|
--- |
|
library_name: transformers |
|
license: apache-2.0 |
|
pipeline_tag: text-generation |
|
tags: |
|
- bitsandbytes |
|
- quantized |
|
- 4bit |
|
- Mistral |
|
- Mistral-7B |
|
- bnb |
|
--- |
|
|
|
# Model Card for Mistral-7B-Instruct-v0.2-bnb-4bit |
|
|
|
<!-- Provide a quick summary of what the model is/does. --> |
|
This repo contains 4-bit quantized (using bitsandbytes) model Mistral AI_'s Mistral-7B-Instruct-v0.2 |
|
|
|
|
|
|
|
## Model Details |
|
|
|
- Model creator: [Mistral AI_](https://huggingface.co/mistralai) |
|
- Original model: [Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) |
|
|
|
|
|
### About 4 bit quantization using bitsandbytes |
|
|
|
- QLoRA: Efficient Finetuning of Quantized LLMs: [arXiv - QLoRA: Efficient Finetuning of Quantized LLMs](https://arxiv.org/abs/2305.14314) |
|
|
|
- Hugging Face Blog post on 4-bit quantization using bitsandbytes: [Making LLMs even more accessible with bitsandbytes, 4-bit quantization and QLoRA](https://huggingface.co/blog/4bit-transformers-bitsandbytes) |
|
|
|
- bitsandbytes github repo: [bitsandbytes github repo](https://github.com/TimDettmers/bitsandbytes) |
|
|
|
|
|
|
|
# How to Get Started with the Model |
|
|
|
Use the code below to get started with the model. |
|
|
|
|
|
## How to run from Python code |
|
|
|
#### First install the package |
|
```shell |
|
pip install -q -U bitsandbytes accelerate torch huggingface_hub |
|
pip install -q -U git+https://github.com/huggingface/transformers.git # Install latest version of transformers |
|
pip install -q -U git+https://github.com/huggingface/peft.git |
|
pip install flash-attn --no-build-isolation |
|
``` |
|
|
|
# Import |
|
|
|
```python |
|
import torch |
|
import os |
|
from torch import bfloat16 |
|
from transformers import AutoTokenizer, AutoModelForCausalLM, pipeline, BitsAndBytesConfig, LlamaForCausalLM |
|
``` |
|
|
|
# Use a pipeline as a high-level helper |
|
|
|
```python |
|
model_id_mistral = "alokabhishek/Mistral-7B-Instruct-v0.2-bnb-4bit" |
|
|
|
tokenizer_mistral = AutoTokenizer.from_pretrained(model_id_mistral, use_fast=True) |
|
|
|
model_mistral = AutoModelForCausalLM.from_pretrained( |
|
model_id_mistral, |
|
device_map="auto" |
|
) |
|
|
|
|
|
pipe_mistral = pipeline(model=model_mistral, tokenizer=tokenizer_mistral, task='text-generation') |
|
|
|
prompt_mistral = "Tell me a funny joke about Large Language Models meeting a Blackhole in an intergalactic Bar." |
|
|
|
output_mistral = pipe_llama(prompt_mistral, max_new_tokens=512) |
|
|
|
print(output_mistral[0]["generated_text"]) |
|
|
|
``` |
|
|
|
|
|
## 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] |
|
|
|
|
|
|
|
## Evaluation |
|
|
|
<!-- This section describes the evaluation protocols and provides the results. --> |
|
|
|
|
|
#### Metrics |
|
|
|
<!-- These are the evaluation metrics being used, ideally with a description of why. --> |
|
|
|
[More Information Needed] |
|
|
|
### Results |
|
|
|
[More Information Needed] |
|
|
|
|
|
## Model Card Authors [optional] |
|
|
|
[More Information Needed] |
|
|
|
## Model Card Contact |
|
|
|
[More Information Needed] |
