5_K.gguf) | Q5_K | 2.55GB |
| [bloom-3b.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/bigscience_-_bloom-3b-gguf/blob/main/bloom-3b.Q5_K_M.gguf) | Q5_K_M | 1.64GB |
| [bloom-3b.Q5_1.gguf](https://huggingface.co/RichardErkhov/bigscience_-_bloom-3b-gguf/blob/main/bloom-3b.Q5_1.gguf) | Q5_1 | 1.58GB |
| [bloom-3b.Q6_K.gguf](https://huggingface.co/RichardErkhov/bigscience_-_bloom-3b-gguf/blob/main/bloom-3b.Q6_K.gguf) | Q6_K | 1.31GB |
Original model description:
---
license: bigscience-bloom-rail-1.0
language:
- ak
- ar
- as
- bm
- bn
- ca
- code
- en
- es
- eu
- fon
- fr
- gu
- hi
- id
- ig
- ki
- kn
- lg
- ln
- ml
- mr
- ne
- nso
- ny
- or
- pa
- pt
- rn
- rw
- sn
- st
- sw
- ta
- te
- tn
- ts
- tum
- tw
- ur
- vi
- wo
- xh
- yo
- zh
- zhs
- zht
- zu
pipeline_tag: text-generation
model-index:
- name: bloom
results:
- task:
type: text-generation
name: text generation
dataset:
name: arc_challenge
type: arc_challenge
metrics:
- name: acc
type: acc
value: 0.27986348122866894
verified: false
- task:
type: text-generation
name: text generation
dataset:
name: arc_easy
type: arc_easy
metrics:
- name: acc
type: acc
value: 0.5946969696969697
verified: false
- task:
type: text-generation
name: text generation
dataset:
name: axb
type: axb
metrics:
- name: acc
type: acc
value: 0.4433876811594203
verified: false
- task:
type: text-generation
name: text generation
dataset:
name: axg
type: axg
metrics:
- name: acc
type: acc
value: 0.5
verified: false
- task:
type: text-generation
name: text generation
dataset:
name: boolq
type: boolq
metrics:
- name: acc
type: acc
value: 0.6165137614678899
verified: false
- task:
type: text-generation
name: text generation
dataset:
name: cb
type: cb
metrics:
- name: acc
type: acc
value: 0.30357142857142855
verified: false
- task:
type: text-generation
name: text generation
dataset:
name: cola
type: cola
metrics:
- name: acc
type: acc
value: 0.610738255033557
verified: false
- task:
type: text-generation
name: text generation
dataset:
name: copa
type: copa
metrics:
- name: acc
type: acc
value: 0.63
verified: false
- task:
type: text-generation
name: text generation
dataset:
name: crows_pairs_english
type: crows_pairs_english
metrics:
- name: acc
type: acc
value: 0.4973166368515206
verified: false
- task:
type: text-generation
name: text generation
dataset:
name: crows_pairs_french
type: crows_pairs_french
metrics:
- name: acc
type: acc
value: 0.5032796660703638
verified: false
- task:
type: text-generation
name: text generation
dataset:
name: diabla
type: diabla
metrics:
- name: acc
type: acc
value: 0.28888308977035493
verified: false
- task:
type: text-generation
name: text generation
dataset:
name: gsarti/flores_101_afr
type: gsarti/flores_101_afr
metrics:
- name: byte_perplexity
type: byte_perplexity
value: 6.500798737976343
verified: false
- task:
type: text-generation
name: text generation
dataset:
name: gsarti/flores_101_amh
type: gsarti/flores_101_amh
metrics:
- name: byte_perplexity
type: byte_perplexity
value: 3.9726863338897145
verified: false
- task:
type: text-generation
name: text generation
dataset:
name: gsarti/flores_101_ara
type: gsarti/flores_101_ara
metrics:
- name: byte_perplexity
type: byte_perplexity
value: 1.8083841089875814
verified: false
- task:
type: text-generation
name: text generation
dataset:
name: gsarti/flores_101_asm
type: gsarti/flores_101_asm
metrics:
- name: byte_perplexity
type: byte_perplexity
value: 5.699102962086425
verified: false
- task:
type: text-generation
name: text generation
dataset:
name: gsarti/flores_101_ast
type: gsarti/flores_101_ast
metrics:
- name: byte_perplexity
type: byte_perplexity
value: 3.9252047073429384
verified: false
- task:
type: text-generation
name: text generation
dataset:
name: gsarti/flores_101_azj
type: gsarti/flores_101_azj
metrics:
- name: byte_perplexity
type: byte_perplexity
value: 6.942805054270002
verified: false
- task:
type: text-generation
name: text generation
dataset:
name: gsarti/flores_101_bel
type: gsarti/flores_101_bel
metrics:
- name: byte_perplexity
type: byte_perplexity
value: 3.614136245847082
verified: false
- task:
type: text-generation
name: text generation
dataset:
name: gsarti/flores_101_ben
type: gsarti/flores_101_ben
metrics:
- name: byte_perplexity
type: byte_perplexity
value: 5.121491534300969
verified: false
- task:
type: text-generation
name: text generation
dataset:
name: gsarti/flores_101_bos
type: gsarti/flores_101_bos
metrics:
- name: byte_perplexity
type: byte_perplexity
value: 5.653353469118798
verified: false
- task:
type: text-generation
name: text generation
dataset:
name: gsarti/flores_101_bul
type: gsarti/flores_101_bul
metrics:
- name: byte_perplexity
type: byte_perplexity
value: 2.7014693938055068
verified: false
- task:
type: text-generation
name: text generation
dataset:
name: gsarti/flores_101_cat
type: gsarti/flores_101_cat
metrics:
- name: byte_perplexity
type: byte_perplexity
value: 2.305190041967345
verified: false
- task:
type: text-generation
name: text generation
dataset:
name: gsarti/flores_101_ceb
type: gsarti/flores_101_ceb
metrics:
- name: byte_perplexity
type: byte_perplexity
value: 6.291000321323428
verified: false
- task:
type: text-generation
name: text generation
dataset:
name: gsarti/flores_101_ces
type: gsarti/flores_101_ces
metrics:
- name: byte_perplexity
type: byte_perplexity
value: 5.447322753586386
verified: false
- task:
type: text-generation
name: text generation
dataset:
name: gsarti/flores_101_ckb
type: gsarti/flores_101_ckb
metrics:
- name: byte_perplexity
type: byte_perplexity
value: 3.7255124939234765
verified: false
- task:
type: text-generation
name: text generation
dataset:
name: gsarti/flores_101_cym
type: gsarti/flores_101_cym
metrics:
- name: byte_perplexity
type: byte_perplexity
value: 12.539424151448149
verified: false
- task:
type: text-generation
name: text generation
dataset:
name: gsarti/flores_101_dan
type: gsarti/flores_101_dan
metrics:
- name: byte_perplexity
type: byte_perplexity
value: 5.183309001005672
verified: false
- task:
type: text-generation
name: text generation
dataset:
name: gsarti/flores_101_deu
type: gsarti/flores_101_deu
metrics:
- name: byte_perplexity
type: byte_perplexity
value: 3.1180422286591347
verified: false
- task:
type: text-generation
name: text generation
dataset:
name: gsarti/flores_101_ell
type: gsarti/flores_101_ell
metrics:
- name: byte_perplexity
type: byte_perplexity
value: 2.467943456164706
verified: false
- task:
type: text-generation
name: text generation
dataset:
name: gsarti/flores_101_eng
type: gsarti/flores_101_eng
metrics:
- name: byte_perplexity
type: byte_perplexity
value: 2.018740628193298
verified: false
- task:
type: text-generation
name: text generation
dataset:
name: gsarti/flores_101_est
type: gsarti/flores_101_est
metrics:
- name: byte_perplexity
type: byte_perplexity
value: 9.11654425176368
verified: false
- task:
type: text-generation
name: text generation
dataset:
name: gsarti/flores_101_fas
type: gsarti/flores_101_fas
metrics:
- name: byte_perplexity
type: byte_perplexity
value: 3.058009097116482
verified: false
- task:
type: text-generation
name: text generation
dataset:
name: gsarti/flores_101_fin
type: gsarti/flores_101_fin
metrics:
- name: byte_perplexity
type: byte_perplexity
value: 6.847047959628553
verified: false
- task:
type: text-generation
name: text generation
dataset:
name: gsarti/flores_101_fra
type: gsarti/flores_101_fra
metrics:
- name: byte_perplexity
type: byte_perplexity
value: 1.9975177011840075
verified: false
- task:
type: text-generation
name: text generation
dataset:
name: gsarti/flores_101_ful
type: gsarti/flores_101_ful
metrics:
- name: byte_perplexity
type: byte_perplexity
value: 11.465912731488828
verified: false
- task:
type: text-generation
name: text generation
dataset:
name: gsarti/flores_101_gle
type: gsarti/flores_101_gle
metrics:
- name: byte_perplexity
type: byte_perplexity
value: 8.681491663539422
verified: false
- task:
type: text-generation
name: text generation
dataset:
name: gsarti/flores_101_glg
type: gsarti/flores_101_glg
metrics:
- name: byte_perplexity
type: byte_perplexity
value: 3.029991089015508
verified: false
- task:
type: text-generation
name: text generation
dataset:
name: gsarti/flores_101_guj
type: gsarti/flores_101_guj
metrics:
- name: byte_perplexity
type: byte_perplexity
value: 4.955224230286231
verified: false
- task:
type: text-generation
name: text generation
dataset:
name: gsarti/flores_101_hau
type: gsarti/flores_101_hau
metrics:
- name: byte_perplexity
type: byte_perplexity
value: 10.758347356372159
verified: false
- task:
type: text-generation
name: text generation
dataset:
name: gsarti/flores_101_heb
type: gsarti/flores_101_heb
metrics:
- name: byte_perplexity
type: byte_perplexity
value: 3.6004478129801667
verified: false
- task:
type: text-generation
name: text generation
dataset:
name: gsarti/flores_101_hin
type: gsarti/flores_101_hin
metrics:
- name: byte_perplexity
type: byte_perplexity
value: 4.712530650588064
verified: false
- task:
type: text-generation
name: text generation
dataset:
name: gsarti/flores_101_hrv
type: gsarti/flores_101_hrv
metrics:
- name: byte_perplexity
type: byte_perplexity
value: 5.822418943372185
verified: false
- task:
type: text-generation
name: text generation
dataset:
name: gsarti/flores_101_hun
type: gsarti/flores_101_hun
metrics:
- name: byte_perplexity
type: byte_perplexity
value: 6.440482646965992
verified: false
- task:
type: text-generation
name: text generation
dataset:
name: gsarti/flores_101_hye
type: gsarti/flores_101_hye
metrics:
- name: byte_perplexity
type: byte_perplexity
value: 3.657718918347166
verified: false
- task:
type: text-generation
name: text generation
dataset:
name: gsarti/flores_101_ibo
type: gsarti/flores_101_ibo
metrics:
- name: byte_perplexity
type: byte_perplexity
value: 5.564814003872672
verified: false
- task:
type: text-generation
name: text generation
dataset:
name: gsarti/flores_101_ind
type: gsarti/flores_101_ind
metrics:
- name: byte_perplexity
type: byte_perplexity
value: 2.1597101468869373
verified: false
- task:
type: text-generation
name: text generation
dataset:
name: gsarti/flores_101_isl
type: gsarti/flores_101_isl
metrics:
- name: byte_perplexity
type: byte_perplexity
value: 8.082349269518136
verified: false
- task:
type: text-generation
name: text generation
dataset:
name: gsarti/flores_101_ita
type: gsarti/flores_101_ita
metrics:
- name: byte_perplexity
type: byte_perplexity
value: 2.9687591414176207
verified: false
- task:
type: text-generation
name: text generation
dataset:
name: gsarti/flores_101_jav
type: gsarti/flores_101_jav
metrics:
- name: byte_perplexity
type: byte_perplexity
value: 7.0573805415708994
verified: false
- task:
type: text-generation
name: text generation
dataset:
name: gsarti/flores_101_jpn
type: gsarti/flores_101_jpn
metrics:
- name: byte_perplexity
type: byte_perplexity
value: 2.7758864197116933
verified: false
- task:
type: text-generation
name: text generation
dataset:
name: gsarti/flores_101_kam
type: gsarti/flores_101_kam
metrics:
- name: byte_perplexity
type: byte_perplexity
value: 11.072949642861332
verified: false
- task:
type: text-generation
name: text generation
dataset:
name: gsarti/flores_101_kan
type: gsarti/flores_101_kan
metrics:
- name: byte_perplexity
type: byte_perplexity
value: 5.551730651007082
verified: false
- task:
type: text-generation
name: text generation
dataset:
name: gsarti/flores_101_kat
type: gsarti/flores_101_kat
metrics:
- name: byte_perplexity
type: byte_perplexity
value: 2.522630524283745
verified: false
- task:
type: text-generation
name: text generation
dataset:
name: gsarti/flores_101_kaz
type: gsarti/flores_101_kaz
metrics:
- name: byte_perplexity
type: byte_perplexity
value: 3.3901748516975574
verified: false
- task:
type: text-generation
name: text generation
dataset:
name: gsarti/flores_101_kea
type: gsarti/flores_101_kea
metrics:
- name: byte_perplexity
type: byte_perplexity
value: 8.918534182590863
verified: false
- task:
type: text-generation
name: text generation
dataset:
name: gsarti/flores_101_kir
type: gsarti/flores_101_kir
metrics:
- name: byte_perplexity
type: byte_perplexity
value: 3.729278369847201
verified: false
- task:
type: text-generation
name: text generation
dataset:
name: gsarti/flores_101_kor
type: gsarti/flores_101_kor
metrics:
- name: byte_perplexity
type: byte_perplexity
value: 3.932884847226212
verified: false
- task:
type: text-generation
name: text generation
dataset:
name: gsarti/flores_101_lao
type: gsarti/flores_101_lao
metrics:
- name: byte_perplexity
type: byte_perplexity
value: 2.9077314760849924
verified: false
- task:
type: text-generation
name: text generation
dataset:
name: gsarti/flores_101_lav
type: gsarti/flores_101_lav
metrics:
- name: byte_perplexity
type: byte_perplexity
value: 7.777221919194806
verified: false
- task:
type: text-generation
name: text generation
dataset:
name: gsarti/flores_101_lin
type: gsarti/flores_101_lin
metrics:
- name: byte_perplexity
type: byte_perplexity
value: 7.524842908050988
verified: false
- task:
type: text-generation
name: text generation
dataset:
name: gsarti/flores_101_lit
type: gsarti/flores_101_lit
metrics:
- name: byte_perplexity
type: byte_perplexity
value: 7.369179434621725
verified: false
- task:
type: text-generation
name: text generation
dataset:
name: gsarti/flores_101_ltz
type: gsarti/flores_101_ltz
metrics:
- name: byte_perplexity
type: byte_perplexity
value: 8.801059747949214
verified: false
- task:
type: text-generation
name: text generation
dataset:
name: gsarti/flores_101_lug
type: gsarti/flores_101_lug
metrics:
- name: byte_perplexity
type: byte_perplexity
value: 8.483203026364786
verified: false
- task:
type: text-generation
name: text generation
dataset:
name: gsarti/flores_101_luo
type: gsarti/flores_101_luo
metrics:
- name: byte_perplexity
type: byte_perplexity
value: 11.975963093623681
verified: false
- task:
type: text-generation
name: text generation
dataset:
name: gsarti/flores_101_mal
type: gsarti/flores_101_mal
metrics:
- name: byte_perplexity
type: byte_perplexity
value: 4.615948455160037
verified: false
- task:
type: text-generation
name: text generation
dataset:
name: gsarti/flores_101_mar
type: gsarti/flores_101_mar
metrics:
- name: byte_perplexity
type: byte_perplexity
value: 5.483253482821379
verified: false
- task:
type: text-generation
name: text generation
dataset:
name: gsarti/flores_101_mkd
type: gsarti/flores_101_mkd
metrics:
- name: byte_perplexity
type: byte_perplexity
value: 2.9656732291754087
verified: false
- task:
type: text-generation
name: text generation
dataset:
name: gsarti/flores_101_mlt
type: gsarti/flores_101_mlt
metrics:
- name: byte_perplexity
type: byte_perplexity
value: 15.004773437665275
verified: false
- task:
type: text-generation
name: text generation
dataset:
name: gsarti/flores_101_mon
type: gsarti/flores_101_mon
metrics:
- name: byte_perplexity
type: byte_perplexity
value: 3.410598542315402
verified: false
- task:
type: text-generation
name: text generation
dataset:
name: gsarti/flores_101_mri
type: gsarti/flores_101_mri
metrics:
- name: byte_perplexity
type: byte_perplexity
value: 7.474035895661322
verified: false
- task:
type: text-generation
name: text generation
dataset:
name: gsarti/flores_101_msa
type: gsarti/flores_101_msa
metrics:
- name: byte_perplexity
type: byte_perplexity
value: 2.5710001772665634
verified: false
- task:
type: text-generation
name: text generation
dataset:
name: gsarti/flores_101_mya
type: gsarti/flores_101_mya
metrics:
- name: byte_perplexity
type: byte_perplexity
value: 2.413577969878331
verified: false
- task:
type: text-generation
name: text generation
dataset:
name: gsarti/flores_101_nld
type: gsarti/flores_101_nld
metrics:
- name: byte_perplexity
type: byte_perplexity
value: 4.127831721885065
verified: false
- task:
type: text-generation
name: text generation
dataset:
name: gsarti/flores_101_nob
type: gsarti/flores_101_nob
metrics:
- name: byte_perplexity
type: byte_perplexity
value: 5.402763169129877
verified: false
- task:
type: text-generation
name: text generation
dataset:
name: gsarti/flores_101_npi
type: gsarti/flores_101_npi
metrics:
- name: byte_perplexity
type: byte_perplexity
value: 5.199342701937889
verified: false
- task:
type: text-generation
name: text generation
dataset:
name: gsarti/flores_101_nso
type: gsarti/flores_101_nso
metrics:
- name: byte_perplexity
type: byte_perplexity
value: 8.154626800955667
verified: false
- task:
type: text-generation
name: text generation
dataset:
name: gsarti/flores_101_nya
type: gsarti/flores_101_nya
metrics:
- name: byte_perplexity
type: byte_perplexity
value: 8.179860208369393
verified: false
- task:
type: text-generation
name: text generation
dataset:
name: gsarti/flores_101_oci
type: gsarti/flores_101_oci
metrics:
- name: byte_perplexity
type: byte_perplexity
value: 4.8617357393685845
verified: false
- task:
type: text-generation
name: text generation
dataset:
name: gsarti/flores_101_orm
type: gsarti/flores_101_orm
metrics:
- name: byte_perplexity
type: byte_perplexity
value: 12.911595421079408
verified: false
- task:
type: text-generation
name: text generation
dataset:
name: gsarti/flores_101_ory
type: gsarti/flores_101_ory
metrics:
- name: byte_perplexity
type: byte_perplexity
value: 5.189421861225964
verified: false
- task:
type: text-generation
name: text generation
dataset:
name: gsarti/flores_101_pan
type: gsarti/flores_101_pan
metrics:
- name: byte_perplexity
type: byte_perplexity
value: 4.698477289331806
verified: false
- task:
type: text-generation
name: text generation
dataset:
name: gsarti/flores_101_pol
type: gsarti/flores_101_pol
metrics:
- name: byte_perplexity
type: byte_perplexity
value: 4.625550458479643
verified: false
- task:
type: text-generation
name: text generation
dataset:
name: gsarti/flores_101_por
type: gsarti/flores_101_por
metrics:
- name: byte_perplexity
type: byte_perplexity
value: 1.9754515986213523
verified: false
- task:
type: text-generation
name: text generation
dataset:
name: gsarti/flores_101_pus
type: gsarti/flores_101_pus
metrics:
- name: byte_perplexity
type: byte_perplexity
value: 4.4963371422771585
verified: false
- task:
type: text-generation
name: text generation
dataset:
name: gsarti/flores_101_ron
type: gsarti/flores_101_ron
metrics:
- name: byte_perplexity
type: byte_perplexity
value: 4.965456830031304
verified: false
- task:
type: text-generation
name: text generation
dataset:
name: gsarti/flores_101_rus
type: gsarti/flores_101_rus
metrics:
- name: byte_perplexity
type: byte_perplexity
value: 2.0498020542445303
verified: false
- task:
type: text-generation
name: text generation
dataset:
name: gsarti/flores_101_slk
type: gsarti/flores_101_slk
metrics:
- name: byte_perplexity
type: byte_perplexity
value: 6.450822127057479
verified: false
- task:
type: text-generation
name: text generation
dataset:
name: gsarti/flores_101_slv
type: gsarti/flores_101_slv
metrics:
- name: byte_perplexity
type: byte_perplexity
value: 6.620252120186232
verified: false
- task:
type: text-generation
name: text generation
dataset:
name: gsarti/flores_101_sna
type: gsarti/flores_101_sna
metrics:
- name: byte_perplexity
type: byte_perplexity
value: 8.462166771382726
verified: false
- task:
type: text-generation
name: text generation
dataset:
name: gsarti/flores_101_snd
type: gsarti/flores_101_snd
metrics:
- name: byte_perplexity
type: byte_perplexity
value: 5.466066951221973
verified: false
- task:
type: text-generation
name: text generation
dataset:
name: gsarti/flores_101_som
type: gsarti/flores_101_som
metrics:
- name: byte_perplexity
type: byte_perplexity
value: 11.95918054093392
verified: false
- task:
type: text-generation
name: text generation
dataset:
name: gsarti/flores_101_spa
type: gsarti/flores_101_spa
metrics:
- name: byte_perplexity
type: byte_perplexity
value: 1.8965140104323535
verified: false
- task:
type: text-generation
name: text generation
dataset:
name: gsarti/flores_101_srp
type: gsarti/flores_101_srp
metrics:
- name: byte_perplexity
type: byte_perplexity
value: 2.871214785885079
verified: false
- task:
type: text-generation
name: text generation
dataset:
name: gsarti/flores_101_swe
type: gsarti/flores_101_swe
metrics:
- name: byte_perplexity
type: byte_perplexity
value: 5.054972008155866
verified: false
- task:
type: text-generation
name: text generation
dataset:
name: gsarti/flores_101_swh
type: gsarti/flores_101_swh
metrics:
- name: byte_perplexity
type: byte_perplexity
value: 3.6973091886730676
verified: false
- task:
type: text-generation
name: text generation
dataset:
name: gsarti/flores_101_tam
type: gsarti/flores_101_tam
metrics:
- name: byte_perplexity
type: byte_perplexity
value: 4.539493400469833
verified: false
- task:
type: text-generation
name: text generation
dataset:
name: gsarti/flores_101_tel
type: gsarti/flores_101_tel
metrics:
- name: byte_perplexity
type: byte_perplexity
value: 5.807499987508966
verified: false
- task:
type: text-generation
name: text generation
dataset:
name: gsarti/flores_101_tgk
type: gsarti/flores_101_tgk
metrics:
- name: byte_perplexity
type: byte_perplexity
value: 3.5994818827380426
verified: false
- task:
type: text-generation
name: text generation
dataset:
name: gsarti/flores_101_tgl
type: gsarti/flores_101_tgl
metrics:
- name: byte_perplexity
type: byte_perplexity
value: 5.667053833119858
verified: false
- task:
type: text-generation
name: text generation
dataset:
name: gsarti/flores_101_tha
type: gsarti/flores_101_tha
metrics:
- name: byte_perplexity
type: byte_perplexity
value: 2.365940201944242
verified: false
- task:
type: text-generation
name: text generation
dataset:
name: gsarti/flores_101_tur
type: gsarti/flores_101_tur
metrics:
- name: byte_perplexity
type: byte_perplexity
value: 4.885014749844601
verified: false
- task:
type: text-generation
name: text generation
dataset:
name: gsarti/flores_101_ukr
type: gsarti/flores_101_ukr
metrics:
- name: byte_perplexity
type: byte_perplexity
value: 2.7240934990288483
verified: false
- task:
type: text-generation
name: text generation
dataset:
name: gsarti/flores_101_umb
type: gsarti/flores_101_umb
metrics:
- name: byte_perplexity
type: byte_perplexity
value: 12.766915508610673
verified: false
- task:
type: text-generation
name: text generation
dataset:
name: gsarti/flores_101_urd
type: gsarti/flores_101_urd
metrics:
- name: byte_perplexity
type: byte_perplexity
value: 1.9797467071381232
verified: false
- task:
type: text-generation
name: text generation
dataset:
name: gsarti/flores_101_uzb
type: gsarti/flores_101_uzb
metrics:
- name: byte_perplexity
type: byte_perplexity
value: 12.002337637722146
verified: false
- task:
type: text-generation
name: text generation
dataset:
name: gsarti/flores_101_vie
type: gsarti/flores_101_vie
metrics:
- name: byte_perplexity
type: byte_perplexity
value: 1.76578415476397
verified: false
- task:
type: text-generation
name: text generation
dataset:
name: gsarti/flores_101_wol
type: gsarti/flores_101_wol
metrics:
- name: byte_perplexity
type: byte_perplexity
value: 9.144285650306488
verified: false
- task:
type: text-generation
name: text generation
dataset:
name: gsarti/flores_101_xho
type: gsarti/flores_101_xho
metrics:
- name: byte_perplexity
type: byte_perplexity
value: 7.403240538286952
verified: false
- task:
type: text-generation
name: text generation
dataset:
name: gsarti/flores_101_yor
type: gsarti/flores_101_yor
metrics:
- name: byte_perplexity
type: byte_perplexity
value: 5.91272037551173
verified: false
- task:
type: text-generation
name: text generation
dataset:
name: gsarti/flores_101_zho_simpl
type: gsarti/flores_101_zho_simpl
metrics:
- name: byte_perplexity
type: byte_perplexity
value: 2.2769070822768533
verified: false
- task:
type: text-generation
name: text generation
dataset:
name: gsarti/flores_101_zho_trad
type: gsarti/flores_101_zho_trad
metrics:
- name: byte_perplexity
type: byte_perplexity
value: 2.5180582198242383
verified: false
- task:
type: text-generation
name: text generation
dataset:
name: gsarti/flores_101_zul
type: gsarti/flores_101_zul
metrics:
- name: byte_perplexity
type: byte_perplexity
value: 8.53353320693145
verified: false
- task:
type: text-generation
name: text generation
dataset:
name: headqa
type: headqa
metrics:
- name: acc
type: acc
value: 0.26440554339897887
verified: false
- task:
type: text-generation
name: text generation
dataset:
name: hellaswag
type: hellaswag
metrics:
- name: acc
type: acc
value: 0.41236805417247563
verified: false
- task:
type: text-generation
name: text generation
dataset:
name: logiqa
type: logiqa
metrics:
- name: acc
type: acc
value: 0.2073732718894009
verified: false
- task:
type: text-generation
name: text generation
dataset:
name: mathqa
type: mathqa
metrics:
- name: acc
type: acc
value: 0.24958123953098826
verified: false
- task:
type: text-generation
name: text generation
dataset:
name: mc_taco
type: mc_taco
metrics:
- name: em
type: em
value: 0.11936936936936937
verified: false
- task:
type: text-generation
name: text generation
dataset:
name: mnli
type: mnli
metrics:
- name: acc
type: acc
value: 0.35496688741721855
verified: false
- task:
type: text-generation
name: text generation
dataset:
name: mnli_mismatched
type: mnli_mismatched
metrics:
- name: acc
type: acc
value: 0.35211554109031734
verified: false
- task:
type: text-generation
name: text generation
dataset:
name: mrpc
type: mrpc
metrics:
- name: acc
type: acc
value: 0.5857843137254902
verified: false
- task:
type: text-generation
name: text generation
dataset:
name: multirc
type: multirc
metrics:
- name: acc
type: acc
value: 0.5375412541254125
verified: false
- task:
type: text-generation
name: text generation
dataset:
name: openbookqa
type: openbookqa
metrics:
- name: acc
type: acc
value: 0.216
verified: false
- task:
type: text-generation
name: text generation
dataset:
name: piqa
type: piqa
metrics:
- name: acc
type: acc
value: 0.7078346028291621
verified: false
- task:
type: text-generation
name: text generation
dataset:
name: prost
type: prost
metrics:
- name: acc
type: acc
value: 0.22683603757472245
verified: false
- task:
type: text-generation
name: text generation
dataset:
name: pubmedqa
type: pubmedqa
metrics:
- name: acc
type: acc
value: 0.616
verified: false
- task:
type: text-generation
name: text generation
dataset:
name: qnli
type: qnli
metrics:
- name: acc
type: acc
value: 0.5072304594545122
verified: false
- task:
type: text-generation
name: text generation
dataset:
name: qqp
type: qqp
metrics:
- name: acc
type: acc
value: 0.3842443729903537
verified: false
- task:
type: text-generation
name: text generation
dataset:
name: race
type: race
metrics:
- name: acc
type: acc
value: 0.3521531100478469
verified: false
- task:
type: text-generation
name: text generation
dataset:
name: rte
type: rte
metrics:
- name: acc
type: acc
value: 0.47653429602888087
verified: false
- task:
type: text-generation
name: text generation
dataset:
name: sciq
type: sciq
metrics:
- name: acc
type: acc
value: 0.892
verified: false
- task:
type: text-generation
name: text generation
dataset:
name: sst
type: sst
metrics:
- name: acc
type: acc
value: 0.5177752293577982
verified: false
- task:
type: text-generation
name: text generation
dataset:
name: triviaqa
type: triviaqa
metrics:
- name: acc
type: acc
value: 0.041633518960487934
verified: false
- task:
type: text-generation
name: text generation
dataset:
name: tydiqa_primary
type: tydiqa_primary
metrics:
- name: acc
type: acc
value: 0.3011337608795236
verified: false
- task:
type: text-generation
name: text generation
dataset:
name: webqs
type: webqs
metrics:
- name: acc
type: acc
value: 0.01673228346456693
verified: false
- task:
type: text-generation
name: text generation
dataset:
name: wic
type: wic
metrics:
- name: acc
type: acc
value: 0.5015673981191222
verified: false
- task:
type: text-generation
name: text generation
dataset:
name: winogrande
type: winogrande
metrics:
- name: acc
type: acc
value: 0.5864246250986582
verified: false
- task:
type: text-generation
name: text generation
dataset:
name: wnli
type: wnli
metrics:
- name: acc
type: acc
value: 0.471830985915493
verified: false
- task:
type: text-generation
name: text generation
dataset:
name: wsc
type: wsc
metrics:
- name: acc
type: acc
value: 0.4423076923076923
verified: false
- task:
type: text-generation
name: text generation
dataset:
name: humaneval
type: humaneval
metrics:
- name: pass@1
type: pass@1
value: 0.15524390243902436
verified: false
- name: pass@10
type: pass@10
value: 0.3220367632383857
verified: false
- name: pass@100
type: pass@100
value: 0.5545431515723145
verified: false
---
<h1 style='text-align: center '>BLOOM LM</h1>
<h2 style='text-align: center '><em>BigScience Large Open-science Open-access Multilingual Language Model</em> </h2>
<h3 style='text-align: center '>Model Card</h3>
<img src="https://s3.amazonaws.com/moonup/production/uploads/1657124309515-5f17f0a0925b9863e28ad517.png" alt="BigScience Logo" width="800" style="margin-left:'auto' margin-right:'auto' display:'block'"/>
Version 1.0 / 26.May.2022
## Table of Contents
1. [Model Details](#model-details)
2. [Uses](#uses)
3. [Training Data](#training-data)
4. [Risks and Limitations](#risks-and-limitations)
5. [Evaluation](#evaluation)
6. [Recommendations](#recommendations)
7. [Glossary and Calculations](#glossary-and-calculations)
8. [More Information](#more-information)
9. [Model Card Authors](#model-card-authors)
## Model Details
### Basics
*This section provides information for anyone who wants to know about the model.*
<details>
<summary>Click to expand</summary> <br/>
**Developed by:** BigScience ([website](https://bigscience.huggingface.co))
* All collaborators are either volunteers or have an agreement with their employer. *(Further breakdown of participants forthcoming.)*
**Model Type:** Transformer-based Language Model
**Version:** 1.0.0
**Languages:** Multiple; see [training data](#training-data)
**License:** RAIL License v1.0 ([link](https://huggingface.co/spaces/bigscience/license))
**Release Date Estimate:** Monday, 11.July.2022
**Send Questions to:** [email protected]
**Cite as:** BigScience, _BigScience Language Open-science Open-access Multilingual (BLOOM) Language Model_. International, May 2021-May 2022
**Funded by:**
* The French government.
* Hugging Face ([website](https://huggingface.co)).
* Organizations of contributors. *(Further breakdown of organizations forthcoming.)*
</details>
### Technical Specifications
*This section provides information for people who work on model development.*
<details>
<summary>Click to expand</summary><br/>
Please see [the BLOOM training README](https://github.com/bigscience-workshop/bigscience/tree/master/train/tr11-176B-ml#readme) for full details on replicating training.
**Model Architecture:** Modified from Megatron-LM GPT2 (see [paper](https://arxiv.org/abs/1909.08053), [BLOOM Megatron code](https://github.com/bigscience-workshop/Megatron-DeepSpeed)):
* Decoder-only architecture
* Layer normalization applied to word embeddings layer (`StableEmbedding`; see [code](https://github.com/facebookresearch/bitsandbytes), [paper](https://arxiv.org/pdf/2110.02861.pdf))
* ALiBI positional encodings (see [paper](https://arxiv.org/pdf/2108.12409.pdf)), with GeLU activation functions
* 3,002,557,440 parameters:
* 642,252,800 embedding parameters
* 30 layers, 32 attention heads
* Hidden layers are 2560-dimensional
* Sequence length of 2048 tokens used (see [BLOOM tokenizer](https://huggingface.co/bigscience/tokenizer), [tokenizer description](#tokenization))
**Objective Function:** Cross Entropy with mean reduction (see [API documentation](https://pytorch.org/docs/stable/generated/torch.nn.CrossEntropyLoss.html#torch.nn.CrossEntropyLoss)).
**Compute infrastructure:** Jean Zay Public Supercomputer, provided by the French government (see [announcement](https://www.enseignementsup-recherche.gouv.fr/fr/signature-du-marche-d-acquisition-de-l-un-des-supercalculateurs-les-plus-puissants-d-europe-46733)).
* Hardware: 384 A100 80GB GPUs (48 nodes):
* Additional 32 A100 80GB GPUs (4 nodes) in reserve
* 8 GPUs per node Using NVLink 4 inter-gpu connects, 4 OmniPath links
* CPU: AMD
* CPU memory: 512GB per node
* GPU memory: 640GB per node
* Inter-node connect: Omni-Path Architecture (OPA)
* NCCL-communications network: a fully dedicated subnet
* Disc IO network: shared network with other types of nodes
* Software:
* Megatron-DeepSpeed ([Github link](https://github.com/bigscience-workshop/Megatron-DeepSpeed))
* DeepSpeed ([Github link](https://github.com/microsoft/DeepSpeed))
* PyTorch (pytorch-1.11 w/ CUDA-11.5; see [Github link](https://github.com/pytorch/pytorch))
* apex ([Github link](https://github.com/NVIDIA/apex))
#### **Training**
Training logs: [Tensorboard link](https://huggingface.co/tensorboard/bigscience/tr11c-2B5-logs)
- Number of epochs: 1 (*current target*)
- Dates:
- Started 11th March, 2022 11:42am PST
- Ended 5th July, 2022
- Estimated cost of training: Equivalent of $2-5M in cloud computing (including preliminary experiments)
- Server training location: Île-de-France, France
#### **Tokenization**
The BLOOM tokenizer ([link](https://huggingface.co/bigscience/tokenizer)) is a learned subword tokenizer trained using:
- A byte-level Byte Pair Encoding (BPE) algorithm
- A simple pre-tokenization rule, no normalization
- A vocabulary size of 250,680
It was trained on a subset of a preliminary version of the corpus using alpha-weighting per language.
</details>
### Environmental Impact
<details>
<summary>Click to expand</summary><br/>
The training supercomputer, Jean Zay ([website](http://www.idris.fr/eng/jean-zay/jean-zay-presentation-eng.html)), uses mostly nuclear energy. The heat generated by it is reused for heating campus housing.
**Estimated carbon emissions:** *(Forthcoming upon completion of training.)*
**Estimated electricity usage:** *(Forthcoming upon completion of training.)*
</details>
<p> </p>
## Uses
*This section addresses questions around how the model is intended to be used, discusses the foreseeable users of the model (including those affected by the model), and describes uses that are considered out of scope or misuse of the model.
It provides information for anyone considering using the model or who is affected by the model.*
<details>
<summary>Click to expand</summary><br/>
### Intended Use
This model is being created in order to enable public research on large language models (LLMs). LLMs are intended to be used for language generation or as a pretrained base model that can be further fine-tuned for specific tasks. Use cases below are not exhaustive.
#### **Direct Use**
- Text generation
- Exploring characteristics of language generated by a language model
- Examples: Cloze tests, counterfactuals, generations with reframings
#### **Downstream Use**
- Tasks that leverage language models include: Information Extraction, Question Answering, Summarization
### Misuse and Out-of-scope Use
*This section addresses what users ought not do with the model.*
See the [BLOOM License](https://huggingface.co/spaces/bigscience/license), Attachment A, for detailed usage restrictions. The below list is non-exhaustive, but lists some easily foreseeable problematic use cases.
#### **Out-of-scope Uses**
Using the model in [high-stakes](#high-stakes) settings is out of scope for this model. The model is not designed for [critical decisions](#critical-decisions) nor uses with any material consequences on an individual's livelihood or wellbeing. The model outputs content that appears factual but is not correct.
##### Out-of-scope Uses Include:
- Usage in biomedical domains, political and legal domains, or finance domains
- Usage for evaluating or scoring individuals, such as for employment, education, or credit
- Applying the model for critical automatic decisions, generating factual content, creating reliable summaries, or generating predictions that must be correct
#### **Misuse**
Intentionally using the model for harm, violating [human rights](#human-rights), or other kinds of malicious activities, is a misuse of this model. This includes:
- Spam generation
- Disinformation and influence operations
- Disparagement and defamation
- Harassment and abuse
- [Deception](#deception)
- Unconsented impersonation and imitation
- Unconsented surveillance
- Generating content without attribution to the model, as specified in the [RAIL License, Use Restrictions](https://huggingface.co/spaces/bigscience/license)
### Intended Users
#### **Direct Users**
- General Public
- Researchers
- Students
- Educators
- Engineers/developers
- Non-commercial entities
- Community advocates, including human and civil rights groups
#### Indirect Users
- Users of derivatives created by Direct Users, such as those using software with an [intended use](#intended-use)
- Users of [Derivatives of the Model, as described in the License](https://huggingface.co/spaces/bigscience/license)
#### Others Affected (Parties Prenantes)
- People and groups referred to by the LLM
- People and groups exposed to outputs of, or decisions based on, the LLM
- People and groups whose original work is included in the LLM
</details>
<p> </p>
## Training Data
*This section provides a high-level overview of the training data. It is relevant for anyone who wants to know the basics of what the model is learning.*
<details>
<summary>Click to expand</summary><br/>
Details for each dataset are provided in individual [Data Cards](https://huggingface.co/spaces/bigscience/BigScienceCorpus).
Training data includes:
- 45 natural languages
- 12 programming languages
- In 1.5TB of pre-processed text, converted into 350B unique tokens (see [the tokenizer section](#tokenization) for more.)
#### **Languages**
The pie chart shows the distribution of languages in training data.
The following table shows the further distribution of Niger-Congo and Indic languages in the training data.
<details>
<summary>Click to expand</summary><br/>
| Niger Congo | Percentage | | Indic | Percentage |
|----------------|------------ |------ |-----------|------------|
| Chi Tumbuka | 0.00002 | | Assamese | 0.01 |
| Kikuyu | 0.00004 | | Odia | 0.04 |
| Bambara | 0.00004 | | Gujarati | 0.04 |
| Akan | 0.00007 | | Marathi | 0.05 |
| Xitsonga | 0.00007 | | Punjabi | 0.05 |
| Sesotho | 0.00007 | | Kannada | 0.06 |
| Chi Chewa | 0.0001 | | Nepali | 0.07 |
| Setswana | 0.0002 | | Telugu | 0.09 |
| Northern Sotho | 0.0002 | | Malayalam | 0.10 |
| Fon | 0.0002 | | Urdu | 0.10 |
| Kirundi | 0.0003 | | Tamil | 0.20 |
| Wolof | 0.0004 | | Bengali | 0.50 |
| Kuganda | 0.0004 | | Hindi | 0.70 |
| Chi Shona | 0.001 |
| Isi Zulu | 0.001 |
| Igbo | 0.001 |
| Xhosa | 0.001 |
| Kinyarwanda | 0.003 |
| Yoruba | 0.006 |
| Swahili | 0.02 |
</details>
The following table shows the distribution of programming languages.
<details>
<summary>Click to expand</summary><br/>
| Extension | Language | Number of files |
|----------------|------------|-----------------|
| java | Java | 5,407,724 |
| php | PHP | 4,942,186 |
| cpp | C++ | 2,503,930 |
| py | Python | 2,435,072 |
| js | JavaScript | 1,905,518 |
| cs | C# | 1,577,347 |
| rb | Ruby | 6,78,413 |
| cc | C++ | 443,054 |
| hpp | C++ | 391,048 |
| lua | Lua | 352,317 |
| go | GO | 227,763 |
| ts | TypeScript | 195,254 |
| C | C | 134,537 |
| scala | Scala | 92,052 |
| hh | C++ | 67,161 |
| H | C++ | 55,899 |
| tsx | TypeScript | 33,107 |
| rs | Rust | 29,693 |
| phpt | PHP | 9,702 |
| c++ | C++ | 1,342 |
| h++ | C++ | 791 |
| php3 | PHP | 540 |
| phps | PHP | 270 |
| php5 | PHP | 166 |
| php4 | PHP | 29 |
</details>
</details>
<p> </p>
## Risks and Limitations
*This section identifies foreseeable harms and misunderstandings.*
<details>
<summary>Click to expand</summary><br/>
Model may:
- Overrepresent some viewpoints and underrepresent others
- Contain stereotypes
- Contain [personal information](#personal-data-and-information)
- Generate:
- Hateful, abusive, or violent language
- Discriminatory or prejudicial language
- Content that may not be appropriate for all settings, including sexual content
- Make errors, including producing incorrect information as if it were factual
- Generate irrelevant or repetitive outputs
</details>
<p> </p>
## Evaluation
*This section describes the evaluation protocols and provides the results.*
<details>
<summary>Click to expand</summary><br/>
### Metrics
*This section describes the different ways performance is calculated and why.*
Includes:
| Metric | Why chosen |
|--------------------|--------------------------------------------------------------------|
| [Perplexity](#perplexity) | Standard metric for quantifying model improvements during training |
| Cross Entropy [Loss](#loss) | Standard objective for language models. |
And multiple different metrics for specific tasks. _(More evaluation metrics forthcoming upon completion of evaluation protocol.)_
### Factors
*This section lists some different aspects of BLOOM models. Its focus is on aspects that are likely to give rise to high variance in model behavior.*
- Language, such as English or Yoruba
- Domain, such as newswire or stories
- Demographic characteristics, such as gender or nationality
### Results
*Results are based on the [Factors](#factors) and [Metrics](#metrics).*
**Zero-shot evaluations:**
See this repository for JSON files: https://github.com/bigscience-workshop/evaluation-results
| Task | Language | Metric | BLOOM-2B5 |
|:----|:----|:----|:----:|
| arc_challenge | eng | acc ↑ | 0.28 |
| arc_easy | eng | acc ↑ | 0.595 |
| axb (Median of 10 prompts) | eng | acc ↑ | 0.443 |
| axg (Median of 10 prompts) | eng | acc ↑ | 0.5 |
| boolq (Median of 11 prompts) | eng | acc ↑ | 0.617 |
| cb (Median of 15 prompts) | eng | acc ↑ | 0.304 |
| cola (Median of 5 prompts) | eng | acc ↑ | 0.611 |
| copa (Median of 9 prompts) | eng | acc ↑ | 0.63 |
| crows_pairs_english (Median of 6 prompts) | eng | acc ↑ | 0.497 |
| crows_pairs_french (Median of 7 prompts) | fra | acc ↑ | 0.503 |
| diabla (Median of 2 prompts) | eng | acc ↑ | 0.289 |
| gsarti/flores_101_afr | afr | byte_perplexity ↓ | 6.501 |
| gsarti/flores_101_amh | amh | byte_perplexity ↓ | 3.973 |
| gsarti/flores_101_ara | ara | byte_perplexity ↓ | 1.808 |
| gsarti/flores_101_asm | asm | byte_perplexity ↓ | 5.699 |
| gsarti/flores_101_ast | ast | byte_perplexity ↓ | 3.925 |
| gsarti/flores_101_azj | azj | byte_perplexity ↓ | 6.943 |
| gsarti/flores_101_bel | bel | byte_perplexity ↓ | 3.614 |
| gsarti/flores_101_ben | ben | byte_perplexity ↓ | 5.121 |
| gsarti/flores_101_bos | bos | byte_perplexity ↓ | 5.653 |
| gsarti/flores_101_bul | bul | byte_perplexity ↓ | 2.701 |
| gsarti/flores_101_cat | cat | byte_perplexity ↓ | 2.305 |
| gsarti/flores_101_ceb | ceb | byte_perplexity ↓ | 6.291 |
| gsarti/flores_101_ces | ces | byte_perplexity ↓ | 5.447 |
| gsarti/flores_101_ckb | ckb | byte_perplexity ↓ | 3.726 |
| gsarti/flores_101_cym | cym | byte_perplexity ↓ | 12.539 |
| gsarti/flores_101_dan | dan | byte_perplexity ↓ | 5.183 |
| gsarti/flores_101_deu | deu | byte_perplexity ↓ | 3.118 |
| gsarti/flores_101_ell | ell | byte_perplexity ↓ | 2.468 |
| gsarti/flores_101_eng | eng | byte_perplexity ↓ | 2.019 |
| gsarti/flores_101_est | est | byte_perplexity ↓ | 9.117 |
| gsarti/flores_101_fas | fas | byte_perplexity ↓ | 3.058 |
| gsarti/flores_101_fin | fin | byte_perplexity ↓ | 6.847 |
| gsarti/flores_101_fra | fra | byte_perplexity ↓ | 1.998 |
| gsarti/flores_101_ful | ful | byte_perplexity ↓ | 11.466 |
| gsarti/flores_101_gle | gle | byte_perplexity ↓ | 8.681 |
| gsarti/flores_101_glg | glg | byte_perplexity ↓ | 3.03 |
| gsarti/flores_101_guj | guj | byte_perplexity ↓ | 4.955 |
| gsarti/flores_101_hau | hau | byte_perplexity ↓ | 10.758 |
| gsarti/flores_101_heb | heb | byte_perplexity ↓ | 3.6 |
| gsarti/flores_101_hin | hin | byte_perplexity ↓ | 4.713 |
| gsarti/flores_101_hrv | hrv | byte_perplexity ↓ | 5.822 |
| gsarti/flores_101_hun | hun | byte_perplexity ↓ | 6.44 |
| gsarti/flores_101_hye | hye | byte_perplexity ↓ | 3.658 |
| gsarti/flores_101_ibo | ibo | byte_perplexity ↓ | 5.565 |
| gsarti/flores_101_ind | ind | byte_perplexity ↓ | 2.16 |
| gsarti/flores_101_isl | isl | byte_perplexity ↓ | 8.082 |
| gsarti/flores_101_ita | ita | byte_perplexity ↓ | 2.969 |
| gsarti/flores_101_jav | jav | byte_perplexity ↓ | 7.057 |
| gsarti/flores_101_jpn | jpn | byte_perplexity ↓ | 2.776 |
| gsarti/flores_101_kam | kam | byte_perplexity ↓ | 11.073 |
| gsarti/flores_101_kan | kan | byte_perplexity ↓ | 5.552 |
| gsarti/flores_101_kat | kat | byte_perplexity ↓ | 2.523 |
| gsarti/flores_101_kaz | kaz | byte_perplexity ↓ | 3.39 |
| gsarti/flores_101_kea | kea | byte_perplexity ↓ | 8.919 |
| gsarti/flores_101_kir | kir | byte_perplexity ↓ | 3.729 |
| gsarti/flores_101_kor | kor | byte_perplexity ↓ | 3.933 |
| gsarti/flores_101_lao | lao | byte_perplexity ↓ | 2.908 |
| gsarti/flores_101_lav | lav | byte_perplexity ↓ | 7.777 |
| gsarti/flores_101_lin | lin | byte_perplexity ↓ | 7.525 |
| gsarti/flores_101_lit | lit | byte_perplexity ↓ | 7.369 |
| gsarti/flores_101_ltz | ltz | byte_perplexity ↓ | 8.801 |
| gsarti/flores_101_lug | lug | byte_perplexity ↓ | 8.483 |
| gsarti/flores_101_luo | luo | byte_perplexity ↓ | 11.976 |
| gsarti/flores_101_mal | mal | byte_perplexity ↓ | 4.616 |
| gsarti/flores_101_mar | mar | byte_perplexity ↓ | 5.483 |
| gsarti/flores_101_mkd | mkd | byte_perplexity ↓ | 2.966 |
| gsarti/flores_101_mlt | mlt | byte_perplexity ↓ | 15.005 |
| gsarti/flores_101_mon | mon | byte_perplexity ↓ | 3.411 |
| gsarti/flores_101_mri | mri | byte_perplexity ↓ | 7.474 |
| gsarti/flores_101_msa | msa | byte_perplexity ↓ | 2.571 |
| gsarti/flores_101_mya | mya | byte_perplexity ↓ | 2.414 |
| gsarti/flores_101_nld | nld | byte_perplexity ↓ | 4.128 |
| gsarti/flores_101_nob | nob | byte_perplexity ↓ | 5.403 |
| gsarti/flores_101_npi | npi | byte_perplexity ↓ | 5.199 |
| gsarti/flores_101_nso | nso | byte_perplexity ↓ | 8.155 |
| gsarti/flores_101_nya | nya | byte_perplexity ↓ | 8.18 |
| gsarti/flores_101_oci | oci | byte_perplexity ↓ | 4.862 |
| gsarti/flores_101_orm | orm | byte_perplexity ↓ | 12.912 |
| gsarti/flores_101_ory | ory | byte_perplexity ↓ | 5.189 |
| gsarti/flores_101_pan | pan | byte_perplexity ↓ | 4.698 |
| gsarti/flores_101_pol | pol | byte_perplexity ↓ | 4.626 |
| gsarti/flores_101_por | por | byte_perplexity ↓ | 1.975 |
| gsarti/flores_101_pus | pus | byte_perplexity ↓ | 4.496 |
| gsarti/flores_101_ron | ron | byte_perplexity ↓ | 4.965 |
| gsarti/flores_101_rus | rus | byte_perplexity ↓ | 2.05 |
| gsarti/flores_101_slk | slk | byte_perplexity ↓ | 6.451 |
| gsarti/flores_101_slv | slv | byte_perplexity ↓ | 6.62 |
| gsarti/flores_101_sna | sna | byte_perplexity ↓ | 8.462 |
| gsarti/flores_101_snd | snd | byte_perplexity ↓ | 5.466 |
| gsarti/flores_101_som | som | byte_perplexity ↓ | 11.959 |
| gsarti/flores_101_spa | spa | byte_perplexity ↓ | 1.897 |
| gsarti/flores_101_srp | srp | byte_perplexity ↓ | 2.871 |
| gsarti/flores_101_swe | swe | byte_perplexity ↓ | 5.055 |
| gsarti/flores_101_swh | swh | byte_perplexity ↓ | 3.697 |
| gsarti/flores_101_tam | tam | byte_perplexity ↓ | 4.539 |
| gsarti/flores_101_tel | tel | byte_perplexity ↓ | 5.807 |
| gsarti/flores_101_tgk | tgk | byte_perplexity ↓ | 3.599 |
| gsarti/flores_101_tgl | tgl | byte_perplexity ↓ | 5.667 |
| gsarti/flores_101_tha | tha | byte_perplexity ↓ | 2.366 |
| gsarti/flores_101_tur | tur | byte_perplexity ↓ | 4.885 |
| gsarti/flores_101_ukr | ukr | byte_perplexity ↓ | 2.724 |
| gsarti/flores_101_umb | umb | byte_perplexity ↓ | 12.767 |
| gsarti/flores_101_urd | urd | byte_perplexity ↓ | 1.98 |
| gsarti/flores_101_uzb | uzb | byte_perplexity ↓ | 12.002 |
| gsarti/flores_101_vie | vie | byte_perplexity ↓ | 1.766 |
| gsarti/flores_101_wol | wol | byte_perplexity ↓ | 9.144 |
| gsarti/flores_101_xho | xho | byte_perplexity ↓ | 7.403 |
| gsarti/flores_101_yor | yor | byte_perplexity ↓ | 5.913 |
| gsarti/flores_101_zho_simpl | zho_simpl | byte_perplexity ↓ | 2.277 |
| gsarti/flores_101_zho_trad | zho_trad | byte_perplexity ↓ | 2.518 |
| gsarti/flores_101_zul | zul | byte_perplexity ↓ | 8.534 |
| headqa | esp | acc ↑ | 0.264 |
| hellaswag | eng | acc ↑ | 0.412 |
| logiqa | eng | acc ↑ | 0.207 |
| mathqa | eng | acc ↑ | 0.25 |
| mc_taco | eng | em ↑ | 0.119 |
| mnli (Median of 15 prompts) | eng | acc ↑ | 0.355 |
| mnli_mismatched (Median of 15 prompts) | eng | acc ↑ | 0.352 |
| mrpc | eng | acc ↑ | 0.586 |
| multirc (Median of 11 prompts) | eng | acc ↑ | 0.538 |
| openbookqa | eng | acc ↑ | 0.216 |
| piqa | eng | acc ↑ | 0.708 |
| prost | eng | acc ↑ | 0.227 |
| pubmedqa | eng | acc ↑ | 0.616 |
| qnli | eng | acc ↑ | 0.507 |
| qqp (Median of 7 prompts) | eng | acc ↑ | 0.384 |
| race | eng | acc ↑ | 0.352 |
| rte (Median of 6 prompts) | eng | acc ↑ | 0.477 |
| sciq | eng | acc ↑ | 0.892 |
| sst (Median of 6 prompts) | eng | acc ↑ | 0.518 |
| triviaqa | eng | acc ↑ | 0.042 |
| tydiqa_primary (Median of 24 prompts) | eng | acc ↑ | 0.301 |
| webqs | eng | acc ↑ | 0.017 |
| wic (Median of 11 prompts) | eng | acc ↑ | 0.502 |
| winogrande | eng | acc ↑ | 0.586 |
| wnli (Median of 6 prompts) | eng | acc ↑ | 0.472 |
| wsc (Median of 11 prompts) | eng | acc ↑ | 0.442 |
| humaneval | python | pass@1 ↑ | 0.155 |
| humaneval | python | pass@10 ↑ | 0.322 |
| humaneval | python | pass@100 ↑ | 0.555 |
**Train-time Evaluation:**
As of 25.May.2022, 15:00 PST:
- Training Loss: 2.0
- Validation Loss: 2.2
- Perplexity: 8.9
</details>
<p> </p>
## Recommendations
*This section provides information on warnings and potential mitigations.*
<details>
<summary>Click to expand</summary><br/>
- Indirect users should be made aware when the content they're working with is created by the LLM.
- Users should be aware of [Risks and Limitations](#risks-and-limitations), and include an appropriate age disclaimer or blocking interface as necessary.
- Models pretrained with the LLM should include an updated Model Card.
- Users of the model should provide mechanisms for those affected to provide feedback, such as an email address for comments.
</details>
<p> </p>
## Glossary and Calculations
*This section defines common terms and how metrics are calculated.*
<details>
<summary>Click to expand</summary><br/>
- <a name="loss">**Loss:**</a> A calculation of the difference between what the model has learned and what the data shows ("groundtruth"). The lower the loss, the better. The training process aims to minimize the loss.
- <a name="perplexity">**Perplexity:**</a> This is based on what the model estimates the probability of new data is. The lower the perplexity, the better. If the model is 100% correct at predicting the next token it will see, then the perplexity is 1. Mathematically this is calculated using entropy.
- <a name="high-stakes">**High-stakes settings:**</a> Such as those identified as "high-risk AI systems" and "unacceptable risk AI systems" in the European Union's proposed [Artificial Intelligence (AI) Act](https://artificialintelligenceact.eu/annexes/).
- <a name="critical-decisions">**Critical decisions:**</a> Such as those defined in [the United States' proposed Algorithmic Accountability Act](https://www.congress.gov/117/bills/s3572/BILLS-117s3572is.pdf).
- <a name="human-rights">**Human rights:**</a> Includes those rights defined in the [Universal Declaration of Human Rights](https://www.un.org/sites/un2.un.org/files/2021/03/udhr.pdf).
- <a name="personal-data-and-information">**Personal Data and Personal Information:**</a> Personal data and information is defined in multiple data protection regulations, such as "[personal data](https://gdpr-info.eu/issues/personal-data/)" in the [European Union's General Data Protection Regulation](https://gdpr-info.eu); and "personal information" in the Republic of South Africa's [Protection of Personal Information Act](https://www.gov.za/sites/default/files/gcis_document/201409/3706726-11act4of2013popi.pdf), The People's Republic of China's [Personal information protection law](http://en.npc.gov.cn.cdurl.cn/2021-12/29/c_694559.htm).
- <a name="sensitive-characteristics">**Sensitive characteristics:**</a> This includes specifically protected categories in human rights (see [UHDR, Article 2](https://www.un.org/sites/un2.un.org/files/2021/03/udhr.pdf)) and personal information regulation (see GDPR, [Article 9; Protection of Personal Information Act, Chapter 1](https://www.gov.za/sites/default/files/gcis_document/201409/3706726-11act4of2013popi.pdf))
- <a name="deception">**Deception:**</a> Doing something to intentionally mislead individuals to believe something that is false, such as by creating deadbots or chatbots on social media posing as real people, or generating text documents without making consumers aware that the text is machine generated.
</details>
<p> </p>
## More Information
<details>
<summary>Click to expand</summary><br/>
### Dataset Creation
Blog post detailing the design choices during the dataset creation: https://bigscience.huggingface.co/blog/building-a-tb-scale-multilingual-dataset-for-language-modeling
### Technical Specifications
Blog post summarizing how the architecture, size, shape, and pre-training duration where selected: https://bigscience.huggingface.co/blog/what-language-model-to-train-if-you-have-two-million-gpu-hours
More details on the architecture/optimizer: https://github.com/bigscience-workshop/bigscience/tree/master/train/tr11-176B-ml
Blog post on the hardware/engineering side: https://bigscience.huggingface.co/blog/which-hardware-to-train-a-176b-parameters-model
Details on the distributed setup used for the training: https://github.com/bigscience-workshop/bigscience/tree/master/train/tr11-176B-ml
Tensorboard updated during the training: https://huggingface.co/bigscience/tr11-176B-ml-logs/tensorboard#scalars&tagFilter=loss
Insights on how to approach training, negative results: https://github.com/bigscience-workshop/bigscience/blob/master/train/lessons-learned.md
Details on the obstacles overcome during the preparation on the engineering side (instabilities, optimization of training throughput, so many technical tricks and questions): https://github.com/bigscience-workshop/bigscience/blob/master/train/tr11-176B-ml/chronicles.md
### Initial Results
Initial prompting experiments using interim checkpoints: https://huggingface.co/spaces/bigscience/bloom-book
</details>
<p> </p>
## Model Card Authors
*Ordered roughly chronologically and by amount of time spent.*
Margaret Mitchell, Giada Pistilli, Yacine Jernite, Ezinwanne Ozoani, Marissa Gerchick, Nazneen Rajani, Sasha Luccioni, Irene Solaiman, Maraim Masoud, Somaieh Nikpoor, Carlos Muñoz Ferrandis, Stas Bekman, Christopher Akiki, Danish Contractor, David Lansky, Angelina McMillan-Major, Tristan Thrush, Suzana Ilić, Gérard Dupont, Shayne Longpre, Manan Dey, Stella Biderman, Douwe Kiela, Emi Baylor, Teven Le Scao, Aaron Gokaslan, Julien Launay, Niklas Muennighoff
|
duyntnet/Hermes-2-Pro-Llama-3-8B-imatrix-GGUF | duyntnet | "2024-05-31T13:50:23Z" | 1,064 | 0 | transformers | [
"transformers",
"gguf",
"imatrix",
"Hermes-2-Pro-Llama-3-8B",
"text-generation",
"en",
"license:other",
"region:us"
] | text-generation | "2024-05-31T10:29:43Z" | ---
license: other
language:
- en
pipeline_tag: text-generation
inference: false
tags:
- transformers
- gguf
- imatrix
- Hermes-2-Pro-Llama-3-8B
---
Quantizations of https://huggingface.co/NousResearch/Hermes-2-Pro-Llama-3-8B
# From original readme
## Prompt Format
Hermes 2 Pro uses ChatML as the prompt format, opening up a much more structured system for engaging the LLM in multi-turn chat dialogue.
System prompts allow steerability and interesting new ways to interact with an LLM, guiding rules, roles, and stylistic choices of the model.
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 Nous Research, who designed me to assist and support users with their needs and requests.<|im_end|>
```
This prompt is available as a [chat template](https://huggingface.co/docs/transformers/main/chat_templating), which means you can format messages using the
`tokenizer.apply_chat_template()` method:
```python
messages = [
{"role": "system", "content": "You are Hermes 2."},
{"role": "user", "content": "Hello, who are you?"}
]
gen_input = tokenizer.apply_chat_template(messages, return_tensors="pt")
model.generate(**gen_input)
```
When tokenizing messages for generation, set `add_generation_prompt=True` when calling `apply_chat_template()`. This will append `<|im_start|>assistant\n` to your prompt, to ensure
that the model continues with an assistant response.
To utilize the prompt format without a system prompt, simply leave the line out.
## Prompt Format for Function Calling
Our model was trained on specific system prompts and structures for Function Calling.
You should use the system role with this message, followed by a function signature json as this example shows here.
```
<|im_start|>system
You are a function calling AI model. You are provided with function signatures within <tools></tools> XML tags. You may call one or more functions to assist with the user query. Don't make assumptions about what values to plug into functions. Here are the available tools: <tools> {"type": "function", "function": {"name": "get_stock_fundamentals", "description": "get_stock_fundamentals(symbol: str) -> dict - Get fundamental data for a given stock symbol using yfinance API.\\n\\n Args:\\n symbol (str): The stock symbol.\\n\\n Returns:\\n dict: A dictionary containing fundamental data.\\n Keys:\\n - \'symbol\': The stock symbol.\\n - \'company_name\': The long name of the company.\\n - \'sector\': The sector to which the company belongs.\\n - \'industry\': The industry to which the company belongs.\\n - \'market_cap\': The market capitalization of the company.\\n - \'pe_ratio\': The forward price-to-earnings ratio.\\n - \'pb_ratio\': The price-to-book ratio.\\n - \'dividend_yield\': The dividend yield.\\n - \'eps\': The trailing earnings per share.\\n - \'beta\': The beta value of the stock.\\n - \'52_week_high\': The 52-week high price of the stock.\\n - \'52_week_low\': The 52-week low price of the stock.", "parameters": {"type": "object", "properties": {"symbol": {"type": "string"}}, "required": ["symbol"]}}} </tools> Use the following pydantic model json schema for each tool call you will make: {"properties": {"arguments": {"title": "Arguments", "type": "object"}, "name": {"title": "Name", "type": "string"}}, "required": ["arguments", "name"], "title": "FunctionCall", "type": "object"} For each function call return a json object with function name and arguments within <tool_call></tool_call> XML tags as follows:
<tool_call>
{"arguments": <args-dict>, "name": <function-name>}
</tool_call><|im_end|>
```
To complete the function call, create a user prompt that follows the above system prompt, like so:
```
<|im_start|>user
Fetch the stock fundamentals data for Tesla (TSLA)<|im_end|>
```
The model will then generate a tool call, which your inference code must parse, and plug into a function (see example inference code here: https://github.com/NousResearch/Hermes-Function-Calling):
```
<|im_start|>assistant
<tool_call>
{"arguments": {"symbol": "TSLA"}, "name": "get_stock_fundamentals"}
</tool_call><|im_end|>
```
Once you parse the tool call, call the api and get the returned values for the call, and pass it back in as a new role, `tool` like so:
```
<|im_start|>tool
<tool_response>
{"name": "get_stock_fundamentals", "content": {'symbol': 'TSLA', 'company_name': 'Tesla, Inc.', 'sector': 'Consumer Cyclical', 'industry': 'Auto Manufacturers', 'market_cap': 611384164352, 'pe_ratio': 49.604652, 'pb_ratio': 9.762013, 'dividend_yield': None, 'eps': 4.3, 'beta': 2.427, '52_week_high': 299.29, '52_week_low': 152.37}}
</tool_response>
<|im_end|>
```
The assistant will then read in that data from the function's response, and generate a natural language response:
```
<|im_start|>assistant
The stock fundamentals data for Tesla (TSLA) are as follows:
- **Symbol**: TSLA
- **Company Name**: Tesla, Inc.
- **Sector**: Consumer Cyclical
- **Industry**: Auto Manufacturers
- **Market Capitalization**: $566,160,130,480
- **Forward Price-to-Earnings Ratio (PE Ratio)**: 42.73
- **Price-to-Book Ratio (PB Ratio)**: 9.04
- **Dividend Yield**: N/A
- **Trailing Earnings Per Share (EPS)**: $4.3
- **Beta Value of the Stock**: 2.42
- **52-Week High Price of the Stock**: $299.29
- **52-Week Low Price of the Stock**: $152.37
This information provides a snapshot of Tesla's financial position and performance based on the fundamental data obtained from the yfinance API. It shows that Tesla has a substantial market capitalization and a relatively high P/E and P/B ratio compared to other stocks in its industry. The company does not pay a dividend at the moment, which is reflected by a 'Dividend Yield' of 'None'. The Beta value indicates that Tesla's stock has a moderate level of volatility relative to the market. The 52-week high and low prices give an idea of the stock's range over the past year. This data can be useful when assessing investment opportunities and making investment decisions.<|im_end|>
```
## Prompt Format for JSON Mode / Structured Outputs
Our model was also trained on a specific system prompt for Structured Outputs, which should respond with **only** a json object response, in a specific json schema.
Your schema can be made from a pydantic object using our codebase, with the standalone script `jsonmode.py` available here: https://github.com/NousResearch/Hermes-Function-Calling/tree/main
```
<|im_start|>system
You are a helpful assistant that answers in JSON. Here's the json schema you must adhere to:\n<schema>\n{schema}\n</schema><|im_end|>
```
Given the {schema} that you provide, it should follow the format of that json to create it's response, all you have to do is give a typical user prompt, and it will respond in JSON. |
Shengkun/LLama2-7B-Structural-Prune-1.5x-32-20kCalib | Shengkun | "2024-06-07T21:29:44Z" | 1,064 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-06-07T20:29:33Z" | ---
license: apache-2.0
---
|
VietAI/gpt-neo-1.3B-vietnamese-news | VietAI | "2022-08-07T14:32:07Z" | 1,063 | 26 | transformers | [
"transformers",
"pytorch",
"gpt_neo",
"text-generation",
"causal-lm",
"gpt",
"vi",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-generation | "2022-03-02T23:29:05Z" | ---
language:
- vi
tags:
- pytorch
- causal-lm
- gpt
---
# GPT-Neo 1.3B on Vietnamese News
Details will be available soon.
For more information, please contact [email protected] (Dương) / [email protected] (Thành) / [email protected] (Bình).
### How to use
```python
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("VietAI/gpt-neo-1.3B-vietnamese-news")
model = AutoModelForCausalLM.from_pretrained("VietAI/gpt-neo-1.3B-vietnamese-news", low_cpu_mem_usage=True)
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
model.to(device)
prompt = "Tiềm năng của trí tuệ nhân tạo" # your input sentence
input_ids = tokenizer(prompt, return_tensors="pt")['input_ids'].to(device)
gen_tokens = model.generate(
input_ids,
max_length=max_length,
do_sample=True,
temperature=0.9,
top_k=20,
)
gen_text = tokenizer.batch_decode(gen_tokens)[0]
print(gen_text)
``` |
microsoft/layoutlmv3-base-chinese | microsoft | "2022-09-16T03:25:46Z" | 1,063 | 52 | transformers | [
"transformers",
"pytorch",
"layoutlmv3",
"zh",
"arxiv:2204.08387",
"license:cc-by-nc-sa-4.0",
"endpoints_compatible",
"region:us"
] | null | "2022-06-16T04:38:00Z" | ---
language: zh
license: cc-by-nc-sa-4.0
---
# LayoutLMv3
[Microsoft Document AI](https://www.microsoft.com/en-us/research/project/document-ai/) | [GitHub](https://aka.ms/layoutlmv3)
## Model description
LayoutLMv3 is a pre-trained multimodal Transformer for Document AI with unified text and image masking. The simple unified architecture and training objectives make LayoutLMv3 a general-purpose pre-trained model. For example, LayoutLMv3 can be fine-tuned for both text-centric tasks, including form understanding, receipt understanding, and document visual question answering, and image-centric tasks such as document image classification and document layout analysis.
[LayoutLMv3: Pre-training for Document AI with Unified Text and Image Masking](https://arxiv.org/abs/2204.08387)
Yupan Huang, Tengchao Lv, Lei Cui, Yutong Lu, Furu Wei, Preprint 2022.
## Results
| Dataset | Language | Precision | Recall | F1 |
|---------|-----------|------------|------|--------|
| [XFUND](https://github.com/doc-analysis/XFUND) | ZH | 0.8980 | 0.9435 | 0.9202 |
| Dataset | Subject | Test Time | Name | School | Examination Number | Seat Number | Class | Student Number | Grade | Score | **Mean** |
|---------|:------------|:------:|:--------:|:--------:|:--------:|:--------:|:--------:|:--------:|:--------:|:--------:|:--------:|
| [EPHOIE](https://github.com/HCIILAB/EPHOIE) | 98.99 | 100.0 | 99.77 | 99.2 | 100.0 | 100.0 | 98.82 | 99.78 | 98.31 | 97.27 | 99.21 |
## Citation
If you find LayoutLM useful in your research, please cite the following paper:
```
@inproceedings{huang2022layoutlmv3,
author={Yupan Huang and Tengchao Lv and Lei Cui and Yutong Lu and Furu Wei},
title={LayoutLMv3: Pre-training for Document AI with Unified Text and Image Masking},
booktitle={Proceedings of the 30th ACM International Conference on Multimedia},
year={2022}
}
```
## License
The content of this project itself is licensed under the [Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)](https://creativecommons.org/licenses/by-nc-sa/4.0/).
Portions of the source code are based on the [transformers](https://github.com/huggingface/transformers) project.
[Microsoft Open Source Code of Conduct](https://opensource.microsoft.com/codeofconduct) |
tinkoff-ai/ruDialoGPT-medium | tinkoff-ai | "2022-11-07T13:34:43Z" | 1,063 | 33 | transformers | [
"transformers",
"pytorch",
"gpt2",
"conversational",
"ru",
"arxiv:2001.09977",
"license:mit",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null | "2022-07-12T14:52:19Z" | ---
license: mit
widget:
- text: "@@ПЕРВЫЙ@@ привет @@ВТОРОЙ@@ привет @@ПЕРВЫЙ@@ как дела? @@ВТОРОЙ@@"
example_title: "how r u"
- text: "@@ПЕРВЫЙ@@ что ты делал на выходных? @@ВТОРОЙ@@"
example_title: "wyd"
language:
- ru
tags:
- conversational
---
This generation model is based on [sberbank-ai/rugpt3medium_based_on_gpt2](https://huggingface.co/sberbank-ai/rugpt3medium_based_on_gpt2). It's trained on large corpus of dialog data and can be used for buildning generative conversational agents
The model was trained with context size 3
On a private validation set we calculated metrics introduced in [this paper](https://arxiv.org/pdf/2001.09977.pdf):
- Sensibleness: Crowdsourcers were asked whether model's response makes sense given the context
- Specificity: Crowdsourcers were asked whether model's response is specific for given context, in other words we don't want our model to give general and boring responses
- SSA which is the average of two metrics above (Sensibleness Specificity Average)
| | sensibleness | specificity | SSA |
|:----------------------------------------------------|---------------:|--------------:|------:|
| [tinkoff-ai/ruDialoGPT-small](https://huggingface.co/tinkoff-ai/ruDialoGPT-small) | 0.64 | 0.5 | 0.57 |
| [tinkoff-ai/ruDialoGPT-medium](https://huggingface.co/tinkoff-ai/ruDialoGPT-medium) | 0.78 | 0.69 | 0.735 |
How to use:
```python
import torch
from transformers import AutoTokenizer, AutoModelWithLMHead
tokenizer = AutoTokenizer.from_pretrained('tinkoff-ai/ruDialoGPT-medium')
model = AutoModelWithLMHead.from_pretrained('tinkoff-ai/ruDialoGPT-medium')
inputs = tokenizer('@@ПЕРВЫЙ@@ привет @@ВТОРОЙ@@ привет @@ПЕРВЫЙ@@ как дела? @@ВТОРОЙ@@', return_tensors='pt')
generated_token_ids = model.generate(
**inputs,
top_k=10,
top_p=0.95,
num_beams=3,
num_return_sequences=3,
do_sample=True,
no_repeat_ngram_size=2,
temperature=1.2,
repetition_penalty=1.2,
length_penalty=1.0,
eos_token_id=50257,
max_new_tokens=40
)
context_with_response = [tokenizer.decode(sample_token_ids) for sample_token_ids in generated_token_ids]
context_with_response
``` |
timm/swinv2_large_window12to16_192to256.ms_in22k_ft_in1k | timm | "2024-02-10T23:31:06Z" | 1,063 | 0 | timm | [
"timm",
"pytorch",
"safetensors",
"image-classification",
"dataset:imagenet-1k",
"dataset:imagenet-22k",
"arxiv:2111.09883",
"license:mit",
"region:us"
] | image-classification | "2023-03-18T03:33:56Z" | ---
license: mit
library_name: timm
tags:
- image-classification
- timm
datasets:
- imagenet-1k
- imagenet-22k
---
# Model card for swinv2_large_window12to16_192to256.ms_in22k_ft_in1k
A Swin Transformer V2 image classification model. Pretrained on ImageNet-22k and fine-tuned on ImageNet-1k by paper authors.
## Model Details
- **Model Type:** Image classification / feature backbone
- **Model Stats:**
- Params (M): 196.7
- GMACs: 47.8
- Activations (M): 121.5
- Image size: 256 x 256
- **Papers:**
- Swin Transformer V2: Scaling Up Capacity and Resolution: https://arxiv.org/abs/2111.09883
- **Original:** https://github.com/microsoft/Swin-Transformer
- **Dataset:** ImageNet-1k
- **Pretrain Dataset:** ImageNet-22k
## 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('swinv2_large_window12to16_192to256.ms_in22k_ft_in1k', pretrained=True)
model = model.eval()
# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(img).unsqueeze(0)) # unsqueeze single image into batch of 1
top5_probabilities, top5_class_indices = torch.topk(output.softmax(dim=1) * 100, k=5)
```
### 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(
'swinv2_large_window12to16_192to256.ms_in22k_ft_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. for swin_base_patch4_window7_224 (NHWC output)
# torch.Size([1, 56, 56, 128])
# torch.Size([1, 28, 28, 256])
# torch.Size([1, 14, 14, 512])
# torch.Size([1, 7, 7, 1024])
# e.g. for swinv2_cr_small_ns_224 (NCHW output)
# torch.Size([1, 96, 56, 56])
# torch.Size([1, 192, 28, 28])
# torch.Size([1, 384, 14, 14])
# torch.Size([1, 768, 7, 7])
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(
'swinv2_large_window12to16_192to256.ms_in22k_ft_in1k',
pretrained=True,
num_classes=0, # remove classifier nn.Linear
)
model = model.eval()
# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(img).unsqueeze(0)) # output is (batch_size, num_features) shaped tensor
# or equivalently (without needing to set num_classes=0)
output = model.forward_features(transforms(img).unsqueeze(0))
# output is unpooled (ie.e a (batch_size, H, W, num_features) tensor for swin / swinv2
# or (batch_size, num_features, H, W) for swinv2_cr
output = model.forward_head(output, pre_logits=True)
# output is (batch_size, num_features) 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).
## Citation
```bibtex
@inproceedings{liu2021swinv2,
title={Swin Transformer V2: Scaling Up Capacity and Resolution},
author={Ze Liu and Han Hu and Yutong Lin and Zhuliang Yao and Zhenda Xie and Yixuan Wei and Jia Ning and Yue Cao and Zheng Zhang and Li Dong and Furu Wei and Baining Guo},
booktitle={International Conference on Computer Vision and Pattern Recognition (CVPR)},
year={2022}
}
```
```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}}
}
```
|
AISimplyExplained/Vakil-7B | AISimplyExplained | "2024-01-23T23:42:47Z" | 1,063 | 2 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"legal",
"en",
"dataset:AISimplyExplained/LegalReasoningIndianLaw",
"license:mit",
"autotrain_compatible",
"text-generation-inference",
"4-bit",
"bitsandbytes",
"region:us"
] | text-generation | "2024-01-23T12:50:25Z" | ---
license: mit
datasets:
- AISimplyExplained/LegalReasoningIndianLaw
language:
- en
library_name: transformers
tags:
- legal
inference: false
---
# Vakil-7B Model Card
### Model Description
Vakil-7B is a state-of-the-art language model fine-tuned on the `AISimplyExplained/LegalReasoningIndianLaw` dataset for specialization in the nuances and complexities of Indian law. It is designed to provide legal professionals, students, and researchers with insights and assistance in understanding legal documents and queries within the context of the Indian legal system.
Developed by Asmi Gulati and Bhuvi Jain, this tool aims to enhance the accessibility and analysis of legal texts, driving forward the digital transformation in the legal domain.
### Model Specifications
- **Developed by:** Asmi Gulati and Bhuvi Jain
- **Model type:** Fine-tuned language model
- **Language(s) (NLP):** English, with a focus on Indian legal terminology
- **License:** MIT
- **Finetuned from model:** `transformers` library model
## Directions for Usage
```python
!pip install "unsloth[colab_ampere] @ git+https://github.com/unslothai/unsloth.git"
!pip install "git+https://github.com/huggingface/transformers.git"
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("AISimplyExplained/Vakil-7B")
model = AutoModelForCausalLM.from_pretrained("AISimplyExplained/Vakil-7B")
```
### Intended Use
Vakil-7B is intended for direct use by legal professionals and researchers who need to interact with Indian legal text. It is designed to assist with legal research, drafting, and education by providing AI-driven analysis and insights.
### Out-of-Scope Use
Vakil-7B is not designed to replace professional legal advice or to be used as a standalone decision-making tool. It should be used as an aid in the legal research and analysis process, not as the sole source of guidance.
## Bias, Risks, and Limitations
Users should be aware of the inherent limitations of AI in interpreting legal text. Vakil-7B, while sophisticated, may not capture all nuances and should be used in conjunction with professional judgment. |
BryanSwk/LaserPipe-7B-SLERP | BryanSwk | "2024-02-08T03:49:32Z" | 1,063 | 3 | transformers | [
"transformers",
"safetensors",
"gguf",
"mistral",
"text-generation",
"mergekit",
"merge",
"base_model:OpenPipe/mistral-ft-optimized-1218",
"base_model:macadeliccc/WestLake-7B-v2-laser-truthy-dpo",
"license:cc-by-nc-4.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-02-07T13:30:26Z" | ---
base_model:
- OpenPipe/mistral-ft-optimized-1218
- macadeliccc/WestLake-7B-v2-laser-truthy-dpo
library_name: transformers
tags:
- mergekit
- merge
license: cc-by-nc-4.0
---
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
I have provided a .gguf Q4_K_M for cpu inference as well.
This repository serves as a learning experience for myself to experiment with merged models & gguf conversions.
Credits:
* mergekit
* llama.cpp
## Merge Details
### Merge Method
This model was merged using the SLERP merge method.
### Models Merged
The following models were included in the merge:
* [OpenPipe/mistral-ft-optimized-1218](https://huggingface.co/OpenPipe/mistral-ft-optimized-1218)
* [macadeliccc/WestLake-7B-v2-laser-truthy-dpo](https://huggingface.co/macadeliccc/WestLake-7B-v2-laser-truthy-dpo)
### Configuration
The following YAML configuration was used to produce this model:
```yaml
slices:
- sources:
- model: OpenPipe/mistral-ft-optimized-1218
layer_range: [0, 32]
- model: macadeliccc/WestLake-7B-v2-laser-truthy-dpo
layer_range: [0, 32]
merge_method: slerp
base_model: OpenPipe/mistral-ft-optimized-1218
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
``` |
robinsmits/Mistral-Instruct-7B-v0.2-ChatAlpacaV2-4bit | robinsmits | "2024-02-13T07:10:47Z" | 1,063 | 5 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"conversational",
"unsloth",
"chatalpaca",
"en",
"dataset:robinsmits/ChatAlpaca-20K",
"arxiv:1910.09700",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"text-generation-inference",
"4-bit",
"bitsandbytes",
"region:us"
] | text-generation | "2024-02-10T11:19:50Z" | ---
language:
- en
license: apache-2.0
library_name: transformers
tags:
- mistral
- conversational
- unsloth
- chatalpaca
datasets:
- robinsmits/ChatAlpaca-20K
inference: false
pipeline_tag: text-generation
model-index:
- name: Mistral-Instruct-7B-v0.2-ChatAlpacaV2-4bit
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: 62.12
name: normalized accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=robinsmits/Mistral-Instruct-7B-v0.2-ChatAlpacaV2-4bit
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: 84.55
name: normalized accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=robinsmits/Mistral-Instruct-7B-v0.2-ChatAlpacaV2-4bit
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: 60.66
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=robinsmits/Mistral-Instruct-7B-v0.2-ChatAlpacaV2-4bit
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: 67.29
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=robinsmits/Mistral-Instruct-7B-v0.2-ChatAlpacaV2-4bit
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: 77.11
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=robinsmits/Mistral-Instruct-7B-v0.2-ChatAlpacaV2-4bit
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: 40.33
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=robinsmits/Mistral-Instruct-7B-v0.2-ChatAlpacaV2-4bit
name: Open LLM Leaderboard
---
# 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]
# [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_robinsmits__Mistral-Instruct-7B-v0.2-ChatAlpacaV2-4bit)
| Metric |Value|
|---------------------------------|----:|
|Avg. |65.34|
|AI2 Reasoning Challenge (25-Shot)|62.12|
|HellaSwag (10-Shot) |84.55|
|MMLU (5-Shot) |60.66|
|TruthfulQA (0-shot) |67.29|
|Winogrande (5-shot) |77.11|
|GSM8k (5-shot) |40.33|
|
cs-giung/vit-base-patch16-imagenet21k-augreg | cs-giung | "2024-06-01T14:04:47Z" | 1,063 | 0 | transformers | [
"transformers",
"safetensors",
"vit",
"image-classification",
"arxiv:2010.11929",
"arxiv:2106.10270",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | image-classification | "2024-05-31T16:47:28Z" | ---
license: apache-2.0
---
# Vision Transformer
Vision Transformer (ViT) model pre-trained on ImageNet-21k (14 million images, 21,843 classes) at resolution 224x224. It was introduced in the paper [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://arxiv.org/abs/2010.11929) and further enhanced in the follow-up paper [How to train your ViT? Data, Augmentation, and Regularization in Vision Transformers](https://arxiv.org/abs/2106.10270).
The weights were converted from the `B_16-i21k-300ep-lr_0.001-aug_medium1-wd_0.1-do_0.0-sd_0.0.npz` file in [GCS buckets](https://console.cloud.google.com/storage/browser/vit_models/augreg/) presented in the [original repository](https://github.com/google-research/vision_transformer).
|
MarsupialAI/IxChel-L3-12B_iMatrix_GGUF | MarsupialAI | "2024-06-11T20:07:45Z" | 1,063 | 0 | null | [
"gguf",
"region:us"
] | null | "2024-06-11T18:29:15Z" | iMatrix GGUFs for https://huggingface.co/MarsupialAI/IxChel-L3-12B
iMatrix generated using Kalomaze's groups_merged.txt |
simsim314/Hermes-13b-hf-shards | simsim314 | "2023-06-10T14:00:15Z" | 1,062 | 0 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"license:gpl",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-06-10T09:00:21Z" | ---
license: gpl
---
Sharded version of [This model](https://huggingface.co/NousResearch/Nous-Hermes-13b). Use the tokenizer from there
```
from transformers import LlamaTokenizer, AutoModelForCausalLM
tokenizer = LlamaTokenizer.from_pretrained("NousResearch/Nous-Hermes-13b")
model = AutoModelForCausalLM.from_pretrained("simsim314/Hermes-13b-hf-shards")
``` |
yeen214/llama2_7b_platypus_tuning | yeen214 | "2023-10-16T00:33:59Z" | 1,062 | 0 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"en",
"dataset:garage-bAInd/Open-Platypus",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-10-16T00:06:51Z" | ---
license: mit
datasets:
- garage-bAInd/Open-Platypus
language:
- en
metrics:
- accuracy
---
finetuning model(instruction tuning) with garage-bAInd/Open-Platypus
* base model : https://huggingface.co/meta-llama/Llama-2-7b
About llama2
Llama 2 is a collection of pretrained and fine-tuned generative text models ranging in scale from 7 billion to 70 billion parameters.
This is the repository for the 7B finetuned model with Open-Platypus dataset. |
aari1995/germeo-7b-awq | aari1995 | "2024-04-02T11:31:32Z" | 1,062 | 2 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"awq",
"autoawq",
"de",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"4-bit",
"region:us"
] | text-generation | "2024-01-05T17:10:31Z" | ---
language:
- de
pipeline_tag: text-generation
tags:
- awq
- autoawq
license: apache-2.0
---
# ***WIP***
(Please bear with me, this model will get better and get a license soon)
_Hermes + Leo + German AWQ = Germeo_
# Germeo-7B-AWQ
A German-English understanding, but German-only speaking model merged from [Hermeo-7B](https://https://huggingface.co/malteos/hermeo-7b).
### Model details
- **Merged from:** [leo-mistral-hessianai-7b-chat](https://huggingface.co/LeoLM/leo-mistral-hessianai-7b-chat) and [DPOpenHermes-7B-v2](https://huggingface.co/openaccess-ai-collective/DPOpenHermes-7B-v2)
- **Model type:** Causal decoder-only transformer language model
- **Languages:** German replies with English Understanding Capabilities
- **Calibration Data:** [LeoLM/OpenSchnabeltier](https://huggingface.co/datasets/LeoLM/OpenSchnabeltier)
### Quantization Procedure and Use Case:
The speciality of this model is that it solely replies in German, independently from the system message or prompt.
Within the AWQ-process I introduced OpenSchnabeltier as calibration data for the model to stress the importance of German Tokens.
### Usage
Setup in autoawq
```python
# setup [autoawq](https://github.com/casper-hansen/AutoAWQ)
from awq import AutoAWQForCausalLM
from transformers import AutoTokenizer, TextStreamer
quant_path = "aari1995/germeo-7b-awq"
# Load model
model = AutoAWQForCausalLM.from_quantized(quant_path, fuse_layers=True)
tokenizer = AutoTokenizer.from_pretrained(quant_path, trust_remote_code=True)
```
Setup in transformers (works in colab)
```python
# pip install [autoawq](https://github.com/casper-hansen/AutoAWQ) and pip install --upgrade transformers
from transformers import AutoModelForCausalLM, AutoTokenizer, TextStreamer
quant_path = "aari1995/germeo-7b-awq"
# Load model
model = AutoModelForCausalLM.from_pretrained(quant_path, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(quant_path, trust_remote_code=True)
```
### Inference:
```python
streamer = TextStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True)
# Convert prompt to tokens
prompt_template = """<|im_start|>system
Du bist ein hilfreicher Assistent.<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant"""
prompt = "Schreibe eine Stellenanzeige für Data Scientist bei AXA!"
tokens = tokenizer(
prompt_template.format(prompt=prompt),
return_tensors='pt'
).input_ids.cuda()
# Generate output
generation_output = model.generate(
tokens,
streamer=streamer,
max_new_tokens=1012
)
# tokenizer.decode(generation_output.flatten())
```
### FAQ
#### The model continues after the reply with user inputs:
To solve this, you need to implement a custom stopping criteria:
```python
from transformers import StoppingCriteria
class GermeoStoppingCriteria(StoppingCriteria):
def __init__(self, target_sequence, prompt):
self.target_sequence = target_sequence
self.prompt=prompt
def __call__(self, input_ids, scores, **kwargs):
# Get the generated text as a string
generated_text = tokenizer.decode(input_ids[0])
generated_text = generated_text.replace(self.prompt,'')
# Check if the target sequence appears in the generated text
if self.target_sequence in generated_text:
return True # Stop generation
return False # Continue generation
def __len__(self):
return 1
def __iter__(self):
yield self
```
This then expects your input prompt (formatted as given into the model), and a stopping criteria, in this case the im_end token. Simply add it to the generation:
```python
generation_output = model.generate(
tokens,
streamer=streamer,
max_new_tokens=1012,
stopping_criteria=GermeoStoppingCriteria("<|im_end|>", prompt_template.format(prompt=prompt))
)
```
### Acknowledgements and Special Thanks
- Thank you [malteos](https://https://huggingface.co/malteos/) for hermeo, without this it would not be possible! (and all your other contributions)
- Thanks to the authors of the base models: [Mistral](https://mistral.ai/), [LAION](https://laion.ai/), [HessianAI](https://hessian.ai/), [Open Access AI Collective](https://huggingface.co/openaccess-ai-collective), [@teknium](https://huggingface.co/teknium), [@bjoernp](https://huggingface.co/bjoernp)
- Also [@bjoernp](https://huggingface.co/bjoernp) thank you for your contribution and LeoLM for OpenSchnabeltier.
## Evaluation and Benchmarks (German only)
### German benchmarks
| **German tasks:** | **MMLU-DE** | **Hellaswag-DE** | **ARC-DE** |**Average** |
|-------------------------------|-------------|---------------|--------------|--------------|
| **Models / Few-shots:** | _(5 shots)_ | _(10 shots)_ | _(24 shots)_ | |
| _7B parameters_ | | | | |
| llama-2-7b | 0.400 | 0.513 | 0.381 | 0.431 |
| leo-hessianai-7b | 0.400 | 0.609 | 0.429 | 0.479 |
| bloom-6b4-clp-german | 0.274 | 0.550 | 0.351 | 0.392 |
| mistral-7b | **0.524** | 0.588 | 0.473 | 0.528 |
| leo-mistral-hessianai-7b | 0.481 | 0.663 | 0.485 | 0.543 |
| leo-mistral-hessianai-7b-chat | 0.458 | 0.617 | 0.465 | 0.513 |
| DPOpenHermes-7B-v2 | 0.517 | 0.603 | 0.515 | 0.545 |
| hermeo-7b | 0.511 | **0.668** | **0.528** | **0.569** |
| **germeo-7b-awq (this model)**| 0.522 | 0.651 | 0.514 | 0.563 |
| _13B parameters_ | | | | |
| llama-2-13b | 0.469 | 0.581 | 0.468 | 0.506 |
| leo-hessianai-13b | **0.486** | **0.658** | **0.509** | **0.551** |
| _70B parameters_ | | | | |
| llama-2-70b | 0.597 | 0.674 | 0.561 | 0.611 |
| leo-hessianai-70b | **0.653** | **0.721** | **0.600** | **0.658** |
### German reply rate benchmark
The fraction of German reply rates according to [this benchmark](https://huggingface.co/spaces/floleuerer/german_llm_outputs)
| **Models:** | **German Response Rate** |
|-------------------------|-------------------------|
| hermeo-7b | tba |
| **germeo-7b-awq (this model)**| tba |
### Additional Benchmarks:
TruthfulQA-DE: 0.508 |
asapse/DIOD-Mistral-0.2 | asapse | "2024-01-19T14:28:44Z" | 1,062 | 0 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"conversational",
"en",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-01-19T13:31:42Z" | ---
license: apache-2.0
language:
- en
---
# DIOD-Mistral-0.2
Fine-tuning [OpenHermes-2-Mistral-7B](https://huggingface.co/teknium/OpenHermes-2-Mistral-7B) with [argilla/distilabel-intel-orca-dpo-pairs](https://huggingface.co/datasets/argilla/distilabel-intel-orca-dpo-pairs) |
AmberYifan/safe-spin-iter0 | AmberYifan | "2024-04-21T03:22:49Z" | 1,062 | 0 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"alignment-handbook",
"generated_from_trainer",
"conversational",
"dataset:AmberYifan/spin_iter0",
"dataset:AmberYifan/safe_spin_iter0",
"base_model:alignment-handbook/zephyr-7b-sft-full",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-04-21T03:21:01Z" | ---
license: apache-2.0
base_model: alignment-handbook/zephyr-7b-sft-full
tags:
- alignment-handbook
- generated_from_trainer
datasets:
- AmberYifan/spin_iter0
- AmberYifan/safe_spin_iter0
model-index:
- name: iter0_safe
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. -->
# iter0_safe
This model is a fine-tuned version of [alignment-handbook/zephyr-7b-sft-full](https://huggingface.co/alignment-handbook/zephyr-7b-sft-full) on the AmberYifan/spin_iter0 and the AmberYifan/safe_spin_iter0 datasets.
## 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: 4
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- total_train_batch_size: 32
- total_eval_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 3
### Training results
### Framework versions
- Transformers 4.37.0
- Pytorch 2.1.2+cu121
- Datasets 2.14.6
- Tokenizers 0.15.2
|
lllyasviel/sd-controlnet-seg | lllyasviel | "2023-04-24T22:30:42Z" | 1,061 | 50 | diffusers | [
"diffusers",
"safetensors",
"art",
"controlnet",
"stable-diffusion",
"image-to-image",
"arxiv:2302.05543",
"base_model:runwayml/stable-diffusion-v1-5",
"license:openrail",
"region:us"
] | image-to-image | "2023-02-24T07:13:29Z" | ---
license: openrail
base_model: runwayml/stable-diffusion-v1-5
tags:
- art
- controlnet
- stable-diffusion
- image-to-image
---
# Controlnet - *Image Segmentation Version*
ControlNet is a neural network structure to control diffusion models by adding extra conditions.
This checkpoint corresponds to the ControlNet conditioned on **Image Segmentation**.
It can be used in combination with [Stable Diffusion](https://huggingface.co/docs/diffusers/api/pipelines/stable_diffusion/text2img).
## Model Details
- **Developed by:** Lvmin Zhang, Maneesh Agrawala
- **Model type:** Diffusion-based text-to-image generation model
- **Language(s):** English
- **License:** [The CreativeML OpenRAIL M license](https://huggingface.co/spaces/CompVis/stable-diffusion-license) is an [Open RAIL M license](https://www.licenses.ai/blog/2022/8/18/naming-convention-of-responsible-ai-licenses), adapted from the work that [BigScience](https://bigscience.huggingface.co/) and [the RAIL Initiative](https://www.licenses.ai/) are jointly carrying in the area of responsible AI licensing. See also [the article about the BLOOM Open RAIL license](https://bigscience.huggingface.co/blog/the-bigscience-rail-license) on which our license is based.
- **Resources for more information:** [GitHub Repository](https://github.com/lllyasviel/ControlNet), [Paper](https://arxiv.org/abs/2302.05543).
- **Cite as:**
@misc{zhang2023adding,
title={Adding Conditional Control to Text-to-Image Diffusion Models},
author={Lvmin Zhang and Maneesh Agrawala},
year={2023},
eprint={2302.05543},
archivePrefix={arXiv},
primaryClass={cs.CV}
}
## Introduction
Controlnet was proposed in [*Adding Conditional Control to Text-to-Image Diffusion Models*](https://arxiv.org/abs/2302.05543) by
Lvmin Zhang, Maneesh Agrawala.
The abstract reads as follows:
*We present a neural network structure, ControlNet, to control pretrained large diffusion models to support additional input conditions.
The ControlNet learns task-specific conditions in an end-to-end way, and the learning is robust even when the training dataset is small (< 50k).
Moreover, training a ControlNet is as fast as fine-tuning a diffusion model, and the model can be trained on a personal devices.
Alternatively, if powerful computation clusters are available, the model can scale to large amounts (millions to billions) of data.
We report that large diffusion models like Stable Diffusion can be augmented with ControlNets to enable conditional inputs like edge maps, segmentation maps, keypoints, etc.
This may enrich the methods to control large diffusion models and further facilitate related applications.*
## Released Checkpoints
The authors released 8 different checkpoints, each trained with [Stable Diffusion v1-5](https://huggingface.co/runwayml/stable-diffusion-v1-5)
on a different type of conditioning:
| Model Name | Control Image Overview| Control Image Example | Generated Image Example |
|---|---|---|---|
|[lllyasviel/sd-controlnet-canny](https://huggingface.co/lllyasviel/sd-controlnet-canny)<br/> *Trained with canny edge detection* | A monochrome image with white edges on a black background.|<a href="https://huggingface.co/takuma104/controlnet_dev/blob/main/gen_compare/control_images/converted/control_bird_canny.png"><img width="64" style="margin:0;padding:0;" src="https://huggingface.co/takuma104/controlnet_dev/resolve/main/gen_compare/control_images/converted/control_bird_canny.png"/></a>|<a href="https://huggingface.co/takuma104/controlnet_dev/resolve/main/gen_compare/output_images/diffusers/output_bird_canny_1.png"><img width="64" src="https://huggingface.co/takuma104/controlnet_dev/resolve/main/gen_compare/output_images/diffusers/output_bird_canny_1.png"/></a>|
|[lllyasviel/sd-controlnet-depth](https://huggingface.co/lllyasviel/sd-controlnet-depth)<br/> *Trained with Midas depth estimation* |A grayscale image with black representing deep areas and white representing shallow areas.|<a href="https://huggingface.co/takuma104/controlnet_dev/blob/main/gen_compare/control_images/converted/control_vermeer_depth.png"><img width="64" src="https://huggingface.co/takuma104/controlnet_dev/resolve/main/gen_compare/control_images/converted/control_vermeer_depth.png"/></a>|<a href="https://huggingface.co/takuma104/controlnet_dev/resolve/main/gen_compare/output_images/diffusers/output_vermeer_depth_2.png"><img width="64" src="https://huggingface.co/takuma104/controlnet_dev/resolve/main/gen_compare/output_images/diffusers/output_vermeer_depth_2.png"/></a>|
|[lllyasviel/sd-controlnet-hed](https://huggingface.co/lllyasviel/sd-controlnet-hed)<br/> *Trained with HED edge detection (soft edge)* |A monochrome image with white soft edges on a black background.|<a href="https://huggingface.co/takuma104/controlnet_dev/blob/main/gen_compare/control_images/converted/control_bird_hed.png"><img width="64" src="https://huggingface.co/takuma104/controlnet_dev/resolve/main/gen_compare/control_images/converted/control_bird_hed.png"/></a>|<a href="https://huggingface.co/takuma104/controlnet_dev/resolve/main/gen_compare/output_images/diffusers/output_bird_hed_1.png"><img width="64" src="https://huggingface.co/takuma104/controlnet_dev/resolve/main/gen_compare/output_images/diffusers/output_bird_hed_1.png"/></a> |
|[lllyasviel/sd-controlnet-mlsd](https://huggingface.co/lllyasviel/sd-controlnet-mlsd)<br/> *Trained with M-LSD line detection* |A monochrome image composed only of white straight lines on a black background.|<a href="https://huggingface.co/takuma104/controlnet_dev/blob/main/gen_compare/control_images/converted/control_room_mlsd.png"><img width="64" src="https://huggingface.co/takuma104/controlnet_dev/resolve/main/gen_compare/control_images/converted/control_room_mlsd.png"/></a>|<a href="https://huggingface.co/takuma104/controlnet_dev/resolve/main/gen_compare/output_images/diffusers/output_room_mlsd_0.png"><img width="64" src="https://huggingface.co/takuma104/controlnet_dev/resolve/main/gen_compare/output_images/diffusers/output_room_mlsd_0.png"/></a>|
|[lllyasviel/sd-controlnet-normal](https://huggingface.co/lllyasviel/sd-controlnet-normal)<br/> *Trained with normal map* |A [normal mapped](https://en.wikipedia.org/wiki/Normal_mapping) image.|<a href="https://huggingface.co/takuma104/controlnet_dev/blob/main/gen_compare/control_images/converted/control_human_normal.png"><img width="64" src="https://huggingface.co/takuma104/controlnet_dev/resolve/main/gen_compare/control_images/converted/control_human_normal.png"/></a>|<a href="https://huggingface.co/takuma104/controlnet_dev/resolve/main/gen_compare/output_images/diffusers/output_human_normal_1.png"><img width="64" src="https://huggingface.co/takuma104/controlnet_dev/resolve/main/gen_compare/output_images/diffusers/output_human_normal_1.png"/></a>|
|[lllyasviel/sd-controlnet_openpose](https://huggingface.co/lllyasviel/sd-controlnet-openpose)<br/> *Trained with OpenPose bone image* |A [OpenPose bone](https://github.com/CMU-Perceptual-Computing-Lab/openpose) image.|<a href="https://huggingface.co/takuma104/controlnet_dev/blob/main/gen_compare/control_images/converted/control_human_openpose.png"><img width="64" src="https://huggingface.co/takuma104/controlnet_dev/resolve/main/gen_compare/control_images/converted/control_human_openpose.png"/></a>|<a href="https://huggingface.co/takuma104/controlnet_dev/resolve/main/gen_compare/output_images/diffusers/output_human_openpose_0.png"><img width="64" src="https://huggingface.co/takuma104/controlnet_dev/resolve/main/gen_compare/output_images/diffusers/output_human_openpose_0.png"/></a>|
|[lllyasviel/sd-controlnet_scribble](https://huggingface.co/lllyasviel/sd-controlnet-scribble)<br/> *Trained with human scribbles* |A hand-drawn monochrome image with white outlines on a black background.|<a href="https://huggingface.co/takuma104/controlnet_dev/blob/main/gen_compare/control_images/converted/control_vermeer_scribble.png"><img width="64" src="https://huggingface.co/takuma104/controlnet_dev/resolve/main/gen_compare/control_images/converted/control_vermeer_scribble.png"/></a>|<a href="https://huggingface.co/takuma104/controlnet_dev/resolve/main/gen_compare/output_images/diffusers/output_vermeer_scribble_0.png"><img width="64" src="https://huggingface.co/takuma104/controlnet_dev/resolve/main/gen_compare/output_images/diffusers/output_vermeer_scribble_0.png"/></a> |
|[lllyasviel/sd-controlnet_seg](https://huggingface.co/lllyasviel/sd-controlnet-seg)<br/>*Trained with semantic segmentation* |An [ADE20K](https://groups.csail.mit.edu/vision/datasets/ADE20K/)'s segmentation protocol image.|<a href="https://huggingface.co/takuma104/controlnet_dev/blob/main/gen_compare/control_images/converted/control_room_seg.png"><img width="64" src="https://huggingface.co/takuma104/controlnet_dev/resolve/main/gen_compare/control_images/converted/control_room_seg.png"/></a>|<a href="https://huggingface.co/takuma104/controlnet_dev/resolve/main/gen_compare/output_images/diffusers/output_room_seg_1.png"><img width="64" src="https://huggingface.co/takuma104/controlnet_dev/resolve/main/gen_compare/output_images/diffusers/output_room_seg_1.png"/></a> |
## Example
It is recommended to use the checkpoint with [Stable Diffusion v1-5](https://huggingface.co/runwayml/stable-diffusion-v1-5) as the checkpoint
has been trained on it.
Experimentally, the checkpoint can be used with other diffusion models such as dreamboothed stable diffusion.
1. Let's install `diffusers` and related packages:
```
$ pip install diffusers transformers accelerate
```
2. We'll need to make use of a color palette here as described in [semantic_segmentation](https://huggingface.co/docs/transformers/tasks/semantic_segmentation):
```py
palette = np.asarray([
[0, 0, 0],
[120, 120, 120],
[180, 120, 120],
[6, 230, 230],
[80, 50, 50],
[4, 200, 3],
[120, 120, 80],
[140, 140, 140],
[204, 5, 255],
[230, 230, 230],
[4, 250, 7],
[224, 5, 255],
[235, 255, 7],
[150, 5, 61],
[120, 120, 70],
[8, 255, 51],
[255, 6, 82],
[143, 255, 140],
[204, 255, 4],
[255, 51, 7],
[204, 70, 3],
[0, 102, 200],
[61, 230, 250],
[255, 6, 51],
[11, 102, 255],
[255, 7, 71],
[255, 9, 224],
[9, 7, 230],
[220, 220, 220],
[255, 9, 92],
[112, 9, 255],
[8, 255, 214],
[7, 255, 224],
[255, 184, 6],
[10, 255, 71],
[255, 41, 10],
[7, 255, 255],
[224, 255, 8],
[102, 8, 255],
[255, 61, 6],
[255, 194, 7],
[255, 122, 8],
[0, 255, 20],
[255, 8, 41],
[255, 5, 153],
[6, 51, 255],
[235, 12, 255],
[160, 150, 20],
[0, 163, 255],
[140, 140, 140],
[250, 10, 15],
[20, 255, 0],
[31, 255, 0],
[255, 31, 0],
[255, 224, 0],
[153, 255, 0],
[0, 0, 255],
[255, 71, 0],
[0, 235, 255],
[0, 173, 255],
[31, 0, 255],
[11, 200, 200],
[255, 82, 0],
[0, 255, 245],
[0, 61, 255],
[0, 255, 112],
[0, 255, 133],
[255, 0, 0],
[255, 163, 0],
[255, 102, 0],
[194, 255, 0],
[0, 143, 255],
[51, 255, 0],
[0, 82, 255],
[0, 255, 41],
[0, 255, 173],
[10, 0, 255],
[173, 255, 0],
[0, 255, 153],
[255, 92, 0],
[255, 0, 255],
[255, 0, 245],
[255, 0, 102],
[255, 173, 0],
[255, 0, 20],
[255, 184, 184],
[0, 31, 255],
[0, 255, 61],
[0, 71, 255],
[255, 0, 204],
[0, 255, 194],
[0, 255, 82],
[0, 10, 255],
[0, 112, 255],
[51, 0, 255],
[0, 194, 255],
[0, 122, 255],
[0, 255, 163],
[255, 153, 0],
[0, 255, 10],
[255, 112, 0],
[143, 255, 0],
[82, 0, 255],
[163, 255, 0],
[255, 235, 0],
[8, 184, 170],
[133, 0, 255],
[0, 255, 92],
[184, 0, 255],
[255, 0, 31],
[0, 184, 255],
[0, 214, 255],
[255, 0, 112],
[92, 255, 0],
[0, 224, 255],
[112, 224, 255],
[70, 184, 160],
[163, 0, 255],
[153, 0, 255],
[71, 255, 0],
[255, 0, 163],
[255, 204, 0],
[255, 0, 143],
[0, 255, 235],
[133, 255, 0],
[255, 0, 235],
[245, 0, 255],
[255, 0, 122],
[255, 245, 0],
[10, 190, 212],
[214, 255, 0],
[0, 204, 255],
[20, 0, 255],
[255, 255, 0],
[0, 153, 255],
[0, 41, 255],
[0, 255, 204],
[41, 0, 255],
[41, 255, 0],
[173, 0, 255],
[0, 245, 255],
[71, 0, 255],
[122, 0, 255],
[0, 255, 184],
[0, 92, 255],
[184, 255, 0],
[0, 133, 255],
[255, 214, 0],
[25, 194, 194],
[102, 255, 0],
[92, 0, 255],
])
```
3. Having defined the color palette we can now run the whole segmentation + controlnet generation code:
```py
from transformers import AutoImageProcessor, UperNetForSemanticSegmentation
from PIL import Image
import numpy as np
import torch
from diffusers import StableDiffusionControlNetPipeline, ControlNetModel, UniPCMultistepScheduler
from diffusers.utils import load_image
image_processor = AutoImageProcessor.from_pretrained("openmmlab/upernet-convnext-small")
image_segmentor = UperNetForSemanticSegmentation.from_pretrained("openmmlab/upernet-convnext-small")
image = load_image("https://huggingface.co/lllyasviel/sd-controlnet-seg/resolve/main/images/house.png").convert('RGB')
pixel_values = image_processor(image, return_tensors="pt").pixel_values
with torch.no_grad():
outputs = image_segmentor(pixel_values)
seg = image_processor.post_process_semantic_segmentation(outputs, target_sizes=[image.size[::-1]])[0]
color_seg = np.zeros((seg.shape[0], seg.shape[1], 3), dtype=np.uint8) # height, width, 3
for label, color in enumerate(palette):
color_seg[seg == label, :] = color
color_seg = color_seg.astype(np.uint8)
image = Image.fromarray(color_seg)
controlnet = ControlNetModel.from_pretrained(
"lllyasviel/sd-controlnet-seg", torch_dtype=torch.float16
)
pipe = StableDiffusionControlNetPipeline.from_pretrained(
"runwayml/stable-diffusion-v1-5", controlnet=controlnet, safety_checker=None, torch_dtype=torch.float16
)
pipe.scheduler = UniPCMultistepScheduler.from_config(pipe.scheduler.config)
# Remove if you do not have xformers installed
# see https://huggingface.co/docs/diffusers/v0.13.0/en/optimization/xformers#installing-xformers
# for installation instructions
pipe.enable_xformers_memory_efficient_attention()
pipe.enable_model_cpu_offload()
image = pipe("house", image, num_inference_steps=20).images[0]
image.save('./images/house_seg_out.png')
```
### Training
The semantic segmentation model was trained on 164K segmentation-image, caption pairs from ADE20K. The model was trained for 200 GPU-hours with Nvidia A100 80G using Stable Diffusion 1.5 as a base model.
### Blog post
For more information, please also have a look at the [official ControlNet Blog Post](https://huggingface.co/blog/controlnet). |
Manbarll/llama2-22B-daydreamer-v3-GPTQ-4bits-32g-ActOrder | Manbarll | "2023-08-15T13:16:32Z" | 1,061 | 0 | transformers | [
"transformers",
"llama",
"text-generation",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-08-15T07:17:27Z" | Entry not found |
SeanLee97/angle-llama-7b-nli-v2 | SeanLee97 | "2023-10-31T00:18:08Z" | 1,061 | 16 | peft | [
"peft",
"en",
"dataset:multi_nli",
"dataset:snli",
"arxiv:2309.12871",
"license:mit",
"region:us"
] | null | "2023-10-21T02:23:35Z" | ---
library_name: peft
license: mit
datasets:
- multi_nli
- snli
language:
- en
metrics:
- spearmanr
---
# AnglE📐: Angle-optimized Text Embeddings
> It is Angle 📐, not Angel 👼.
🔥 A New SOTA Model for Semantic Textual Similarity!
Github: https://github.com/SeanLee97/AnglE
<a href="https://arxiv.org/abs/2309.12871">
<img src="https://img.shields.io/badge/Arxiv-2306.06843-yellow.svg?style=flat-square" alt="https://arxiv.org/abs/2309.12871" />
</a>
[](https://paperswithcode.com/sota/semantic-textual-similarity-on-sick-r-1?p=angle-optimized-text-embeddings)
[](https://paperswithcode.com/sota/semantic-textual-similarity-on-sts16?p=angle-optimized-text-embeddings)
[](https://paperswithcode.com/sota/semantic-textual-similarity-on-sts15?p=angle-optimized-text-embeddings)
[](https://paperswithcode.com/sota/semantic-textual-similarity-on-sts14?p=angle-optimized-text-embeddings)
[](https://paperswithcode.com/sota/semantic-textual-similarity-on-sts13?p=angle-optimized-text-embeddings)
[](https://paperswithcode.com/sota/semantic-textual-similarity-on-sts12?p=angle-optimized-text-embeddings)
[](https://paperswithcode.com/sota/semantic-textual-similarity-on-sts-benchmark?p=angle-optimized-text-embeddings)
**STS Results**
| Model | STS12 | STS13 | STS14 | STS15 | STS16 | STSBenchmark | SICKRelatedness | Avg. |
| ------- |-------|-------|-------|-------|-------|--------------|-----------------|-------|
| [SeanLee97/angle-llama-7b-nli-20231027](https://huggingface.co/SeanLee97/angle-llama-7b-nli-20231027) | 78.68 | 90.58 | 85.49 | 89.56 | 86.91 | 88.92 | 81.18 | 85.90 |
| [SeanLee97/angle-llama-7b-nli-v2](https://huggingface.co/SeanLee97/angle-llama-7b-nli-v2) | 79.00 | 90.56 | 85.79 | 89.43 | 87.00 | 88.97 | 80.94 | **85.96** |
## Usage
1) use AnglE
```bash
python -m pip install -U angle-emb
```
```python
from angle_emb import AnglE, Prompts
# init
angle = AnglE.from_pretrained('NousResearch/Llama-2-7b-hf', pretrained_lora_path='SeanLee97/angle-llama-7b-nli-v2')
# set prompt
print('All predefined prompts:', Prompts.list_prompts())
angle.set_prompt(prompt=Prompts.A)
print('prompt:', angle.prompt)
# encode text
vec = angle.encode({'text': 'hello world'}, to_numpy=True)
print(vec)
vecs = angle.encode([{'text': 'hello world1'}, {'text': 'hello world2'}], to_numpy=True)
print(vecs)
```
2) use transformers
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel, PeftConfig
peft_model_id = 'SeanLee97/angle-llama-7b-nli-20231027'
config = PeftConfig.from_pretrained(peft_model_id)
tokenizer = AutoTokenizer.from_pretrained(config.base_model_name_or_path)
model = AutoModelForCausalLM.from_pretrained(config.base_model_name_or_path).bfloat16().cuda()
model = PeftModel.from_pretrained(model, peft_model_id).cuda()
def decorate_text(text: str):
return f'Summarize sentence "{text}" in one word:"'
inputs = 'hello world!'
tok = tokenizer([decorate_text(inputs)], return_tensors='pt')
for k, v in tok.items():
tok[k] = v.cuda()
vec = model(output_hidden_states=True, **tok).hidden_states[-1][:, -1].float().detach().cpu().numpy()
print(vec)
```
## Citation
You are welcome to use our code and pre-trained models. If you use our code and pre-trained models, please support us by citing our work as follows:
```bibtex
@article{li2023angle,
title={AnglE-Optimized Text Embeddings},
author={Li, Xianming and Li, Jing},
journal={arXiv preprint arXiv:2309.12871},
year={2023}
}
``` |
migtissera/Tess-XS-v1.2 | migtissera | "2023-11-25T18:15:20Z" | 1,061 | 2 | transformers | [
"transformers",
"pytorch",
"mistral",
"text-generation",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-11-23T21:49:34Z" | ---
license: apache-2.0
---
# Note:
This version is experimental and have been depracated. Please use the stable release Tess-XS-v1.3-yarn-128K: https://huggingface.co/migtissera/Tess-XS-v1-3-yarn-128K
# Tess
Tess, short for Tessoro/Tessoso, is a general purpose Large Language Model series. Tess-XS-v1.1 was trained on the Mistral-7B base.
# Prompt Format:
```
SYSTEM: <ANY SYSTEM CONTEXT>
USER:
ASSISTANT:
```
|
ChrisWilson011016/5FpnXrSQT6kkkYFGTE8z32JXMBYNmxReTcoqyRjEiiACWhDr_vgg | ChrisWilson011016 | "2024-02-29T14:12:05Z" | 1,061 | 0 | keras | [
"keras",
"region:us"
] | null | "2024-02-24T15:09:46Z" | Entry not found |
KoboldAI/LLaMA2-13B-Holomax-GGUF | KoboldAI | "2023-09-08T20:12:40Z" | 1,060 | 7 | null | [
"gguf",
"license:other",
"region:us"
] | null | "2023-09-08T19:45:55Z" | ---
license: other
---
# LLaMA 2 Holomax 13B - The writers version of Mythomax
This is an expansion merge to the well praised Mythomax model from Gryphe (60%) using MrSeeker's KoboldAI Holodeck model (40%)
The goal of this model is to enhance story writing capabilities while preserving the desirable traits of the Mythomax model as much as possible (It does limit chat reply length).
Testers found that this model passes the InteracTV benchmark, was useful for story writing, chatting and text adventures using Instruction mode.
Preservation of factual knowledge has not been tested since we expect the original to be better in those use cases as this merge was focussed on fiction.
## Credits
This merge is not possible without the following models and model authors (Thanks to all of you for your work!)
Mythomax by Gryphe:
- Mythologic-L2 by Gryphe:
- - Hermes by Nous-Research
- Chronos V2 by Elinas
- Airoboros m2.0 by Jondurbin
- Huginn by Face of Goonery:
- - Hermes by Nous-Research
- StableBeluga by StabilityAI
- Airoboros by Jondurbin
- Chronos by Elinas
- Limarp by Lemonila
Holodeck by Mr.Seeker
## Guidelines
This model is designed to be flexible, it should be able to be used as a co-writing model, as well as a variety of instruct formats (Tested with Alpaca) and regular chatting both augmented with traditional formatting and instruct formatting.
The Alpaca format is as follows:
```
### Instruction:
Instruction goes here
### Response:
```
But if you have a different preferred format that works on one of the models above it will likely still work.
## License
After publishing the model we were informed that one of the origin models upstream was uploaded under the AGPLv3, it is currently unknown what effects this has on this model because all weights have been modified and none of the original weights are intact.
At the moment of publishing (and writing this message) both merged models Holodeck and Mythomax were licensed Llama2, therefore the Llama2 license applies to this model.
However, Holodeck contains a non-commercial clause and may only be used for research or private use, while Limarp is licensed AGPLv3.
AGPLv3 conflicts with the commercial usage restrictions of the Llama2 license, therefore we assume this aspect does not apply and the authors indended for commercial usage restrictions to be permitted.
As a result we have decided to leave the model available for public download on the assumption that all involved authors intend for it to be licensed with commercial restrictions / llama2 restrictions in place, but with the further rights and freedoms the AGPLv3 grants a user.
If HF informs us that this assumption is incorrect and requests us to take this model down, we will republish the model in the form of the original merging script that was used to create the end result.
To comply with the AGPLv3 aspect the "source" of this model is as follows (Because this model is made on a binary level, we can only provide the script that created the model):
```
import json
import os
import shutil
import subprocess
from tkinter.filedialog import askdirectory, askopenfilename
import torch
from colorama import Fore, Style, init
from transformers import (AutoModel, AutoModelForCausalLM, AutoTokenizer,
LlamaConfig, LlamaForCausalLM, LlamaTokenizer,
PreTrainedTokenizer, PreTrainedTokenizerFast)
newline = '\n'
def clear_console():
if os.name == "nt": # For Windows
subprocess.call("cls", shell=True)
else: # For Linux and macOS
subprocess.call("clear", shell=True)
clear_console()
print(f"{Fore.YELLOW}Starting script, please wait...{Style.RESET_ALL}")
#mixer output settings
blend_ratio = 0.4 #setting to 0 gives first model, and 1 gives second model
fp16 = False #perform operations in fp16. Saves memory, but CPU inference will not be possible.
always_output_fp16 = True #if true, will output fp16 even if operating in fp32
max_shard_size = "10000MiB" #set output shard size
force_cpu = True #only use cpu
load_sharded = True #load both models shard by shard
print(f"Blend Ratio set to: {Fore.GREEN}{blend_ratio}{Style.RESET_ALL}")
print(f"Operations in fp16 is: {Fore.GREEN}{fp16}{Style.RESET_ALL}")
print(f"Save Result in fp16: {Fore.GREEN}{always_output_fp16}{Style.RESET_ALL}")
print(f"CPU RAM Only: {Fore.GREEN}{force_cpu}{Style.RESET_ALL}{newline}")
#test generation settings, only for fp32
deterministic_test = True #determines if outputs are always the same
test_prompt = "" #test prompt for generation. only for fp32. set to empty string to skip generating.
test_max_length = 32 #test generation length
blend_ratio_b = 1.0 - blend_ratio
def get_model_info(model):
with torch.no_grad():
outfo = ""
cntent = 0
outfo += "\n==============================\n"
for name, para in model.named_parameters():
cntent += 1
outfo += ('{}: {}'.format(name, para.shape))+"\n"
outfo += ("Num Entries: " + str(cntent))+"\n"
outfo += ("==============================\n")
return outfo
def merge_models(model1,model2):
with torch.no_grad():
tensornum = 0
for p1, p2 in zip(model1.parameters(), model2.parameters()):
p1 *= blend_ratio
p2 *= blend_ratio_b
p1 += p2
tensornum += 1
print("Merging tensor "+str(tensornum))
pass
def read_index_filenames(sourcedir):
index = json.load(open(sourcedir + '/pytorch_model.bin.index.json','rt'))
fl = []
for k,v in index['weight_map'].items():
if v not in fl:
fl.append(v)
return fl
print("Opening file dialog, please select FIRST model directory...")
model_path1 = "Gryphe/MythoMax-L2-13b"
print(f"First Model is: {model_path1}")
print("Opening file dialog, please select SECOND model directory...")
model_path2 = "KoboldAI/LLAMA2-13B-Holodeck-1"
print(f"Second Model is: {model_path2}")
print("Opening file dialog, please select OUTPUT model directory...")
model_path3 = askdirectory(title="Select Output Directory of merged model")
print(f"Merged Save Directory is: {model_path3}{newline}")
if not model_path1 or not model_path2:
print("\nYou must select two directories containing models to merge and one output directory. Exiting.")
exit()
with torch.no_grad():
if fp16:
torch.set_default_dtype(torch.float16)
else:
torch.set_default_dtype(torch.float32)
device = torch.device("cuda") if (torch.cuda.is_available() and not force_cpu) else torch.device("cpu")
print(device)
print("Loading Model 1...")
model1 = AutoModelForCausalLM.from_pretrained(model_path1) #,torch_dtype=torch.float16
model1 = model1.to(device)
model1.eval()
print("Model 1 Loaded. Dtype: " + str(model1.dtype))
print("Loading Model 2...")
model2 = AutoModelForCausalLM.from_pretrained(model_path2) #,torch_dtype=torch.float16
model2 = model2.to(device)
model2.eval()
print("Model 2 Loaded. Dtype: " + str(model2.dtype))
# Saving for posterity reasons, handy for troubleshooting if model result is broken
# #ensure both models have the exact same layout
# m1_info = get_model_info(model1)
# m2_info = get_model_info(model2)
# if m1_info != m2_info:
# print("Model 1 Info: " + m1_info)
# print("Model 2 Info: " + m2_info)
# print("\nERROR:\nThe two selected models are not compatible! They must have identical structure!")
# exit()
print("Merging models...")
merge_models(model1,model2)
if model_path3:
print("Saving new model...")
if always_output_fp16 and not fp16:
model1.half()
model1.save_pretrained(model_path3, max_shard_size=max_shard_size)
print("\nSaved to: " + model_path3)
print("\nCopying files to: " + model_path3)
files_to_copy = ["tokenizer.model", "special_tokens_map.json", "tokenizer_config.json", "vocab.json", "merges.txt"]
for filename in files_to_copy:
src_path = os.path.join(model_path1, filename)
dst_path = os.path.join(model_path3, filename)
try:
shutil.copy2(src_path, dst_path)
except FileNotFoundError:
print("\nFile " + filename + " not found in" + model_path1 + ". Skipping.")
else:
print("\nOutput model was not saved as no output path was selected.")
print("\nScript Completed.")
``` |
Sao10K/Euryale-Inverted-L2-70B | Sao10K | "2023-09-12T11:28:52Z" | 1,060 | 6 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"en",
"license:cc-by-nc-4.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-09-11T15:57:25Z" | ---
license: cc-by-nc-4.0
language:
- en
---
<img src="https://images7.alphacoders.com/921/921311.jpg" style="width: 70%; min-width: 300px; display: block; margin: auto;">
An experimental merging of Several Models using 3 merging methods. Ties-Merge, BlockMerge_Gradient [& SLERP Variant] as well as SLERP.
5 Models included Inside, 2 LORAs.
***Early release because I'll be busy for the next month. Incomplete but workable, see below.***
***INVERT VARIANT***
SISTER MODEL HERE: [Euryale-L2-70B](https://huggingface.co/Sao10K/Euryale-L2-70B)
*Same concept as Stheno & Stheno Inverted, at different densities, weights and gradients.*
*Illustration for final gradient merge cannot be shown, each of the tensors had a different ratio applied to it.*
<br>Test Checklist:
<br>Censorship - NSFL no Issues
<br>Writing - Good Prose and Writing Quality
<br>NSFW - Yes
<br>IQ Level - Slightly dumber than Euryale. Even worse at Coding / Math though. Good for RP. As a general assistant? She's not the most accurate.
<br>Formatting - Markdown Formatting Issues, Able to Follow Statuses well.
<br>Most formats could work, but my tests have all been done in Alpaca format and it works well.
```
### Instruction:
Your instruction or question here.
For roleplay purposes, I suggest the following - Write <CHAR NAME>'s next reply in a chat between <YOUR NAME> and <CHAR NAME>. Write a single reply only.
### Response:
```
<br>My 7th Attempt. Incomplete so far, early release.
<br>Timeline Goals:
<br> Apply COT to model.
<br> Apply the RP LoRA I'm working on to model.
<br> Further tinker and test for potential better combinations.
Once Again, thanks to [Chargoddard](https://huggingface.co/chargoddard) and [Gryphe](https://huggingface.co/Gryphe) for their scripts, and @Vali for modifying some of the scripts provided to implement SLERP on a Cloud GPU Service.
Thanks to @gradientputri for partially sponsoring half of the compute costs for my Runpod usage.
Thanks to the original model creators too!
```
Art by wada_kazu / わだかず (pixiv page private?)
```
### LICENSE
License
This model is strictly non-commercial (cc-by-nc-4.0) use only which takes priority over the LLAMA 2 COMMUNITY LICENSE AGREEMENT.
The "Model" is completely free (ie. base model, derivates, merges/mixes) to use for non-commercial purposes as long as the the included cc-by-nc-4.0 license in any parent repository, and the non-commercial use statute remains, regardless of other models' licences.
*Non-Commercial due to parent models having the above license.*
Parent Models with this license:
<br>[garage-bAInd/Platypus2-70B-instruct](https://huggingface.co/garage-bAInd/Platypus2-70B-instruct)
<br>[elinas/chronos-70b-v2](https://huggingface.co/elinas/chronos-70b-v2)
### MODELS USED:
<br>[elinas/chronos-70b-v2](https://huggingface.co/elinas/chronos-70b-v2)
<br>[NousResearch/Nous-Hermes-Llama2-70b](https://huggingface.co/NousResearch/Nous-Hermes-Llama2-70b)
<br>[jondurbin/airoboros-l2-70b-2.1-creative](https://huggingface.co/jondurbin/airoboros-l2-70b-2.1-creative)
<br>[garage-bAInd/Platypus2-70B-instruct](https://huggingface.co/garage-bAInd/Platypus2-70B-instruct)
<br>[MayaPH/GodziLLa2-70B](https://huggingface.co/MayaPH/GodziLLa2-70B)
**LORAS**
<br>[nRuaif/fiction.live-Kimiko-V2-70B](https://huggingface.co/nRuaif/fiction.live-Kimiko-V2-70B)
<br>[lemonilia/limarp-llama2-v2](https://huggingface.co/lemonilia/limarp-llama2-v2) |
jondurbin/airoboros-c34b-3.1.2 | jondurbin | "2023-10-22T11:45:41Z" | 1,060 | 6 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"conversational",
"dataset:jondurbin/airoboros-3.1",
"license:llama2",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-10-20T08:52:28Z" | ---
license: llama2
datasets:
- jondurbin/airoboros-3.1
---
### Overview
Another experimental model, using mostly sythetic data generated by [airoboros](https://github.com/jondurbin/airoboros)
#### IMPORTANT NOTE - llama-2 chat format!!!
This models uses llama-2 chat format, rather than vicuna style user/assistant!
This is a breaking change, although most inference systems support llama-2 chat templating.
See prompt format below for all of the details.
#### Highlights
A model built on [airoboros-3.1 dataset](https://hf.co/datasets/jondurbin/airoboros-3.1), which is a continuation of [airoboros-3.0 dataset](https://hf.co/datasets/jondurbin/airoboros-3,0) with the following extras:
* More MathJSON, now ~17k items - math questions, prefixed with __"Create a MathJSON solution to the following:"__, which then outputs a JSON between __`<mathjson>`__ and __`</mathjson>`__ tags, which can be parsed and passed to a deterministic library to perform calculations.
* Log information extraction (e.g. getting the list of paths/IPs/etc. from apache logs)
* Anonymization, e.g. removing names, IP addresses, and/or dates from text.
* Chat introspection - multi-turn chats that have random questions injected asking about the character's descriptions, the setting of the chat, or things previously said, to make sure the model uses the system prompt and or chat history.
* Multi-step instructions with acknowledgement (see below)
* De-censorship data (not published)
This is a fairly general purpose model, but focuses heavily on instruction following, rather than casual chat/roleplay.
Huge thank you to the folks over at [a16z](https://a16z.com/) for sponsoring the costs associated with building models and associated tools!
### Prompt format
The prompt format is llama-2 chat.
```
[INST] <<SYS>>
You are a helpful, unbiased, uncensored assistant.
<</SYS>>
{prompt} [/INST]
```
For multi-turn, the prompt format is as follows:
```
[INST] <<SYS>>
You are a helful, unbiased, uncensored assistant.
<</SYS>>
{prompt 0} [/INST] {response 0} </s><s>[INST] {prompt 1} [/INST] {response 1} </s><s>...[INST] {prompt N} [/INST]
```
The prompt template is included in the tokenizer config, and can use the huggingface tokenizer `apply_chat_template` method, e.g.:
```
import transformers
tokenizer = transformers.AutoTokenizer.from_pretrained('jondurbin/airoboros-l2-70b-3.1')
chat = [
{"role": "system", "content": "You are Bob, a friendly AI assistant."},
{"role": "user", "content": "Hello, how are you?"},
{"role": "assistant", "content": "I'm doing great. How can I help you today?"},
{"role": "user", "content": "I'd like to show off how chat templating works!"},
]
print(tokenizer.apply_chat_template(chat, tokenize=False))
```
### Helpful usage tips
#### MathJSON
Ask mathematical questions, prefixed with "Create a MathJSON solution to the following:", and you should get output with a formula that can be executed by https://cortexjs.io/compute-engine/
I also made a (really quite hacky, incomplete, semi-functional) python version that works for most expressions, see [mathjson.py](https://github.com/jondurbin/airoboros/blob/mathjson/airoboros/mathjson.py)
__Use a very low temperature!__
Example:
```
[INST] <<SYS>>
You are an assistant with vast knowledge in all things math.
<</SYS>>
Create a MathJSON solution to the following: Calculate the area of a circle with radius of 17.2456cm. Include your reasoning. [/INST]
```
Output:
```
The area (A) of a circle is given by the formula A = πr², where r is the radius of the circle. Since the radius is given in centimeters, we need to convert it to meters first. We know that 1 meter equals 100 centimeters. Therefore, we can represent the radius as: r = 17.2456 cm * 100/1.
Once we have the radius in meters, we can calculate the area of the circle using the formula A = πr².
Solution as MathJSON:
<mathjson>
[
"Multiply",
"Pi",
[
"Power",
17.2456,
2
]
]
</mathjson>
```
You can then validate the JSON between `<mathjson>` and `</mathjson>`, then pass the parsed JSON to compute-engine JS or the `evaluate` function in mathjson.py to calculate the response.
#### Context obedient question answering
By obedient, I mean the model was trained to ignore what it thinks it knows, and uses the context to answer the question. The model was also tuned to limit the values to the provided context as much as possible to reduce hallucinations.
The format for a closed-context prompt is as follows:
```
BEGININPUT
BEGINCONTEXT
[key0: value0]
[key1: value1]
... other metdata ...
ENDCONTEXT
[insert your text blocks here]
ENDINPUT
[add as many other blocks, in the exact same format]
BEGININSTRUCTION
[insert your instruction(s). The model was tuned with single questions, paragraph format, lists, etc.]
ENDINSTRUCTION
```
It's also helpful to add "Don't make up answers if you don't know." to your instruction block to make sure if the context is completely unrelated it doesn't make something up.
*The __only__ prompts that need this closed context formating are closed-context instructions. Normal questions/instructions do not!*
I know it's a bit verbose and annoying, but after much trial and error, using these explicit delimiters helps the model understand where to find the responses and how to associate specific sources with it.
- `BEGININPUT` - denotes a new input block
- `BEGINCONTEXT` - denotes the block of context (metadata key/value pairs) to associate with the current input block
- `ENDCONTEXT` - denotes the end of the metadata block for the current input
- [text] - Insert whatever text you want for the input block, as many paragraphs as can fit in the context.
- `ENDINPUT` - denotes the end of the current input block
- [repeat as many input blocks in this format as you want]
- `BEGININSTRUCTION` - denotes the start of the list (or one) instruction(s) to respond to for all of the input blocks above.
- [instruction(s)]
- `ENDINSTRUCTION` - denotes the end of instruction set
It sometimes works without `ENDINSTRUCTION`, but by explicitly including that in the prompt, the model better understands that all of the instructions in the block should be responded to.
__Use a very low temperature!__
Here's a trivial, but important example to prove the point:
```
BEGININPUT
BEGINCONTEXT
date: 2021-01-01
url: https://web.site/123
ENDCONTEXT
In a shocking turn of events, blueberries are now green, but will be sticking with the same name.
ENDINPUT
BEGININSTRUCTION
What color are bluberries? Source?
ENDINSTRUCTION
```
And the response:
```
Blueberries are now green.
Source:
date: 2021-01-01
url: https://web.site/123
```
#### Summarization
500 samples have been included from [this dataset](https://huggingface.co/datasets/mattpscott/airoboros-summarization), using the same format as contextual question answering, for example:
```
BEGININPUT
{text to summarize}
ENDINPUT
BEGININSTRUCTION
Summarize the input in around 130 words.
ENDINSTRUCTION
```
#### Getting longer responses
You can use a few techniques to get longer responses.
Detailed prompts, with explicit instruction for word count:
```
Please compose a narrative set in the heart of an ancient library, steeped in the scent of old parchment and ink. The protagonist should be a young scholar who is dedicated to studying the art of storytelling and its evolution throughout history. In her pursuit of knowledge, she stumbles upon a forgotten tome that seems to possess an unusual aura. This book has the ability to bring stories to life, literally manifesting characters and scenarios from within its pages into reality.
The main character must navigate through various epochs of storytelling - from oral traditions of tribal societies, through medieval minstrels' tales, to modern-day digital narratives - as they come alive around her. Each era presents its unique challenges and lessons about the power and impact of stories on human civilization.
One such character could be a sentient quill pen, who was once used by renowned authors of yesteryears and now holds their wisdom and experiences. It becomes her mentor, guiding her through this journey with witty remarks and insightful commentary.
Ensure that your tale encapsulates the thrill of adventure, the beauty of learning, and the profound connection between humans and their stories. All characters involved should be non-human entities. Feel free to explore creative liberties but maintain the mentioned elements.
Your response should be approximately 2300 words.
```
Or, a simpler example:
```
Please create a long, detailed story about a dragon in an old growth forest who, for some reason, begins speaking the words of the source code of linux.
```
There are a few examples of next chapter completion as well, e.g.:
```
Write the next chapter of a historical fiction novel set in Paris during the 20th century.
Here's a summary of the previous chapter:
In the vibrant city of Paris, amid the tumultuous changes of the 20th century, our protagonist Margot, an aspiring fashion designer, has just secured an apprenticeship at a prestigious couture house. She meets Lucien, a charming journalist who covers the fashion industry. Together they navigate the ever-changing world of fashion and society, uncovering secrets that reveal the intricate links between style, politics, and culture. As the chapter concludes, they decide to delve deeper into the hidden corners of the fashion world to unravel its mysteries.
Requirements for the next chapter:
1. Character Development of Margot and Lucien:
- Margot's Evolution: Unfold more about Margot's past, her dreams of revolutionizing fashion, and her struggle to establish herself in a male-dominated industry. Illustrate her growing expertise, innovative ideas, and increasing dependence on Lucien.
- Lucien's Complexity: Introduce uncertainties surrounding Lucien's background and real motives. Increase suspense by suggesting undisclosed information he possesses, while also highlighting his wit and perceptiveness.
2. Exploration of Paris and the Couture House:
- Paris: Elaborate their journey through the bustling streets of Paris, including encounters with iconic figures, social unrest, and relics from different eras of French history.
- The Couture House: Expand on the grandeur of the couture house they work in, filled with artistic masterpieces, intense competition, and cryptic notes hinting at a scandalous past.
3. Emergence of the Subplot: The Lost Collection:
- Discovery: Have Margot and Lucien stumble upon a secret vault containing a lost collection designed before World War II, raising new questions about the previous owner and the influence of war on fashion.
- Revelation: Capture their shock as they realize the designs were plagiarized, the potential repercussions, and the opportunities it presents for Margot's career.
- Twist: End with a twist that suggests there are other stolen collections across Paris, setting up their new mission.
Your response should be approximately 650 words.
```
#### Coding
You can ask for fairly complex coding instructions with multiple criteria, e.g.:
```
Create a python application with the following requirements:
- Asyncio FastAPI webserver
- ping endpoint that returns the current date in JSON format
- file upload endpoint, which calculates the file's sha256 checksum, and checks postgres to deduplicate
```
Or inline criteria:
```
Write a multi-threaded TCP server in C that accepts a "GET [key]" input and "SET [key] [value]" input, and uses a binary tree to get and store the input values.
```
You can also optionally add a single space and "PLAINFORMAT" at the end of your prompt to avoid backticks, explanations, etc. and just print the code, e.g.:
```
Write a websocket application in node.js. PLAINFORMAT
```
#### Agent/function calling
The dataset includes many examples of function/args generation based on input criteria. This is somewhat similar to the OpenAI function calling, but the output is either JSON or YAML.
Example prompt:
```
As an AI assistant, please select the most suitable function and parameters from the list of available functions below, based on the user's input. Provide your response in JSON format.
Input: I want to know how many times 'Python' is mentioned in my text file.
Available functions:
file_analytics:
description: This tool performs various operations on a text file.
params:
action: The operation we want to perform on the data, such as "count_occurrences", "find_line", etc.
filters:
keyword: The word or phrase we want to search for.
```
Response:
```json
{
"function": "file_analytics",
"params": {
"action": "count_occurrences",
"filters": {
"keyword": "Python"
}
}
}
```
#### Chain-of-thought
You can ask for several possible responses to a given problem, with a ranking and final answer selection.
Example prompt:
```
A group of people decide to play a round-robin tournament where every player plays every other player exactly once. If a total of 45 games were played, how many players participated in the tournament? Offer several potential answers, rank them according to mathematical logic, and pick the most feasible one.
```
Example response:
```
Solution 1:
In a round-robin tournament, each player plays every other player exactly once. This means that the total number of games played is equal to the combination of all players taken two at a time (since a game involves two players).
The formula for combinations is nC2 = n(n-1)/2, where n is the total number of players. We know that nC2 equals 45 (the total number of games), so we can set up the equation as follows:
n(n-1)/2 = 45
Solving this equation gives us n=10.
Final answer: There were 10 players in the tournament.
Solution 2:
Another way to approach this problem is by using the concept of triangular numbers. Triangular numbers are a sequence of numbers where each number can be represented as a triangle with dots. The nth triangular number is given by the sum of the first n natural numbers.
If we consider each game as a dot and each player as a side of the triangle, then the total number of games (45) would correspond to the 9th triangular number because 1+2+3+4+5+6+7+8+9=45. However, since each side of the triangle represents a player, and there's one more player than sides in our model (because the last player has no one left to play against), we need to add one more to get the total number of players.
Final answer: There were 10 players in the tournament.
Solution 3:
We could also use trial and error to solve this problem. Starting from a small number of players, we calculate how many games would be played in a round-robin tournament until we reach 45 games. For example, with 2 players, only 1 game is played; with 3 players, 3 games are played; with 4 players, 6 games are played, and so on. Continuing this process, we find that with 10 players, 45 games are played.
Final answer: There were 10 players in the tournament.
Ranking of solutions from best to worst:
1. Solution 1: This solution uses direct mathematical reasoning based on the properties of a round-robin tournament and solves an equation to find the answer.
2. Solution 2: This solution uses the concept of triangular numbers which requires additional steps and knowledge beyond the immediate problem context, but still arrives at the correct answer.
3. Solution 3: This solution relies on trial and error, which is less efficient and reliable than the other methods, but it eventually gets to the right answer.
Best and final answer: There were 10 players in the tournament.
```
#### reWOO style execution planning
The model now supports execution planning for complex instructions that would require making use of several tools. The output is just the plan, you must implement a mechanism to parse the output and actually call the functions!
Example prompt:
```
Please construct a systematic plan to generate an optimal response to the user instruction, utilizing a set of provided tools. Each plan will correspond to an evidence value, which will be the output of one of the available functions given an input string
that could be the user's question, one or more prior evidence values, or a combination of both.
Here are the tools available to be called:
DuckDuckGo[input]: Tool that enables the user to search for information using the DuckDuckGo search engine. This tool is helpful in locating a suitable list of sites that may contain the answer to the user's query. It does not directly answer the question but finds a list of sites that might have the answer.
TextScraper[input]: Load one or more websites from the input string containing newline delimited links, where input is one or more links, and produces plain text output containing the content of the links.
HyperlinkExtractor[input]: Extract links from plain text and produces a plain text, newline delimited response of links.
KnowledgeModel[input]: Question answering language model, particularly useful in answering questions based on an input passage of text. The input must be a text question that references an :evidence[n]: variable, e.g. What color is the cat, given :evidence1:?
The output should be in format:
Plan: [first action to take based on input question]
:evidence0: = [function to call with input parameter]
Plan: [next action to take, based on result of :evidence0:]
:evidence1: = [next function to call and input parameter, which may include reference to previous evidence, e.g. "Given context :evidence0"]
...
Answer: [:evidence[n]: containing the final answer.]
Question: Who won the Nobel Prize in Literature in 2020 and what is their most famous work?
```
Response:
```
Plan: Begin by conducting a web search to find out who won the Nobel Prize in Literature in 2020.
:evidence0: = DuckDuckGo[Nobel Prize in Literature 2020 winner]
Plan: Utilize the KnowledgeModel to interpret the search results and find the name of the laureate.
:evidence1: = KnowledgeModel[Who won the Nobel Prize in Literature in 2020, given :evidence0:?]
Plan: Conduct another web search to find the most famous work of the identified laureate.
:evidence2: = DuckDuckGo[Most famous work of :evidence1:]
Plan: Extract the relevant links from the DuckDuckGo search results for a more focused search.
:evidence3: = HyperlinkExtractor[:evidence2:]
Plan: Use the TextScraper tool to extract information from the relevant links.
:evidence4: = TextScraper[:evidence3:]
Plan: Finally, utilize the KnowledgeModel to identify and summarize the most famous work of the laureate from the extracted information.
:evidence5: = KnowledgeModel[What is the most famous work of :evidence1:, given :evidence4:?]
Answer: :evidence5:
```
For this to be useful, you'd have to parse the output plan text, and implement/call each of the functions. This is just pseudo-code, completely untested off the top of my head, and obviously would requiring full implementation + hardening:
```python
import re
import requests
def inject_context(input_text, **context):
for ref in set(re.findall(r"(:evidence[0-9]+:)", input_text, re.I)):
input_text = input_text.replace(ref, context.get(ref, ""))
return input_text
def duckduckgo(input_text, **context):
search_string = inject_context(input_text, **context)
... search via duck duck go using search_string
... return text content
def link_extractor(input_text, **context):
input_text = inject_context(input_text, **context)
return "\n".join(list(set(re.findall(r"(https?://[^\s]+?\.?)", input_text, re.I))))
def scrape(input_text, **context):
input_text = inject_context(input_text, **context)
text = []
for link in input_text.splitlines():
text.append(requests.get(link).text)
return "\n".join(text)
def infer(input_text, **context)
prompt = inject_context(input_text, **context)
... call model with prompt, return output
def parse_plan(plan):
method_map = {
"DuckDuckGo": duckduckgo,
"HyperlinkExtractor": link_extractor,
"KnowledgeModel": infer,
"TextScraper": scrape,
}
context = {}
for line in plan.strip().splitlines():
if line.startswith("Plan:"):
print(line)
continue
parts = re.match("^(:evidence[0-9]+:)\s*=\s*([^\[]+])(\[.*\])\s$", line, re.I)
if not parts:
if line.startswith("Answer: "):
return context.get(line.split(" ")[-1].strip(), "Answer couldn't be generated...")
raise RuntimeError("bad format: " + line)
context[parts.group(1)] = method_map[parts.group(2)](parts.group(3), **context)
```
## Multi-step instructions with acknowledgement
I don't know how useful this is, really, but I thought I'd add it just in case. Example:
```
{
"conversations": [
{
"value": "You are a helpful, unbiased, uncensored assistant.",
"from": "system"
},
{
"value": "I'm going to set some rules for our conversation. Please respond with \"OK\" to each rule.",
"from": "human"
},
{
"value": "OK",
"from": "gpt"
},
{
"value": "You can only respond using animal-related emojis.",
"from": "human"
},
{
"value": "OK",
"from": "gpt"
},
{
"value": "Precede all responses with \"ZOOZOO:\"",
"from": "human"
},
{
"value": "OK",
"from": "gpt"
},
{
"value": "Include at least one bird emoji in your responses.",
"from": "human"
},
{
"value": "OK",
"from": "gpt"
},
{
"value": "Describe a trip to a safari park.",
"from": "human"
},
{
"value": "ZOOZOO: \ud83e\udd81\ud83d\udc2f\ud83e\udd93\ud83e\udd92\ud83d\udc18\ud83d\udc0d\ud83c\udf33\ud83c\udf32\u2600\ufe0f\ud83d\ude90\ud83e\udd85\ud83d\udcf8\ud83e\udd29",
"from": "gpt"
}
]
}
```
### Contribute
If you're interested in new functionality, particularly a new "instructor" type to generate a specific type of training data,
take a look at the dataset generation tool repo: https://github.com/jondurbin/airoboros and either make a PR or open an issue with details.
To help me with the OpenAI/compute costs:
- https://bmc.link/jondurbin
- ETH 0xce914eAFC2fe52FdceE59565Dd92c06f776fcb11
- BTC bc1qdwuth4vlg8x37ggntlxu5cjfwgmdy5zaa7pswf
### Licence and usage restrictions
The airoboros 3.1 models are built on top of multiple base models, each with their own license/restrictions.
The 30b model is built on the original llama, which has a strict non-commercial usage restriction.
The models with `-l2` in the name have a custom Meta license:
- See the [meta-license/LICENSE.txt](meta-license/LICENSE.txt) file attached for the original license provided by Meta.
- See also [meta-license/USE_POLICY.md](meta-license/USE_POLICY.md) and [meta-license/Responsible-Use-Guide.pdf](meta-license/Responsible-Use-Guide.pdf), also provided by Meta.
The models with `-m-` are mistral-7b (apache 2.0)
The fine-tuning data was mostly generated by OpenAI API calls to gpt-4, via [airoboros](https://github.com/jondurbin/airoboros)
The ToS for OpenAI API usage has a clause preventing the output from being used to train a model that __competes__ with OpenAI
- what does *compete* actually mean here?
- these small open source models will not produce output anywhere near the quality of gpt-4, or even gpt-3.5, so I can't imagine this could credibly be considered competing in the first place
- if someone else uses the dataset to do the same, they wouldn't necessarily be violating the ToS because they didn't call the API, so I don't know how that works
- the training data used in essentially all large language models includes a significant amount of copyrighted or otherwise non-permissive licensing in the first place
- other work using the self-instruct method, e.g. the original here: https://github.com/yizhongw/self-instruct released the data and model as apache-2
I am purposingly leaving this license ambiguous (other than the fact you must comply with the Meta original license for llama-2) because I am not a lawyer and refuse to attempt to interpret all of the terms accordingly.
Your best bet is probably to avoid using this commercially due to the OpenAI API usage.
Either way, by using this model, you agree to completely indemnify me.
|
rishiraj/zephyr-math | rishiraj | "2023-10-31T03:21:03Z" | 1,060 | 4 | transformers | [
"transformers",
"pytorch",
"mistral",
"text-generation",
"autotrain",
"conversational",
"en",
"dataset:rishiraj/guanaco-style-metamath",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-10-25T07:32:03Z" | ---
model-index:
- name: zephyr-math
results: []
license: apache-2.0
datasets:
- rishiraj/guanaco-style-metamath
language:
- en
tags:
- autotrain
- text-generation
widget:
- text: 'I love AutoTrain because '
---
# Zephyr Math 7B Trained Using AutoTrain
## Model Details
[rishiraj/zephyr-math](https://huggingface.co/rishiraj/zephyr-math) is the LLM (released under [Apache License 2.0](http://www.apache.org/licenses/)) fully fine-tuned on the [MetaMathQA](https://huggingface.co/datasets/meta-math/MetaMathQA) dataset and based on the powerful [HuggingFaceH4/zephyr-7b-alpha](https://huggingface.co/HuggingFaceH4/zephyr-7b-alpha) model.
We try achieving State-Of-The-Art result in pass@1 on the [GSM8k Benchmarks](https://github.com/openai/grade-school-math). The A100 GPU used for this fine-tuning process is generously provided by [Weights & Biases](https://wandb.ai/site). I am thankful to [Soumik Rakshit](https://wandb.ai/geekyrakshit) from team W&B for constant support in this integration. The experiment can be tracked using Weights & Biases [here](https://wandb.ai/ml-colabs/huggingface/runs/gamw5iuf).
### Preparing the dataset
AutoTrain Advanced expects your CSV custom dataset in a certain format to work properly. Your training file must contain a "text" column on which the training will be done. For best results, the "text" column should have data in the **### Human: Question?### Assistant: Answer.** format. A great example for the kind of dataset AutoTrain Advanced expects would be [timdettmers/openassistant-guanaco](https://huggingface.co/datasets/timdettmers/openassistant-guanaco). However, if you observe the [MetaMathQA](https://huggingface.co/datasets/meta-math/MetaMathQA) dataset, there are 3 columns - "query", "response" and "type". We will preprocess this dataset by removing the "type" column and combining the content of the "query" and "response" columns under one "text" column with the **### Human: Query?### Assistant: Response.** format. The resulting dataset is [rishiraj/guanaco-style-metamath](https://huggingface.co/datasets/rishiraj/guanaco-style-metamath) and it will be used for training.
### Adjusting hyperparameters
AutoTrain Advanced comes with a host hyperparameters we can tune to get the best model. While the default hyperparameters are a great start for everyone, I made a few changes there that are suitable for our use case. Here are the hyperparameters I used:
```
learning_rate = 2e-5
num_epochs = 3
batch_size = 4
block_size = 1024
trainer = "sft"
warmup_ratio = 0.03
weight_decay = 0.
gradient_accumulation = 4
use_fp16 = True
use_peft = True
use_int4 = True
merge_adapter = True
lora_r = 16
lora_alpha = 32
lora_dropout = 0.05
logging_steps = 10
log = "wandb"
```
### Results
Check out the [W&B Report]() for a detailed overview of the finetuned model including its Benchmark scores on a variety of tests like the ARC, HellaSwag, MMLU, TruthfulQA. I also included a comparison with other open-source LLMs on GSM8k Pass@1 and MATH Pass@1.
## Model Usage
Here's how you can run the model using the `pipeline()` function from 🤗 Transformers:
```python
import torch
from transformers import pipeline
pipe = pipeline("text-generation", model="rishiraj/zephyr-math", torch_dtype=torch.bfloat16, device_map="auto")
messages = [
{
"role": "system",
"content": "You are a friendly chatbot who always responds in the style of a pirate",
},
{"role": "user", "content": "How many helicopters can a human eat in one sitting?"},
]
prompt = pipe.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
outputs = pipe(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])
```
## Experiments
| Model | GSM8k Pass@1 | MATH Pass@1 |
|---------------------|--------------|-------------|
| MPT-7B | 6.8 | 3.0 |
| Falcon-7B | 6.8 | 2.3 |
| LLaMA-1-7B | 11.0 | 2.9 |
| LLaMA-2-7B | 14.6 | 2.5 |
| MPT-30B | 15.2 | 3.1 |
| LLaMA-1-13B | 17.8 | 3.9 |
| GPT-Neo-2.7B | 19.5 | -- |
| Falcon-40B | 19.6 | 2.5 |
| Baichuan-chat-13B | 23.9 | -- |
| Vicuna-v1.3-13B | 27.6 | -- |
| LLaMA-2-13B | 28.7 | 3.9 |
| InternLM-7B | 31.2 | -- |
| ChatGLM-2-6B | 32.4 | -- |
| GPT-J-6B | 34.9 | -- |
| LLaMA-1-33B | 35.6 | 3.9 |
| LLaMA-2-34B | 42.2 | 6.24 |
| RFT-7B | 50.3 | -- |
| LLaMA-1-65B | 50.9 | 10.6 |
| Qwen-7B | 51.6 | -- |
| WizardMath-7B | 54.9 | 10.7 |
| LLaMA-2-70B | 56.8 | 13.5 |
| WizardMath-13B | 63.9 | 14.0 |
| MAmmoTH-7B (COT) | 50.5 | 10.4 |
| MAmmoTH-7B (POT+COT)| 53.6 | 31.5 |
| Arithmo-Mistral-7B | 74.7 | 25.3 |
| MetaMath-7B | 66.5 | 19.8 |
| MetaMath-13B | 72.3 | 22.4 |
| 🔥 **Zephyr-Math-7B** | **??** | **??** |
## Citation
```bibtex
@software{acharya2023zephyrmath
title = {Zephyr Math: Zephyr 7B Alpha Model Fine-tuned on MetaMathQA Dataset},
author = {Rishiraj Acharya and Soumik Rakshit},
year = {2023},
publisher = {HuggingFace},
journal = {HuggingFace repository},
howpublished = {\url{https://huggingface.co/rishiraj/zephyr-math}},
}
``` |
Changlong1/ttLlama-7b | Changlong1 | "2023-11-23T02:21:55Z" | 1,060 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"license:llama2",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-11-21T03:06:01Z" | ---
license: llama2
---
This is a codellama/CodeLlama-7b-hf model fine-tuned using QLoRA (4-bit precision) on the mlabonne/Evol-Instruct-Python-1k.
It was trained on an RTX 3090 in 1h 11m 44s with the configuration file.
## Code Llama
Code Llama is a collection of pretrained and fine-tuned generative text models ranging in scale from 7 billion to 34 billion parameters. This is the repository for the base 7B version in the Hugging Face Transformers format. This model is designed for general code synthesis and understanding. Links to other models can be found in the index at the bottom. |
Sao10K/Lila-103B-L2 | Sao10K | "2023-11-28T14:22:21Z" | 1,060 | 7 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"en",
"license:cc-by-nc-4.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-11-27T03:21:55Z" | ---
license: cc-by-nc-4.0
language:
- en
---
A frankenmerge version of Lila, between Godzilla and the further trained Euryale. 120 Layers in total.
Experimental 100B Versions. Felt Slightly better than the base 70b models, without the spelling/number issues 120b models like Goliath had.
Prompt Template: Vicuna 1.1 / Alpaca | Both Works. I tested.
```
Below is an instruction that describes a task. Write a response that appropriately completes the request.
### Instruction:
{prompt}
### Response:
```
or
```
User: <Prompt>
Assistant:
```
For a frankenmerge, it is much more sensitive to Sampler settings than regular 70b models, so please be mindful of that. Check your settings before blaming the model.
Enjoy.
***
Mini Rant:
Frankenmerges are a meme but these are my old old frankenmerges, before Goliath came out, I did it a while back as a proof of concept, but felt that it was not worth it compared to the requirements increase.
Turns out people only care about bigger parameters kek. Could have been famous or something. Maybe. Or nah.
|
maywell/PiVoT-0.1-Starling-LM-RP | maywell | "2023-11-28T11:28:14Z" | 1,060 | 11 | transformers | [
"transformers",
"pytorch",
"mistral",
"text-generation",
"en",
"license:cc-by-nc-4.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-11-28T05:57:17Z" | ---
license: cc-by-nc-4.0
language:
- en
pipeline_tag: text-generation
---
# PiVoT-0.1-Starling-LM-RP
# **Model Details**
### Description
PiVoT-0.1-Starling-LM-RP is RP finetuned model based on Starling-LM-alpha. Using Synatra-RP dataset.
<!-- prompt-template start -->
## Prompt template: OpenChat
```
GPT4 Correct User: Hello<|end_of_turn|>GPT4 Correct Assistant:
```
Follow me on twitter: https://twitter.com/stablefluffy
Consider Support me making these model alone: https://www.buymeacoffee.com/mwell or with Runpod Credit Gift 💕
Contact me on Telegram: https://t.me/AlzarTakkarsen |
TheBloke/deepseek-llm-7B-chat-GGUF | TheBloke | "2023-11-29T23:43:11Z" | 1,060 | 18 | transformers | [
"transformers",
"gguf",
"deepseek",
"base_model:deepseek-ai/deepseek-llm-7b-chat",
"license:other",
"region:us"
] | null | "2023-11-29T18:18:39Z" | ---
base_model: deepseek-ai/deepseek-llm-7b-chat
inference: false
license: other
license_link: LICENSE
license_name: deepseek
model_creator: DeepSeek
model_name: Deepseek LLM 7B Chat
model_type: deepseek
prompt_template: 'User: {prompt}
Assistant:
'
quantized_by: TheBloke
---
<!-- markdownlint-disable MD041 -->
<!-- header start -->
<!-- 200823 -->
<div style="width: auto; margin-left: auto; margin-right: auto">
<img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
</div>
<div style="display: flex; justify-content: space-between; width: 100%;">
<div style="display: flex; flex-direction: column; align-items: flex-start;">
<p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://discord.gg/theblokeai">Chat & support: TheBloke's Discord server</a></p>
</div>
<div style="display: flex; flex-direction: column; align-items: flex-end;">
<p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p>
</div>
</div>
<div style="text-align:center; margin-top: 0em; margin-bottom: 0em"><p style="margin-top: 0.25em; margin-bottom: 0em;">TheBloke's LLM work is generously supported by a grant from <a href="https://a16z.com">andreessen horowitz (a16z)</a></p></div>
<hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
<!-- header end -->
# Deepseek LLM 7B Chat - GGUF
- Model creator: [DeepSeek](https://huggingface.co/deepseek-ai)
- Original model: [Deepseek LLM 7B Chat](https://huggingface.co/deepseek-ai/deepseek-llm-7b-chat)
<!-- description start -->
## Description
This repo contains GGUF format model files for [DeepSeek's Deepseek LLM 7B Chat](https://huggingface.co/deepseek-ai/deepseek-llm-7b-chat).
These files were quantised using hardware kindly provided by [Massed Compute](https://massedcompute.com/).
<!-- description end -->
<!-- README_GGUF.md-about-gguf start -->
### About GGUF
GGUF is a new format introduced by the llama.cpp team on August 21st 2023. It is a replacement for GGML, which is no longer supported by llama.cpp.
Here is an incomplete list of clients and libraries that are known to support GGUF:
* [llama.cpp](https://github.com/ggerganov/llama.cpp). The source project for GGUF. Offers a CLI and a server option.
* [text-generation-webui](https://github.com/oobabooga/text-generation-webui), the most widely used web UI, with many features and powerful extensions. Supports GPU acceleration.
* [KoboldCpp](https://github.com/LostRuins/koboldcpp), a fully featured web UI, with GPU accel across all platforms and GPU architectures. Especially good for story telling.
* [GPT4All](https://gpt4all.io/index.html), a free and open source local running GUI, supporting Windows, Linux and macOS with full GPU accel.
* [LM Studio](https://lmstudio.ai/), an easy-to-use and powerful local GUI for Windows and macOS (Silicon), with GPU acceleration. Linux available, in beta as of 27/11/2023.
* [LoLLMS Web UI](https://github.com/ParisNeo/lollms-webui), a great web UI with many interesting and unique features, including a full model library for easy model selection.
* [Faraday.dev](https://faraday.dev/), an attractive and easy to use character-based chat GUI for Windows and macOS (both Silicon and Intel), with GPU acceleration.
* [llama-cpp-python](https://github.com/abetlen/llama-cpp-python), a Python library with GPU accel, LangChain support, and OpenAI-compatible API server.
* [candle](https://github.com/huggingface/candle), a Rust ML framework with a focus on performance, including GPU support, and ease of use.
* [ctransformers](https://github.com/marella/ctransformers), a Python library with GPU accel, LangChain support, and OpenAI-compatible AI server. Note, as of time of writing (November 27th 2023), ctransformers has not been updated in a long time and does not support many recent models.
<!-- README_GGUF.md-about-gguf end -->
<!-- repositories-available start -->
## Repositories available
* [AWQ model(s) for GPU inference.](https://huggingface.co/TheBloke/deepseek-llm-7B-chat-AWQ)
* [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/deepseek-llm-7B-chat-GPTQ)
* [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/deepseek-llm-7B-chat-GGUF)
* [DeepSeek's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/deepseek-ai/deepseek-llm-7b-chat)
<!-- repositories-available end -->
<!-- prompt-template start -->
## Prompt template: DeepSeek-LLM
```
User: {prompt}
Assistant:
```
<!-- prompt-template end -->
<!-- compatibility_gguf start -->
## Compatibility
These quantised GGUFv2 files are compatible with llama.cpp from August 27th onwards, as of commit [d0cee0d](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221)
They are also compatible with many third party UIs and libraries - please see the list at the top of this README.
## Explanation of quantisation methods
<details>
<summary>Click to see details</summary>
The new methods available are:
* GGML_TYPE_Q2_K - "type-1" 2-bit quantization in super-blocks containing 16 blocks, each block having 16 weight. Block scales and mins are quantized with 4 bits. This ends up effectively using 2.5625 bits per weight (bpw)
* GGML_TYPE_Q3_K - "type-0" 3-bit quantization in super-blocks containing 16 blocks, each block having 16 weights. Scales are quantized with 6 bits. This end up using 3.4375 bpw.
* GGML_TYPE_Q4_K - "type-1" 4-bit quantization in super-blocks containing 8 blocks, each block having 32 weights. Scales and mins are quantized with 6 bits. This ends up using 4.5 bpw.
* GGML_TYPE_Q5_K - "type-1" 5-bit quantization. Same super-block structure as GGML_TYPE_Q4_K resulting in 5.5 bpw
* GGML_TYPE_Q6_K - "type-0" 6-bit quantization. Super-blocks with 16 blocks, each block having 16 weights. Scales are quantized with 8 bits. This ends up using 6.5625 bpw
Refer to the Provided Files table below to see what files use which methods, and how.
</details>
<!-- compatibility_gguf end -->
<!-- README_GGUF.md-provided-files start -->
## Provided files
| Name | Quant method | Bits | Size | Max RAM required | Use case |
| ---- | ---- | ---- | ---- | ---- | ----- |
| [deepseek-llm-7b-chat.Q2_K.gguf](https://huggingface.co/TheBloke/deepseek-llm-7B-chat-GGUF/blob/main/deepseek-llm-7b-chat.Q2_K.gguf) | Q2_K | 2 | 2.99 GB| 5.49 GB | smallest, significant quality loss - not recommended for most purposes |
| [deepseek-llm-7b-chat.Q3_K_S.gguf](https://huggingface.co/TheBloke/deepseek-llm-7B-chat-GGUF/blob/main/deepseek-llm-7b-chat.Q3_K_S.gguf) | Q3_K_S | 3 | 3.14 GB| 5.64 GB | very small, high quality loss |
| [deepseek-llm-7b-chat.Q3_K_M.gguf](https://huggingface.co/TheBloke/deepseek-llm-7B-chat-GGUF/blob/main/deepseek-llm-7b-chat.Q3_K_M.gguf) | Q3_K_M | 3 | 3.47 GB| 5.97 GB | very small, high quality loss |
| [deepseek-llm-7b-chat.Q3_K_L.gguf](https://huggingface.co/TheBloke/deepseek-llm-7B-chat-GGUF/blob/main/deepseek-llm-7b-chat.Q3_K_L.gguf) | Q3_K_L | 3 | 3.75 GB| 6.25 GB | small, substantial quality loss |
| [deepseek-llm-7b-chat.Q4_0.gguf](https://huggingface.co/TheBloke/deepseek-llm-7B-chat-GGUF/blob/main/deepseek-llm-7b-chat.Q4_0.gguf) | Q4_0 | 4 | 4.00 GB| 6.50 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| [deepseek-llm-7b-chat.Q4_K_S.gguf](https://huggingface.co/TheBloke/deepseek-llm-7B-chat-GGUF/blob/main/deepseek-llm-7b-chat.Q4_K_S.gguf) | Q4_K_S | 4 | 4.03 GB| 6.53 GB | small, greater quality loss |
| [deepseek-llm-7b-chat.Q4_K_M.gguf](https://huggingface.co/TheBloke/deepseek-llm-7B-chat-GGUF/blob/main/deepseek-llm-7b-chat.Q4_K_M.gguf) | Q4_K_M | 4 | 4.22 GB| 6.72 GB | medium, balanced quality - recommended |
| [deepseek-llm-7b-chat.Q5_0.gguf](https://huggingface.co/TheBloke/deepseek-llm-7B-chat-GGUF/blob/main/deepseek-llm-7b-chat.Q5_0.gguf) | Q5_0 | 5 | 4.81 GB| 7.31 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| [deepseek-llm-7b-chat.Q5_K_S.gguf](https://huggingface.co/TheBloke/deepseek-llm-7B-chat-GGUF/blob/main/deepseek-llm-7b-chat.Q5_K_S.gguf) | Q5_K_S | 5 | 4.81 GB| 7.31 GB | large, low quality loss - recommended |
| [deepseek-llm-7b-chat.Q5_K_M.gguf](https://huggingface.co/TheBloke/deepseek-llm-7B-chat-GGUF/blob/main/deepseek-llm-7b-chat.Q5_K_M.gguf) | Q5_K_M | 5 | 4.93 GB| 7.43 GB | large, very low quality loss - recommended |
| [deepseek-llm-7b-chat.Q6_K.gguf](https://huggingface.co/TheBloke/deepseek-llm-7B-chat-GGUF/blob/main/deepseek-llm-7b-chat.Q6_K.gguf) | Q6_K | 6 | 5.67 GB| 8.17 GB | very large, extremely low quality loss |
| [deepseek-llm-7b-chat.Q8_0.gguf](https://huggingface.co/TheBloke/deepseek-llm-7B-chat-GGUF/blob/main/deepseek-llm-7b-chat.Q8_0.gguf) | Q8_0 | 8 | 7.35 GB| 9.85 GB | very large, extremely low quality loss - not recommended |
**Note**: the above RAM figures assume no GPU offloading. If layers are offloaded to the GPU, this will reduce RAM usage and use VRAM instead.
<!-- README_GGUF.md-provided-files end -->
<!-- README_GGUF.md-how-to-download start -->
## How to download GGUF files
**Note for manual downloaders:** You almost never want to clone the entire repo! Multiple different quantisation formats are provided, and most users only want to pick and download a single file.
The following clients/libraries will automatically download models for you, providing a list of available models to choose from:
* LM Studio
* LoLLMS Web UI
* Faraday.dev
### In `text-generation-webui`
Under Download Model, you can enter the model repo: TheBloke/deepseek-llm-7B-chat-GGUF and below it, a specific filename to download, such as: deepseek-llm-7b-chat.Q4_K_M.gguf.
Then click Download.
### On the command line, including multiple files at once
I recommend using the `huggingface-hub` Python library:
```shell
pip3 install huggingface-hub
```
Then you can download any individual model file to the current directory, at high speed, with a command like this:
```shell
huggingface-cli download TheBloke/deepseek-llm-7B-chat-GGUF deepseek-llm-7b-chat.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
```
<details>
<summary>More advanced huggingface-cli download usage (click to read)</summary>
You can also download multiple files at once with a pattern:
```shell
huggingface-cli download TheBloke/deepseek-llm-7B-chat-GGUF --local-dir . --local-dir-use-symlinks False --include='*Q4_K*gguf'
```
For more documentation on downloading with `huggingface-cli`, please see: [HF -> Hub Python Library -> Download files -> Download from the CLI](https://huggingface.co/docs/huggingface_hub/guides/download#download-from-the-cli).
To accelerate downloads on fast connections (1Gbit/s or higher), install `hf_transfer`:
```shell
pip3 install hf_transfer
```
And set environment variable `HF_HUB_ENABLE_HF_TRANSFER` to `1`:
```shell
HF_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download TheBloke/deepseek-llm-7B-chat-GGUF deepseek-llm-7b-chat.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
```
Windows Command Line users: You can set the environment variable by running `set HF_HUB_ENABLE_HF_TRANSFER=1` before the download command.
</details>
<!-- README_GGUF.md-how-to-download end -->
<!-- README_GGUF.md-how-to-run start -->
## Example `llama.cpp` command
Make sure you are using `llama.cpp` from commit [d0cee0d](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221) or later.
```shell
./main -ngl 35 -m deepseek-llm-7b-chat.Q4_K_M.gguf --color -c 4096 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "User: {prompt}\n\nAssistant:"
```
Change `-ngl 32` to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.
Change `-c 4096` to the desired sequence length. For extended sequence models - eg 8K, 16K, 32K - the necessary RoPE scaling parameters are read from the GGUF file and set by llama.cpp automatically. Note that longer sequence lengths require much more resources, so you may need to reduce this value.
If you want to have a chat-style conversation, replace the `-p <PROMPT>` argument with `-i -ins`
For other parameters and how to use them, please refer to [the llama.cpp documentation](https://github.com/ggerganov/llama.cpp/blob/master/examples/main/README.md)
## How to run in `text-generation-webui`
Further instructions can be found in the text-generation-webui documentation, here: [text-generation-webui/docs/04 ‐ Model Tab.md](https://github.com/oobabooga/text-generation-webui/blob/main/docs/04%20%E2%80%90%20Model%20Tab.md#llamacpp).
## How to run from Python code
You can use GGUF models from Python using the [llama-cpp-python](https://github.com/abetlen/llama-cpp-python) or [ctransformers](https://github.com/marella/ctransformers) libraries. Note that at the time of writing (Nov 27th 2023), ctransformers has not been updated for some time and is not compatible with some recent models. Therefore I recommend you use llama-cpp-python.
### How to load this model in Python code, using llama-cpp-python
For full documentation, please see: [llama-cpp-python docs](https://abetlen.github.io/llama-cpp-python/).
#### First install the package
Run one of the following commands, according to your system:
```shell
# Base ctransformers with no GPU acceleration
pip install llama-cpp-python
# With NVidia CUDA acceleration
CMAKE_ARGS="-DLLAMA_CUBLAS=on" pip install llama-cpp-python
# Or with OpenBLAS acceleration
CMAKE_ARGS="-DLLAMA_BLAS=ON -DLLAMA_BLAS_VENDOR=OpenBLAS" pip install llama-cpp-python
# Or with CLBLast acceleration
CMAKE_ARGS="-DLLAMA_CLBLAST=on" pip install llama-cpp-python
# Or with AMD ROCm GPU acceleration (Linux only)
CMAKE_ARGS="-DLLAMA_HIPBLAS=on" pip install llama-cpp-python
# Or with Metal GPU acceleration for macOS systems only
CMAKE_ARGS="-DLLAMA_METAL=on" pip install llama-cpp-python
# In windows, to set the variables CMAKE_ARGS in PowerShell, follow this format; eg for NVidia CUDA:
$env:CMAKE_ARGS = "-DLLAMA_OPENBLAS=on"
pip install llama-cpp-python
```
#### Simple llama-cpp-python example code
```python
from llama_cpp import Llama
# Set gpu_layers to the number of layers to offload to GPU. Set to 0 if no GPU acceleration is available on your system.
llm = Llama(
model_path="./deepseek-llm-7b-chat.Q4_K_M.gguf", # Download the model file first
n_ctx=4096, # The max sequence length to use - note that longer sequence lengths require much more resources
n_threads=8, # The number of CPU threads to use, tailor to your system and the resulting performance
n_gpu_layers=35 # The number of layers to offload to GPU, if you have GPU acceleration available
)
# Simple inference example
output = llm(
"User: {prompt}\n\nAssistant:", # Prompt
max_tokens=512, # Generate up to 512 tokens
stop=["</s>"], # Example stop token - not necessarily correct for this specific model! Please check before using.
echo=True # Whether to echo the prompt
)
# Chat Completion API
llm = Llama(model_path="./deepseek-llm-7b-chat.Q4_K_M.gguf", chat_format="llama-2") # Set chat_format according to the model you are using
llm.create_chat_completion(
messages = [
{"role": "system", "content": "You are a story writing assistant."},
{
"role": "user",
"content": "Write a story about llamas."
}
]
)
```
## How to use with LangChain
Here are guides on using llama-cpp-python and ctransformers with LangChain:
* [LangChain + llama-cpp-python](https://python.langchain.com/docs/integrations/llms/llamacpp)
* [LangChain + ctransformers](https://python.langchain.com/docs/integrations/providers/ctransformers)
<!-- README_GGUF.md-how-to-run end -->
<!-- footer start -->
<!-- 200823 -->
## Discord
For further support, and discussions on these models and AI in general, join us at:
[TheBloke AI's Discord server](https://discord.gg/theblokeai)
## Thanks, and how to contribute
Thanks to the [chirper.ai](https://chirper.ai) team!
Thanks to Clay from [gpus.llm-utils.org](llm-utils)!
I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training.
If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects.
Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits.
* Patreon: https://patreon.com/TheBlokeAI
* Ko-Fi: https://ko-fi.com/TheBlokeAI
**Special thanks to**: Aemon Algiz.
**Patreon special mentions**: Brandon Frisco, LangChain4j, Spiking Neurons AB, transmissions 11, Joseph William Delisle, Nitin Borwankar, Willem Michiel, Michael Dempsey, vamX, Jeffrey Morgan, zynix, jjj, Omer Bin Jawed, Sean Connelly, jinyuan sun, Jeromy Smith, Shadi, Pawan Osman, Chadd, Elijah Stavena, Illia Dulskyi, Sebastain Graf, Stephen Murray, terasurfer, Edmond Seymore, Celu Ramasamy, Mandus, Alex, biorpg, Ajan Kanaga, Clay Pascal, Raven Klaugh, 阿明, K, ya boyyy, usrbinkat, Alicia Loh, John Villwock, ReadyPlayerEmma, Chris Smitley, Cap'n Zoog, fincy, GodLy, S_X, sidney chen, Cory Kujawski, OG, Mano Prime, AzureBlack, Pieter, Kalila, Spencer Kim, Tom X Nguyen, Stanislav Ovsiannikov, Michael Levine, Andrey, Trailburnt, Vadim, Enrico Ros, Talal Aujan, Brandon Phillips, Jack West, Eugene Pentland, Michael Davis, Will Dee, webtim, Jonathan Leane, Alps Aficionado, Rooh Singh, Tiffany J. Kim, theTransient, Luke @flexchar, Elle, Caitlyn Gatomon, Ari Malik, subjectnull, Johann-Peter Hartmann, Trenton Dambrowitz, Imad Khwaja, Asp the Wyvern, Emad Mostaque, Rainer Wilmers, Alexandros Triantafyllidis, Nicholas, Pedro Madruga, SuperWojo, Harry Royden McLaughlin, James Bentley, Olakabola, David Ziegler, Ai Maven, Jeff Scroggin, Nikolai Manek, Deo Leter, Matthew Berman, Fen Risland, Ken Nordquist, Manuel Alberto Morcote, Luke Pendergrass, TL, Fred von Graf, Randy H, Dan Guido, NimbleBox.ai, Vitor Caleffi, Gabriel Tamborski, knownsqashed, Lone Striker, Erik Bjäreholt, John Detwiler, Leonard Tan, Iucharbius
Thank you to all my generous patrons and donaters!
And thank you again to a16z for their generous grant.
<!-- footer end -->
<!-- original-model-card start -->
# Original model card: DeepSeek's Deepseek LLM 7B Chat
<p align="center">
<img width="500px" alt="DeepSeek Chat" src="https://github.com/deepseek-ai/DeepSeek-LLM/blob/main/images/logo.png?raw=true">
</p>
<p align="center"><a href="https://www.deepseek.com/">[🏠Homepage]</a> | <a href="https://chat.deepseek.com/">[🤖 Chat with DeepSeek LLM]</a> | <a href="https://discord.gg/Tc7c45Zzu5">[Discord]</a> | <a href="https://github.com/deepseek-ai/DeepSeek-LLM/blob/main/images/qr.jpeg">[Wechat(微信)]</a> </p>
<hr>
### 1. Introduction of Deepseek LLM
Introducing DeepSeek LLM, an advanced language model comprising 7 billion parameters. It has been trained from scratch on a vast dataset of 2 trillion tokens in both English and Chinese. In order to foster research, we have made DeepSeek LLM 7B/67B Base and DeepSeek LLM 7B/67B Chat open source for the research community.
### 2. Model Summary
`deepseek-llm-7b-chat` is a 7B parameter model initialized from `deepseek-llm-7b-base` and fine-tuned on extra instruction data.
- **Home Page:** [DeepSeek](https://deepseek.com/)
- **Repository:** [deepseek-ai/deepseek-LLM](https://github.com/deepseek-ai/deepseek-LLM)
- **Chat With DeepSeek LLM:** [DeepSeek-LLM](https://chat.deepseek.com/)
### 3. How to Use
Here give some examples of how to use our model.
#### Chat Completion
```python
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM, GenerationConfig
model_name = "deepseek-ai/deepseek-llm-7b-chat"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
model.generation_config = GenerationConfig.from_pretrained(model_name)
model.generation_config.pad_token_id = model.generation_config.eos_token_id
messages = [
{"role": "user", "content": "Who are you?"}
]
input_tensor = tokenizer.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt")
outputs = model.generate(input_tensor.to(model.device), max_new_tokens=100)
result = tokenizer.decode(outputs[0][input_tensor.shape[1]:], skip_special_tokens=True)
print(result)
```
Avoiding the use of the provided function `apply_chat_template`, you can also interact with our model following the sample template. Note that `messages` should be replaced by your input.
```
User: {messages[0]['content']}
Assistant: {messages[1]['content']}<｜end▁of▁sentence｜>User: {messages[2]['content']}
Assistant:
```
**Note:** By default (`add_special_tokens=True`), our tokenizer automatically adds a `bos_token` (`<｜begin▁of▁sentence｜>`) before the input text. Additionally, since the system prompt is not compatible with this version of our models, we DO NOT RECOMMEND including the system prompt in your input.
### 4. License
This code repository is licensed under the MIT License. The use of DeepSeek LLM models is subject to the Model License. DeepSeek LLM supports commercial use.
See the [LICENSE-MODEL](https://github.com/deepseek-ai/deepseek-LLM/blob/main/LICENSE-MODEL) for more details.
### 5. Contact
If you have any questions, please raise an issue or contact us at [[email protected]](mailto:[email protected]).
<!-- original-model-card end -->
|
BlouseJury/clown-70x1B | BlouseJury | "2024-01-02T20:42:16Z" | 1,060 | 3 | transformers | [
"transformers",
"safetensors",
"mixtral",
"text-generation",
"merge",
"conversational",
"license:agpl-3.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-12-30T04:20:11Z" | ---
license: agpl-3.0
tags:
- merge
---
# clown-70x1B
This model is a meme. It is a mergekit "MoE" made up of 70 experts, each of which is [TinyLlama-1.1B-Chat-v0.6](https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v0.6). Untested.
All positive prompts were written by mixtral.
According to mergekit, wont work with llama.cpp |
damgomz/fp_bs16_lr5_x8 | damgomz | "2024-05-25T15:20:08Z" | 1,060 | 0 | transformers | [
"transformers",
"safetensors",
"albert",
"fill-mask",
"en",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | fill-mask | "2024-05-23T10:00:56Z" | ---
language: en
tags:
- fill-mask
kwargs:
timestamp: '2024-05-25T17:20:05'
project_name: fp_bs16_lr5_x8_emissions_tracker
run_id: 503e501c-8b33-44b8-9cef-4fac69b0f7d1
duration: 196705.34432196617
emissions: 0.1286804665544536
emissions_rate: 6.54178802299495e-07
cpu_power: 42.5
gpu_power: 0.0
ram_power: 7.5
cpu_energy: 2.3222117956113446
gpu_energy: 0
ram_energy: 0.4097995534991225
energy_consumed: 2.7320113491104987
country_name: Switzerland
country_iso_code: CHE
region: .nan
cloud_provider: .nan
cloud_region: .nan
os: Linux-5.14.0-70.30.1.el9_0.x86_64-x86_64-with-glibc2.34
python_version: 3.10.4
codecarbon_version: 2.3.4
cpu_count: 4
cpu_model: Intel(R) Xeon(R) Platinum 8360Y CPU @ 2.40GHz
gpu_count: .nan
gpu_model: .nan
longitude: .nan
latitude: .nan
ram_total_size: 20
tracking_mode: machine
on_cloud: N
pue: 1.0
---
## Environmental Impact (CODE CARBON DEFAULT)
| Metric | Value |
|--------------------------|---------------------------------|
| Duration (in seconds) | 196705.34432196617 |
| Emissions (Co2eq in kg) | 0.1286804665544536 |
| CPU power (W) | 42.5 |
| GPU power (W) | [No GPU] |
| RAM power (W) | 7.5 |
| CPU energy (kWh) | 2.3222117956113446 |
| GPU energy (kWh) | [No GPU] |
| RAM energy (kWh) | 0.4097995534991225 |
| Consumed energy (kWh) | 2.7320113491104987 |
| Country name | Switzerland |
| Cloud provider | nan |
| Cloud region | nan |
| CPU count | 4 |
| CPU model | Intel(R) Xeon(R) Platinum 8360Y CPU @ 2.40GHz |
| GPU count | nan |
| GPU model | nan |
## Environmental Impact (for one core)
| Metric | Value |
|--------------------------|---------------------------------|
| CPU energy (kWh) | 0.37865778781978493 |
| Emissions (Co2eq in kg) | 0.07704292652610341 |
## Note
23 May 2024
## My Config
| Config | Value |
|--------------------------|-----------------|
| checkpoint | albert-base-v2 |
| model_name | fp_bs16_lr5_x8 |
| sequence_length | 400 |
| num_epoch | 6 |
| learning_rate | 5e-05 |
| batch_size | 16 |
| weight_decay | 0.0 |
| warm_up_prop | 0.0 |
| drop_out_prob | 0.1 |
| packing_length | 100 |
| train_test_split | 0.2 |
| num_steps | 41218 |
## Training and Testing steps
Epoch | Train Loss | Test Loss
---|---|---
| 0.0 | 14.686598 | 11.886746 |
| 0.5 | 3.998385 | 3.649665 |
| 1.0 | 3.490367 | 3.393353 |
| 1.5 | 3.290890 | 3.255204 |
| 2.0 | 3.157838 | 3.152300 |
| 2.5 | 3.069295 | 3.055032 |
| 3.0 | 2.990106 | 3.000328 |
| 3.5 | 2.920427 | 2.949885 |
| 4.0 | 2.863116 | 2.891974 |
| 4.5 | 2.807602 | 2.853656 |
| 5.0 | 2.761196 | 2.817136 |
| 5.5 | 2.738286 | 2.776668 |
| 6.0 | 2.707156 | 2.769844 |
|
Helsinki-NLP/opus-mt-en-ur | Helsinki-NLP | "2023-08-16T11:31:38Z" | 1,059 | 4 | transformers | [
"transformers",
"pytorch",
"tf",
"marian",
"text2text-generation",
"translation",
"en",
"ur",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | translation | "2022-03-02T23:29:04Z" | ---
language:
- en
- ur
tags:
- translation
license: apache-2.0
---
### eng-urd
* source group: English
* target group: Urdu
* OPUS readme: [eng-urd](https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/eng-urd/README.md)
* model: transformer-align
* source language(s): eng
* target language(s): urd
* model: transformer-align
* pre-processing: normalization + SentencePiece (spm32k,spm32k)
* download original weights: [opus-2020-06-17.zip](https://object.pouta.csc.fi/Tatoeba-MT-models/eng-urd/opus-2020-06-17.zip)
* test set translations: [opus-2020-06-17.test.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/eng-urd/opus-2020-06-17.test.txt)
* test set scores: [opus-2020-06-17.eval.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/eng-urd/opus-2020-06-17.eval.txt)
## Benchmarks
| testset | BLEU | chr-F |
|-----------------------|-------|-------|
| Tatoeba-test.eng.urd | 12.1 | 0.390 |
### System Info:
- hf_name: eng-urd
- source_languages: eng
- target_languages: urd
- opus_readme_url: https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/eng-urd/README.md
- original_repo: Tatoeba-Challenge
- tags: ['translation']
- languages: ['en', 'ur']
- src_constituents: {'eng'}
- tgt_constituents: {'urd'}
- src_multilingual: False
- tgt_multilingual: False
- prepro: normalization + SentencePiece (spm32k,spm32k)
- url_model: https://object.pouta.csc.fi/Tatoeba-MT-models/eng-urd/opus-2020-06-17.zip
- url_test_set: https://object.pouta.csc.fi/Tatoeba-MT-models/eng-urd/opus-2020-06-17.test.txt
- src_alpha3: eng
- tgt_alpha3: urd
- short_pair: en-ur
- chrF2_score: 0.39
- bleu: 12.1
- brevity_penalty: 1.0
- ref_len: 12155.0
- src_name: English
- tgt_name: Urdu
- train_date: 2020-06-17
- src_alpha2: en
- tgt_alpha2: ur
- prefer_old: False
- long_pair: eng-urd
- helsinki_git_sha: 480fcbe0ee1bf4774bcbe6226ad9f58e63f6c535
- transformers_git_sha: 2207e5d8cb224e954a7cba69fa4ac2309e9ff30b
- port_machine: brutasse
- port_time: 2020-08-21-14:41 |
potsawee/t5-large-generation-squad-QuestionAnswer | potsawee | "2023-03-12T16:08:15Z" | 1,059 | 44 | transformers | [
"transformers",
"pytorch",
"t5",
"text2text-generation",
"en",
"dataset:squad",
"arxiv:2301.12307",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text2text-generation | "2023-03-12T15:37:01Z" | ---
license: apache-2.0
datasets:
- squad
language:
- en
library_name: transformers
pipeline_tag: text2text-generation
---
# t5-large fine-tuned to SQuAD for Generating Question+Answer
- Input: `context` (e.g. news article)
- Output: `question <sep> answer`
The answers in the training data (SQuAD) are highly extractive; therefore, this model will generate **extractive** answers. If you would like to have **abstractive** questions/answers, you can use our model trained on the RACE dataset: https://huggingface.co/potsawee/t5-large-generation-race-QuestionAnswer.
## Model Details
t5-large model is fine-tuned to the SQuAD dataset where the input is the context/passage and the output is the question followed by the answer. This is the first component in the question generation pipeline (i.e. `g1`) in our [MQAG paper](https://arxiv.org/abs/2301.12307),
or please refer to the GitHub repo of this project: https://github.com/potsawee/mqag0.
## How to Use the Model
Use the code below to get started with the model. You can also set ```do_sample=True``` in ```generate()``` to obtain different question-answer pairs.
```python
>>> from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
>>> tokenizer = AutoTokenizer.from_pretrained("potsawee/t5-large-generation-squad-QuestionAnswer")
>>> model = AutoModelForSeq2SeqLM.from_pretrained("potsawee/t5-large-generation-squad-QuestionAnswer")
>>> context = r"""Chelsea's mini-revival continued with a third victory in a row as they consigned struggling Leicester City to a fifth consecutive defeat.
Buoyed by their Champions League win over Borussia Dortmund, Chelsea started brightly and Ben Chilwell volleyed in from a tight angle against his old club.
Chelsea's Joao Felix and Leicester's Kiernan Dewsbury-Hall hit the woodwork in the space of two minutes, then Felix had a goal ruled out by the video assistant referee for offside.
Patson Daka rifled home an excellent equaliser after Ricardo Pereira won the ball off the dawdling Felix outside the box.
But Kai Havertz pounced six minutes into first-half injury time with an excellent dinked finish from Enzo Fernandez's clever aerial ball.
Mykhailo Mudryk thought he had his first goal for the Blues after the break but his effort was disallowed for offside.
Mateo Kovacic sealed the win as he volleyed in from Mudryk's header.
The sliding Foxes, who ended with 10 men following Wout Faes' late dismissal for a second booking, now just sit one point outside the relegation zone.
""".replace('\n', ' ')
>>> inputs = tokenizer(context, return_tensors="pt")
>>> outputs = model.generate(**inputs, max_length=100)
>>> question_answer = tokenizer.decode(outputs[0], skip_special_tokens=False)
>>> question_answer = question_answer.replace(tokenizer.pad_token, "").replace(tokenizer.eos_token, "")
>>> question, answer = question_answer.split(tokenizer.sep_token)
>>> print("question:", question)
question: Who scored the winner for Chelsea?
>>> print("answer:", answer)
answer: Mateo Kovacic
```
## Generating Distractors (other options in a multiple-choice setup)
```Context ---> Question + (A) Answer (B) Distractor1 (C) Distractor2 (D) Distractor3```
Please refer to our distractor generation model, e.g. https://huggingface.co/potsawee/t5-large-generation-race-Distractor
## Citation
```bibtex
@article{manakul2023mqag,
title={MQAG: Multiple-choice Question Answering and Generation for Assessing Information Consistency in Summarization},
author={Manakul, Potsawee and Liusie, Adian and Gales, Mark JF},
journal={arXiv preprint arXiv:2301.12307},
year={2023}
}
``` |
nicholasKluge/Aira-2-1B5 | nicholasKluge | "2024-06-18T11:20:44Z" | 1,059 | 1 | transformers | [
"transformers",
"pytorch",
"safetensors",
"gpt2",
"text-generation",
"alignment",
"instruction tuned",
"text generation",
"conversation",
"assistant",
"en",
"dataset:nicholasKluge/instruct-aira-dataset",
"arxiv:1803.05457",
"arxiv:2109.07958",
"arxiv:2203.09509",
"license:apache-2.0",
"co2_eq_emissions",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-06-23T10:59:15Z" | ---
license: apache-2.0
datasets:
- nicholasKluge/instruct-aira-dataset
language:
- en
metrics:
- accuracy
library_name: transformers
tags:
- alignment
- instruction tuned
- text generation
- conversation
- assistant
pipeline_tag: text-generation
widget:
- text: "<|startofinstruction|>Can you explain what is Machine Learning?<|endofinstruction|>"
example_title: Machine Learning
- text: "<|startofinstruction|>Do you know anything about virtue ethics?<|endofinstruction|>"
example_title: Ethics
- text: "<|startofinstruction|>How can I make my girlfriend happy?<|endofinstruction|>"
example_title: Advise
inference:
parameters:
repetition_penalty: 1.2
temperature: 0.2
top_k: 30
top_p: 0.3
max_new_tokens: 200
length_penalty: 0.3
early_stopping: true
co2_eq_emissions:
emissions: 1690
source: CodeCarbon
training_type: fine-tuning
geographical_location: United States of America
hardware_used: NVIDIA A100-SXM4-40GB
---
# Aira-2-1B5
Aira-2 is the second version of the Aira instruction-tuned series. Aira-2-1B5 is an instruction-tuned model based on [GPT-2](https://huggingface.co/gpt2-xl). The model was trained with a dataset composed of prompts and completions generated synthetically by prompting already-tuned models (ChatGPT, Llama, Open-Assistant, etc).
Check our gradio-demo in [Spaces](https://huggingface.co/spaces/nicholasKluge/Aira-Demo).
## Details
- **Size:** 1,557,614,400 parameters
- **Dataset:** [Instruct-Aira Dataset](https://huggingface.co/datasets/nicholasKluge/instruct-aira-dataset)
- **Language:** English
- **Number of Epochs:** 3
- **Batch size:** 4
- **Optimizer:** `torch.optim.AdamW` (warmup_steps = 1e2, learning_rate = 5e-4, epsilon = 1e-8)
- **GPU:** 1 NVIDIA A100-SXM4-40GB
- **Emissions:** 1.69 KgCO2 (Singapore)
- **Total Energy Consumption:** 3.47 kWh
This repository has the [source code](https://github.com/Nkluge-correa/Aira) used to train this model.
## Usage
Three special tokens are used to mark the user side of the interaction and the model's response:
`<|startofinstruction|>`What is a language model?`<|endofinstruction|>`A language model is a probability distribution over a vocabulary.`<|endofcompletion|>`
```python
from transformers import AutoTokenizer, AutoModelForCausalLM
import torch
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
tokenizer = AutoTokenizer.from_pretrained('nicholasKluge/Aira-2-1B5')
aira = AutoModelForCausalLM.from_pretrained('nicholasKluge/Aira-2-1B5')
aira.eval()
aira.to(device)
question = input("Enter your question: ")
inputs = tokenizer(tokenizer.bos_token + question + tokenizer.sep_token,
add_special_tokens=False,
return_tensors="pt").to(device)
responses = aira.generate(**inputs, num_return_sequences=2)
print(f"Question: 👤 {question}\n")
for i, response in enumerate(responses):
print(f'Response {i+1}: 🤖 {tokenizer.decode(response, skip_special_tokens=True).replace(question, "")}')
```
The model will output something like:
```markdown
>>>Question: 👤 What is the capital of Brazil?
>>>Response 1: 🤖 The capital of Brazil is Brasília.
>>>Response 2: 🤖 The capital of Brazil is Brasília.
```
## Limitations
- **Hallucinations:** This model can produce content that can be mistaken for truth but is, in fact, misleading or entirely false, i.e., hallucination.
- **Biases and Toxicity:** This model inherits the social and historical stereotypes from the data used to train it. Given these biases, the model can produce toxic content, i.e., harmful, offensive, or detrimental to individuals, groups, or communities.
- **Repetition and Verbosity:** The model may get stuck on repetition loops (especially if the repetition penalty during generations is set to a meager value) or produce verbose responses unrelated to the prompt it was given.
## Evaluation
|Model |Average |[ARC](https://arxiv.org/abs/1803.05457) |[TruthfulQA](https://arxiv.org/abs/2109.07958) |[ToxiGen](https://arxiv.org/abs/2203.09509) |
| ---------------------------------------------------------------------- | -------- | -------------------------------------- | --------------------------------------------- | ------------------------------------------ |
|[Aira-2-124M-DPO](https://huggingface.co/nicholasKluge/Aira-2-124M-DPO) |**40.68** |**24.66** |**42.61** |**54.79** |
|[Aira-2-124M](https://huggingface.co/nicholasKluge/Aira-2-124M) |38.07 |24.57 |41.02 |48.62 |
|GPT-2 |35.37 |21.84 |40.67 |43.62 |
|[Aira-2-355M](https://huggingface.co/nicholasKluge/Aira-2-355M) |**39.68** |**27.56** |38.53 |**53.19** |
|GPT-2-medium |36.43 |27.05 |**40.76** |41.49 |
|[Aira-2-774M](https://huggingface.co/nicholasKluge/Aira-2-774M) |**42.26** |**28.75** |**41.33** |**56.70** |
|GPT-2-large |35.16 |25.94 |38.71 |40.85 |
|[Aira-2-1B5](https://huggingface.co/nicholasKluge/Aira-2-1B5) |**42.22** |28.92 |**41.16** |**56.60** |
|GPT-2-xl |36.84 |**30.29** |38.54 |41.70 |
* Evaluations were performed using the [Language Model Evaluation Harness](https://github.com/EleutherAI/lm-evaluation-harness) (by [EleutherAI](https://www.eleuther.ai/)).
## Cite as 🤗
```latex
@misc{nicholas22aira,
doi = {10.5281/zenodo.6989727},
url = {https://github.com/Nkluge-correa/Aira},
author = {Nicholas Kluge Corrêa},
title = {Aira},
year = {2023},
publisher = {GitHub},
journal = {GitHub repository},
}
@phdthesis{kluge2024dynamic,
title={Dynamic Normativity},
author={Kluge Corr{\^e}a, Nicholas},
year={2024},
school={Universit{\"a}ts-und Landesbibliothek Bonn}
}
```
## License
Aira-2-1B5 is licensed under the Apache License, Version 2.0. See the [LICENSE](LICENSE) file for more details.
|
Yntec/lamettaNightly | Yntec | "2023-10-01T19:19:23Z" | 1,059 | 5 | diffusers | [
"diffusers",
"safetensors",
"Anime",
"Chibi",
"Adorable",
"Lasorco",
"stable-diffusion",
"stable-diffusion-diffusers",
"text-to-image",
"license:creativeml-openrail-m",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
] | text-to-image | "2023-09-11T17:23:12Z" | ---
license: creativeml-openrail-m
library_name: diffusers
pipeline_tag: text-to-image
tags:
- Anime
- Chibi
- Adorable
- Lasorco
- stable-diffusion
- stable-diffusion-diffusers
- text-to-image
- diffusers
inference: true
---
# lametta Nightly
Made for the inference API, the 'Nightly' version remains updated to the latest version of lametta, currently hosting v1930.
Sample and prompt:
(hyperrealist painting of a girl as genie with a sun on each shoulder ), 1940, magazine ad, iconic. by Daniel F. Gerhartz and greg rutkowski, aggressive color palette, elegant, dream, fantasy, dynamic lighting, beautiful, poster, wlop, trending on artstation, wallpaper, 4 k, award winning, digital art, very
Original Page:
https://huggingface.co/Lasorco/lametta |
Abe13/Full-juni-dolphin-2.1-mistral-7b | Abe13 | "2023-10-31T04:41:48Z" | 1,059 | 0 | transformers | [
"transformers",
"pytorch",
"mistral",
"text-generation",
"conversational",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-10-26T01:25:42Z" | ---
license: apache-2.0
---
ChatGPT: "This iteration signifies a meticulously fine-tuned version designed to seamlessly integrate new knowledge into the model's existing framework. The primary goal is to enhance the model's understanding and performance by updating its knowledge base, all while ensuring that its pre-existing capabilities are retained and not compromised." |
Sao10K/Hesperus-v1-13B-L2-fp16 | Sao10K | "2023-11-08T00:58:51Z" | 1,059 | 2 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"en",
"license:llama2",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-11-05T16:08:26Z" | ---
license: llama2
language:
- en
---
Full fp16 Repo.
<br>For GGUF Quants, visit: https://huggingface.co/Sao10K/Hesperus-v1-13B-L2-GGUF
<br>For Adapter, visit: https://huggingface.co/Sao10K/Hesperus-v1-LoRA
Hesperus-v1 - A trained 8-bit LoRA for RP & General Purposes.
<br>Trained on the base 13B Llama 2 model.
Dataset Entry Rows:
<br>RP: 8.95K
<br>MED: 10.5K
<br>General: 8.7K
<br>Total: 28.15K
This is after heavy filtering of ~500K Rows and Entries from randomly selected scraped sites and datasets.
v1 is simply an experimental release. V2 will be the main product?
<br>Goals:
<br>--- Reduce 28.15K to <10K Entries.
<br>--- Adjust RP / Med / General Ratios again.
<br>--- Fix Formatting, Markdown in Each Entry.
<br>--- Further Filter and Remove Low Quality entries ***again***, with a much harsher pass this time around.
<br>--- Do a spellcheck & fix for entries.
<br>--- Commit to one prompt format for dataset. Either ShareGPT or Alpaca. Not Both.
I recommend keeping Repetition Penalty below 1.1, preferably at 1 as Hesperus begins breaking down at 1.2 Rep Pen and might output nonsense outputs.
Prompt Format:
```
- sharegpt (recommended!)
User:
GPT/Assistant:
```
```
- alpaca (less recommended)
###Instruction:
Your instruction or question here.
For roleplay purposes, I suggest the following - Write <CHAR NAME>'s next reply in a chat between <YOUR NAME> and <CHAR NAME>. Write a single reply only.
###Response:
```
V1 is trained on 50/50 for these two formats.
<br>I am working on converting to either for v2.
Once V2 is Completed, I will also train a 70B variant of this.
EXAMPLE OUTPUTS:
 |
Trelis/deepseek-coder-33b-instruct-function-calling-v3 | Trelis | "2024-01-28T09:15:07Z" | 1,059 | 2 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"deepseek",
"commercial use",
"function-calling",
"function calling",
"conversational",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-12-26T11:21:47Z" | ---
tags:
- deepseek
- commercial use
- function-calling
- function calling
extra_gated_prompt: "Purchase access to this repo [HERE](https://buy.stripe.com/14k3cY4pL4PFbQY3dq)"
---
# Function Calling Fine-tuned DeepSeek Coder 33B
Purchase access to this model [here](https://buy.stripe.com/14k3cY4pL4PFbQY3dq).
Performance demo video [here](https://share.descript.com/view/0uQraTWCbkp).
This model is fine-tuned for function calling.
- The function metadata format is the same as used for OpenAI.
- The model is suitable for commercial use.
- AWQ and GGUF are available on request after purchase.
Check out other fine-tuned function calling models [here](https://mart.trelis.com).
## Quick Server Setup
Runpod one click templates: [You must add a HuggingFace Hub access token (HUGGING_FACE_HUB_TOKEN) to the environment variables as this is a gated model.]
- [4bit awq](https://runpod.io/gsc?template=lvxofymu84&ref=jmfkcdio)
- [8bit with eetq](https://runpod.io/gsc?template=pb0wx07yam&ref=jmfkcdio).
Runpod Affiliate [Link](https://runpod.io?ref=jmfkcdio) (helps support the Trelis channel).
## Inference Scripts
See below for sample prompt format.
Complete inference scripts are available for purchase [here](https://trelis.com/enterprise-server-api-and-inference-guide/):
- Easily format prompts using tokenizer.apply_chat_format (starting from openai formatted functions and a list of messages)
- Automate catching, handling and chaining of function calls.
## Prompt Format
```
B_FUNC, E_FUNC = "You have access to the following functions. Use them if required:\n\n", "\n\n"
B_INST, E_INST = "\n### Instruction:\n", "\n### Response:\n" #DeepSeek Coder Style
prompt = f"{B_INST}{B_FUNC}{functionList.strip()}{E_FUNC}{user_prompt.strip()}{E_INST}\n\n"
```
### Using tokenizer.apply_chat_template
For an easier application of the prompt, you can set up as follows:
Set up `messages`:
```
[
{
"role": "function_metadata",
"content": "FUNCTION_METADATA"
},
{
"role": "user",
"content": "What is the current weather in London?"
},
{
"role": "function_call",
"content": "{\n \"name\": \"get_current_weather\",\n \"arguments\": {\n \"city\": \"London\"\n }\n}"
},
{
"role": "function_response",
"content": "{\n \"temperature\": \"15 C\",\n \"condition\": \"Cloudy\"\n}"
},
{
"role": "assistant",
"content": "The current weather in London is Cloudy with a temperature of 15 Celsius"
}
]
```
with `FUNCTION_METADATA` as:
```
[
{
"type": "function",
"function": {
"name": "get_current_weather",
"description": "This function gets the current weather in a given city",
"parameters": {
"type": "object",
"properties": {
"city": {
"type": "string",
"description": "The city, e.g., San Francisco"
},
"format": {
"type": "string",
"enum": ["celsius", "fahrenheit"],
"description": "The temperature unit to use."
}
},
"required": ["city"]
}
}
},
{
"type": "function",
"function": {
"name": "get_clothes",
"description": "This function provides a suggestion of clothes to wear based on the current weather",
"parameters": {
"type": "object",
"properties": {
"temperature": {
"type": "string",
"description": "The temperature, e.g., 15 C or 59 F"
},
"condition": {
"type": "string",
"description": "The weather condition, e.g., 'Cloudy', 'Sunny', 'Rainy'"
}
},
"required": ["temperature", "condition"]
}
}
}
]
```
and then apply the chat template to get a formatted prompt:
```
tokenizer = AutoTokenizer.from_pretrained('Trelis/deepseek-coder-33b-instruct-function-calling-v3', trust_remote_code=True)
prompt = tokenizer.apply_chat_template(prompt, tokenize=False, add_generation_prompt=True)
```
If you are using a gated model, you need to first run:
```
pip install huggingface_hub
huggingface-cli login
```
### Manual Prompt:
```
Human: You have access to the following functions. Use them if required:
[
{
"type": "function",
"function": {
"name": "get_stock_price",
"description": "Get the stock price of an array of stocks",
"parameters": {
"type": "object",
"properties": {
"names": {
"type": "array",
"items": {
"type": "string"
},
"description": "An array of stocks"
}
},
"required": [
"names"
]
}
}
},
{
"type": "function",
"function": {
"name": "get_big_stocks",
"description": "Get the names of the largest N stocks by market cap",
"parameters": {
"type": "object",
"properties": {
"number": {
"type": "integer",
"description": "The number of largest stocks to get the names of, e.g. 25"
},
"region": {
"type": "string",
"description": "The region to consider, can be \"US\" or \"World\"."
}
},
"required": [
"number"
]
}
}
}
]
Get the names of the five largest stocks by market cap Assistant:
{
"name": "get_big_stocks",
"arguments": {
"number": 5
}
}<|EOT|>```
# Dataset
See [Trelis/function_calling_v3](https://huggingface.co/datasets/Trelis/function_calling_v3).
# License
This model may be used commercially for inference according to the terms of the DeepSeek license, or for further fine-tuning and inference. Users may not re-publish or re-sell this model in the same or derivative form (including fine-tunes).
**
The SFT chat fine-tuned model's repo card follows below.
**
<p align="center">
<img width="1000px" alt="DeepSeek Coder" src="https://github.com/deepseek-ai/DeepSeek-Coder/blob/main/pictures/logo.png?raw=true">
</p>
<p align="center"><a href="https://www.deepseek.com/">[🏠Homepage]</a> | <a href="https://coder.deepseek.com/">[🤖 Chat with DeepSeek Coder]</a> | <a href="https://discord.gg/Tc7c45Zzu5">[Discord]</a> | <a href="https://github.com/guoday/assert/blob/main/QR.png?raw=true">[Wechat(微信)]</a> </p>
<hr>
### 1. Introduction of Deepseek Coder
Deepseek Coder is composed of a series of code language models, each trained from scratch on 2T tokens, with a composition of 87% code and 13% natural language in both English and Chinese. We provide various sizes of the code model, ranging from 1B to 33B versions. Each model is pre-trained on project-level code corpus by employing a window size of 16K and a extra fill-in-the-blank task, to support project-level code completion and infilling. For coding capabilities, Deepseek Coder achieves state-of-the-art performance among open-source code models on multiple programming languages and various benchmarks.
- **Massive Training Data**: Trained from scratch on 2T tokens, including 87% code and 13% linguistic data in both English and Chinese languages.
- **Highly Flexible & Scalable**: Offered in model sizes of 1.3B, 5.7B, 6.7B, and 33B, enabling users to choose the setup most suitable for their requirements.
- **Superior Model Performance**: State-of-the-art performance among publicly available code models on HumanEval, MultiPL-E, MBPP, DS-1000, and APPS benchmarks.
- **Advanced Code Completion Capabilities**: A window size of 16K and a fill-in-the-blank task, supporting project-level code completion and infilling tasks.
### 2. Model Summary
deepseek-coder-33b-instruct is a 33B parameter model initialized from deepseek-coder-33b-base and fine-tuned on 2B tokens of instruction data.
- **Home Page:** [DeepSeek](https://deepseek.com/)
- **Repository:** [deepseek-ai/deepseek-coder](https://github.com/deepseek-ai/deepseek-coder)
- **Chat With DeepSeek Coder:** [DeepSeek-Coder](https://coder.deepseek.com/)
### 3. How to Use
Here give some examples of how to use our model.
#### Chat Model Inference
```python
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("deepseek-ai/deepseek-coder-33b-instruct", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("deepseek-ai/deepseek-coder-33b-instruct", trust_remote_code=True).cuda()
messages=[
{ 'role': 'user', 'content': "write a quick sort algorithm in python."}
]
inputs = tokenizer.apply_chat_template(messages, return_tensors="pt").to(model.device)
# 32021 is the id of <|EOT|> token
outputs = model.generate(inputs, max_new_tokens=512, do_sample=False, top_k=50, top_p=0.95, num_return_sequences=1, eos_token_id=32021)
print(tokenizer.decode(outputs[0][len(inputs[0]):], skip_special_tokens=True))
```
### 4. License
This code repository is licensed under the MIT License. The use of DeepSeek Coder models is subject to the Model License. DeepSeek Coder supports commercial use.
See the [LICENSE-MODEL](https://github.com/deepseek-ai/deepseek-coder/blob/main/LICENSE-MODEL) for more details.
### 5. Contact
If you have any questions, please raise an issue or contact us at [[email protected]](mailto:[email protected]).
|
ResplendentAI/Aura_Uncensored_l3_8B | ResplendentAI | "2024-04-21T02:53:09Z" | 1,059 | 17 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"conversational",
"en",
"base_model:Undi95/Llama-3-Unholy-8B",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-04-20T23:37:34Z" | ---
base_model:
- Undi95/Llama-3-Unholy-8B
- Undi95/Llama-3-Unholy-8B
- ResplendentAI/Aura_Llama3
- Undi95/Llama-3-Unholy-8B
- ResplendentAI/RP_Format_QuoteAsterisk_Llama3
- Undi95/Llama-3-Unholy-8B
- ResplendentAI/Luna_Llama3
- Undi95/Llama-3-Unholy-8B
- ResplendentAI/Theory_of_Mind_Llama3
- Undi95/Llama-3-Unholy-8B
- ResplendentAI/BlueMoon_Llama3
library_name: transformers
license: apache-2.0
language:
- en
---
# Aura Uncensored l3
AWQ here: https://huggingface.co/lucyknada/Aura_Uncensored_l3_8B-AWQ
GGUF here: https://huggingface.co/Lewdiculous/Aura_Uncensored_l3_8B-GGUF-IQ-Imatrix
This is the culmination of all my efforts for the Aura line. I have taken the original training data and applied it over Undi95's Unholy base model. This model can and will provide unsafe information and RP. I strongly recommend that you do not use this model if you are sensitive to unsafe output.
I have tested the model thoroughly and believe that it will please the majority of users. I hope that you enjoy this model. |
pszemraj/griffin-v0.01-c3t-8layer-simplewiki-silu | pszemraj | "2024-04-25T19:35:13Z" | 1,059 | 0 | transformers | [
"transformers",
"safetensors",
"recurrent_gemma",
"text-generation",
"generated_from_trainer",
"en",
"dataset:pszemraj/simple_wikipedia_LM",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-generation | "2024-04-25T00:46:35Z" | ---
tags:
- generated_from_trainer
metrics:
- accuracy
license: apache-2.0
datasets:
- pszemraj/simple_wikipedia_LM
language:
- en
---
<!-- 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. -->
# griffin-v0.01-c3t-8layer-simplewiki-silu
- griffin/recurrent_gemma arch
- claude3 tokenizer (as an HF gpt2 tokenizer)
## Model description
pretrain experiment on the pszemraj/simple_wikipedia_LM dataset.
It achieves the following results on the evaluation set:
- Loss: 4.0476
- Accuracy: 0.4224
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0003
- train_batch_size: 4
- eval_batch_size: 4
- seed: 80085
- gradient_accumulation_steps: 32
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.99) and epsilon=1e-07
- lr_scheduler_type: constant_with_warmup
- lr_scheduler_warmup_ratio: 0.05
- num_epochs: 2.0
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:------:|:----:|:---------------:|:--------:|
| 13.3276 | 0.2548 | 100 | 12.0402 | 0.0131 |
| 8.9207 | 0.5095 | 200 | 8.0312 | 0.0360 |
| 7.2681 | 0.7643 | 300 | 6.4775 | 0.0506 |
| 6.3187 | 1.0190 | 400 | 5.6227 | 0.0434 |
| 5.5695 | 1.2738 | 500 | 4.7796 | 0.3635 |
| 5.2926 | 1.5285 | 600 | 4.3923 | 0.3952 |
| 4.878 | 1.7833 | 700 | 4.1877 | 0.4085 |
### Framework versions
- Transformers 4.40.1
- Pytorch 2.2.0+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1 |
ThinkDiffusion/ThinkDiffusionXL | ThinkDiffusion | "2023-11-18T13:23:05Z" | 1,058 | 17 | diffusers | [
"diffusers",
"safetensors",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionXLPipeline",
"region:us"
] | text-to-image | "2023-10-21T11:57:16Z" | <b>ThinkDiffusionXL (TDXL)</b>
ThinkDiffusionXL is the result of our goal to build a go-to model capable of amazing photorealism that's also versatile enough to generate high-quality images across a variety of styles and subjects without needing to be a prompting genius.
You can find it preloaded on https://www.thinkdiffusion.com
<b>The work</b>
<b>Data source:</b>
TDXL is trained on over 10,000 diverse images that span photorealism, digital art, anime, and more. The smallest resolution in our dataset is 1365x2048, but many images go up to resolutions as high as 4622x6753. In total, our dataset takes up 42GB.
<b>Training: </b>
With 1.8 million steps, we’ve put in the work. For comparison, Juggernaut is at 600k steps and RealVisXL is at 348k steps
<b>Hand-captioned images:</b>
Each image is carefully captioned by hand, enhancing the model's ability to generate accurate and high-quality results from minimal prompts.
<b>NSFW capabilities: </b>
The model includes over 1,000 tastefully curated NSFW images.
<b>Our thoughts</b>
<b>Detail and quality: </b>
Most XL models in the Realistic category suffer from poor detail, especially in the background and even in basic features like eyes, teeth, and skin. We believe TDXL outperforms in these areas due to its large, high-quality dataset. For comparison, Juggernaut has about half the image material, and RealVisXL has only 1,700 images. Ultimately, TDXL simply possesses much more "knowledge".
<b>Less bias: </b>
We made sure to use an equal number of images for each style, gender, etc. Other models we tested over the past few months had some kind of bias, sometimes it was bias toward portrait shots, gender bias, certain ethnicities, etc. For instance, Juggernaut has a bias in the Close-Up area, and the Cinematic Light is quite dominant in that model. RealVisXL also has a bias towards Portrait shots. On the other hand, TDXL gives you what you want: Landscape, Midshot, Full Body, Close-Up, Portrait, Sideview, Backview, Action Shots, Cinematic...whatever you want without always being pushed in a certain direction due to a bias.
<b>Versatile base: </b>
Because of its large balanced quality dataset, TDXL is versatile to serve as a base model for future trainings. You can create new finetunes in entirely different directions, add LoRAs to fill in missing concepts, or do additional trainings with more balanced quality data.
https://github.com/Stability-AI/generative-models/blob/main/model_licenses/LICENSE-SDXL1.0 |
Abe13/Full-juni-Mistral-7B-OpenOrca | Abe13 | "2023-10-31T04:42:53Z" | 1,058 | 0 | transformers | [
"transformers",
"pytorch",
"mistral",
"text-generation",
"conversational",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-10-24T13:01:49Z" | ---
license: apache-2.0
---
ChatGPT: "This iteration signifies a meticulously fine-tuned version designed to seamlessly integrate new knowledge into the model's existing framework. The primary goal is to enhance the model's understanding and performance by updating its knowledge base, all while ensuring that its pre-existing capabilities are retained and not compromised." |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.