---
base_model: EleutherAI/llemma_7b
datasets:
- EleutherAI/proof-pile-2
inference: false
language:
- en
license: llama2
model_creator: EleutherAI
model_name: Llemma 7B
model_type: llama
prompt_template: '{prompt}
'
quantized_by: TheBloke
tags:
- math
- reasoning
---
# Llemma 7B - AWQ
- Model creator: [EleutherAI](https://huggingface.co/EleutherAI)
- Original model: [Llemma 7B](https://huggingface.co/EleutherAI/llemma_7b)
## Description
This repo contains AWQ model files for [EleutherAI's Llemma 7B](https://huggingface.co/EleutherAI/llemma_7b).
### About AWQ
AWQ is an efficient, accurate and blazing-fast low-bit weight quantization method, currently supporting 4-bit quantization. Compared to GPTQ, it offers faster Transformers-based inference with equivalent or better quality compared to the most commonly used GPTQ settings.
It is supported by:
- [Text Generation Webui](https://github.com/oobabooga/text-generation-webui) - using Loader: AutoAWQ
- [vLLM](https://github.com/vllm-project/vllm) - Llama and Mistral models only
- [Hugging Face Text Generation Inference (TGI)](https://github.com/huggingface/text-generation-inference)
- [AutoAWQ](https://github.com/casper-hansen/AutoAWQ) - for use from Python code
## Repositories available
* [AWQ model(s) for GPU inference.](https://huggingface.co/TheBloke/llemma_7b-AWQ)
* [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/llemma_7b-GPTQ)
* [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/llemma_7b-GGUF)
* [EleutherAI's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/EleutherAI/llemma_7b)
## Prompt template: Unknown
```
{prompt}
```
## Provided files, and AWQ parameters
For my first release of AWQ models, I am releasing 128g models only. I will consider adding 32g as well if there is interest, and once I have done perplexity and evaluation comparisons, but at this time 32g models are still not fully tested with AutoAWQ and vLLM.
Models are released as sharded safetensors files.
| Branch | Bits | GS | AWQ Dataset | Seq Len | Size |
| ------ | ---- | -- | ----------- | ------- | ---- |
| [main](https://huggingface.co/TheBloke/llemma_7b-AWQ/tree/main) | 4 | 128 | [CamelAI Math](https://huggingface.co/datasets/andersonbcdefg/math) | 4096 | 3.89 GB
## How to easily download and use this model in [text-generation-webui](https://github.com/oobabooga/text-generation-webui)
Please make sure you're using the latest version of [text-generation-webui](https://github.com/oobabooga/text-generation-webui).
It is strongly recommended to use the text-generation-webui one-click-installers unless you're sure you know how to make a manual install.
1. Click the **Model tab**.
2. Under **Download custom model or LoRA**, enter `TheBloke/llemma_7b-AWQ`.
3. Click **Download**.
4. The model will start downloading. Once it's finished it will say "Done".
5. In the top left, click the refresh icon next to **Model**.
6. In the **Model** dropdown, choose the model you just downloaded: `llemma_7b-AWQ`
7. Select **Loader: AutoAWQ**.
8. Click Load, and the model will load and is now ready for use.
9. If you want any custom settings, set them and then click **Save settings for this model** followed by **Reload the Model** in the top right.
10. Once you're ready, click the **Text Generation** tab and enter a prompt to get started!
## Multi-user inference server: vLLM
Documentation on installing and using vLLM [can be found here](https://vllm.readthedocs.io/en/latest/).
- Please ensure you are using vLLM version 0.2 or later.
- When using vLLM as a server, pass the `--quantization awq` parameter.
For example:
```shell
python3 python -m vllm.entrypoints.api_server --model TheBloke/llemma_7b-AWQ --quantization awq
```
- When using vLLM from Python code, again set `quantization=awq`.
For example:
```python
from vllm import LLM, SamplingParams
prompts = [
"Tell me about AI",
"Write a story about llamas",
"What is 291 - 150?",
"How much wood would a woodchuck chuck if a woodchuck could chuck wood?",
]
prompt_template=f'''{prompt}
'''
prompts = [prompt_template.format(prompt=prompt) for prompt in prompts]
sampling_params = SamplingParams(temperature=0.8, top_p=0.95)
llm = LLM(model="TheBloke/llemma_7b-AWQ", quantization="awq", dtype="auto")
outputs = llm.generate(prompts, sampling_params)
# Print the outputs.
for output in outputs:
prompt = output.prompt
generated_text = output.outputs[0].text
print(f"Prompt: {prompt!r}, Generated text: {generated_text!r}")
```
## Multi-user inference server: Hugging Face Text Generation Inference (TGI)
Use TGI version 1.1.0 or later. The official Docker container is: `ghcr.io/huggingface/text-generation-inference:1.1.0`
Example Docker parameters:
```shell
--model-id TheBloke/llemma_7b-AWQ --port 3000 --quantize awq --max-input-length 3696 --max-total-tokens 4096 --max-batch-prefill-tokens 4096
```
Example Python code for interfacing with TGI (requires [huggingface-hub](https://github.com/huggingface/huggingface_hub) 0.17.0 or later):
```shell
pip3 install huggingface-hub
```
```python
from huggingface_hub import InferenceClient
endpoint_url = "https://your-endpoint-url-here"
prompt = "Tell me about AI"
prompt_template=f'''{prompt}
'''
client = InferenceClient(endpoint_url)
response = client.text_generation(prompt,
max_new_tokens=128,
do_sample=True,
temperature=0.7,
top_p=0.95,
top_k=40,
repetition_penalty=1.1)
print(f"Model output: ", response)
```
## Inference from Python code using AutoAWQ
### Install the AutoAWQ package
Requires: [AutoAWQ](https://github.com/casper-hansen/AutoAWQ) 0.1.1 or later.
```shell
pip3 install autoawq
```
If you have problems installing [AutoAWQ](https://github.com/casper-hansen/AutoAWQ) using the pre-built wheels, install it from source instead:
```shell
pip3 uninstall -y autoawq
git clone https://github.com/casper-hansen/AutoAWQ
cd AutoAWQ
pip3 install .
```
### AutoAWQ example code
```python
from awq import AutoAWQForCausalLM
from transformers import AutoTokenizer
model_name_or_path = "TheBloke/llemma_7b-AWQ"
# Load tokenizer
tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, trust_remote_code=False)
# Load model
model = AutoAWQForCausalLM.from_quantized(model_name_or_path, fuse_layers=True,
trust_remote_code=False, safetensors=True)
prompt = "Tell me about AI"
prompt_template=f'''{prompt}
'''
print("*** Running model.generate:")
token_input = tokenizer(
prompt_template,
return_tensors='pt'
).input_ids.cuda()
# Generate output
generation_output = model.generate(
token_input,
do_sample=True,
temperature=0.7,
top_p=0.95,
top_k=40,
max_new_tokens=512
)
# Get the tokens from the output, decode them, print them
token_output = generation_output[0]
text_output = tokenizer.decode(token_output)
print("LLM output: ", text_output)
"""
# Inference should be possible with transformers pipeline as well in future
# But currently this is not yet supported by AutoAWQ (correct as of September 25th 2023)
from transformers import pipeline
print("*** Pipeline:")
pipe = pipeline(
"text-generation",
model=model,
tokenizer=tokenizer,
max_new_tokens=512,
do_sample=True,
temperature=0.7,
top_p=0.95,
top_k=40,
repetition_penalty=1.1
)
print(pipe(prompt_template)[0]['generated_text'])
"""
```
## Compatibility
The files provided are tested to work with:
- [text-generation-webui](https://github.com/oobabooga/text-generation-webui) using `Loader: AutoAWQ`.
- [vLLM](https://github.com/vllm-project/vllm) version 0.2.0 and later.
- [Hugging Face Text Generation Inference (TGI)](https://github.com/huggingface/text-generation-inference) version 1.1.0 and later.
- [AutoAWQ](https://github.com/casper-hansen/AutoAWQ) version 0.1.1 and later.
## Discord
For further support, and discussions on these models and AI in general, join us at:
[TheBloke AI's Discord server](https://discord.gg/theblokeai)
## Thanks, and how to contribute
Thanks to the [chirper.ai](https://chirper.ai) team!
Thanks to Clay from [gpus.llm-utils.org](llm-utils)!
I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training.
If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects.
Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits.
* Patreon: https://patreon.com/TheBlokeAI
* Ko-Fi: https://ko-fi.com/TheBlokeAI
**Special thanks to**: Aemon Algiz.
**Patreon special mentions**: Pierre Kircher, Stanislav Ovsiannikov, Michael Levine, Eugene Pentland, Andrey, 준교 김, Randy H, Fred von Graf, Artur Olbinski, Caitlyn Gatomon, terasurfer, Jeff Scroggin, James Bentley, Vadim, Gabriel Puliatti, Harry Royden McLaughlin, Sean Connelly, Dan Guido, Edmond Seymore, Alicia Loh, subjectnull, AzureBlack, Manuel Alberto Morcote, Thomas Belote, Lone Striker, Chris Smitley, Vitor Caleffi, Johann-Peter Hartmann, Clay Pascal, biorpg, Brandon Frisco, sidney chen, transmissions 11, Pedro Madruga, jinyuan sun, Ajan Kanaga, Emad Mostaque, Trenton Dambrowitz, Jonathan Leane, Iucharbius, usrbinkat, vamX, George Stoitzev, Luke Pendergrass, theTransient, Olakabola, Swaroop Kallakuri, Cap'n Zoog, Brandon Phillips, Michael Dempsey, Nikolai Manek, danny, Matthew Berman, Gabriel Tamborski, alfie_i, Raymond Fosdick, Tom X Nguyen, Raven Klaugh, LangChain4j, Magnesian, Illia Dulskyi, David Ziegler, Mano Prime, Luis Javier Navarrete Lozano, Erik Bjäreholt, 阿明, Nathan Dryer, Alex, Rainer Wilmers, zynix, TL, Joseph William Delisle, John Villwock, Nathan LeClaire, Willem Michiel, Joguhyik, GodLy, OG, Alps Aficionado, Jeffrey Morgan, ReadyPlayerEmma, Tiffany J. Kim, Sebastain Graf, Spencer Kim, Michael Davis, webtim, Talal Aujan, knownsqashed, John Detwiler, Imad Khwaja, Deo Leter, Jerry Meng, Elijah Stavena, Rooh Singh, Pieter, SuperWojo, Alexandros Triantafyllidis, Stephen Murray, Ai Maven, ya boyyy, Enrico Ros, Ken Nordquist, Deep Realms, Nicholas, Spiking Neurons AB, Elle, Will Dee, Jack West, RoA, Luke @flexchar, Viktor Bowallius, Derek Yates, Subspace Studios, jjj, Toran Billups, Asp the Wyvern, Fen Risland, Ilya, NimbleBox.ai, Chadd, Nitin Borwankar, Emre, Mandus, Leonard Tan, Kalila, K, Trailburnt, S_X, Cory Kujawski
Thank you to all my generous patrons and donaters!
And thank you again to a16z for their generous grant.
# Original model card: EleutherAI's Llemma 7B
[ArXiv](http://arxiv.org/abs/2310.10631) | [Models](https://huggingface.co/EleutherAI/llemma_34b) | [Data](https://huggingface.co/datasets/EleutherAI/proof-pile-2) | [Code](https://github.com/EleutherAI/math-lm) | [Blog](https://blog.eleuther.ai/llemma/) | [Sample Explorer](https://llemma-demo.github.io/)
[Zhangir Azerbayev](https://zhangir-azerbayev.github.io/), [Hailey Schoelkopf](https://github.com/haileyschoelkopf), [Keiran Paster](https://keirp.com), [Marco Dos Santos](https://github.com/dsantosmarco), [Stephen McAleer](https://www.andrew.cmu.edu/user/smcaleer/), [Albert Q. Jiang](https://albertqjiang.github.io/), [Jia Deng](https://www.cs.princeton.edu/~jiadeng/), [Stella Biderman](https://www.stellabiderman.com/), [Sean Welleck](https://wellecks.com/)
**Llemma 7B** is a language model for mathematics. It was initialized with [Code Llama 7B](https://github.com/facebookresearch/codellama) weights, and trained on the [Proof-Pile-2](https://huggingface.co/datasets/EleutherAI/proof-pile-2) for 200B tokens.
This model also comes in a 34B parameter version: [Llemma 34B](https://huggingface.co/EleutherAI/llemma_34b).
## Evaluations
Llemma models are particularly strong at chain-of-thought mathematical reasoning and using computational tools for mathematics, such as Python and formal theorem provers.
### Chain-of-thought Math
On chain-of-thought mathematics tasks, Llemma models outperform Llama-2, Code Llama, and when controlled for model size, outperform Minerva.
| Model | Size | GSM8k | [OCW](https://openreview.net/forum?id=IFXTZERXdM7) | MMLU-STEM | [SAT](https://huggingface.co/datasets/mcaleste/sat_multiple_choice_math_may_23) | MATH |
|------------|------|--------|-------|-----------|-------|-------|
| Llama 2 | 7B | 11.8% | 3.7% | 29.9% | 25% | 3.2% |
| Code Llama | 7B | 10.5% | 4.4% | 25.1% | 9.4% | 4.5% |
| LLEMMA | 7B | **36.4%** | **7.7%** | **37.7%** | **53.1%** | **18.0%** |
| Minerva | 8B | 16.2% | **7.7%** | 35.6% | - | 14.1% |
|------------|------|--------|-------|-----------|-------|-------|
| Code Llama | 34B | 29.6% | 7.0% | 40.5% | 40.6% | 12.2% |
| LLEMMA | 34B | **51.5%** | **11.8%** | **49.0%** | **71.9%** | **25.0%** |
|------------|------|--------|-------|-----------|-------|-------|
| Minerva | 62B | 52.4% | 12.0% | 53.9% | - | 27.6% |
| Minerva | 540B | 58.8% | 17.6% | 63.9% | - | 33.6% |
Further performance can be extracted by using majority voting:
| Model | Size | GSM8k maj@100 | OCW maj@100 | MMLU-STEM maj@16 | SAT maj@16 | MATH maj@256 |
|---------|------|-------------|-----------|-----------------|-----------|------------|
| LLEMMA | 7B | 54.0% | 14.3% | 49.9% | 78.1% | **33.5** |
| Minerva | 8B | 28.4% | 12.5% | 43.4% | - | 25.4% |
|---------|------|-------------|-----------|-----------------|-----------|------------|
| LLEMMA | 34B | 69.3% | 18.4% | 59.7% | 81.3% | **43.1%** |
|---------|------|-------------|-----------|-----------------|-----------|------------|
| Minerva | 62B | 68.5% | 23.5% | 63.5% | - | 43.4% |
| Minerva | 540B | 78.5% | 30.8% | 75.0% | - | 50.3% |
### Tool Use and Theorem Proving
In addition to chain-of-thought reasoning, Llemma has strong capabilities in computational mathematics tasks. For tool use and formal theorem proving evaluations, see [our paper](http://arxiv.org/abs/2310.10631).
### Citation
```
@misc{azerbayev2023llemma,
title={Llemma: An Open Language Model For Mathematics},
author={Zhangir Azerbayev and Hailey Schoelkopf and Keiran Paster and Marco Dos Santos and Stephen McAleer and Albert Q. Jiang and Jia Deng and Stella Biderman and Sean Welleck},
year={2023},
eprint={2310.10631},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
```
