Instructions to use TheBloke/Mistral-7B-Instruct-v0.1-AWQ with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TheBloke/Mistral-7B-Instruct-v0.1-AWQ with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="TheBloke/Mistral-7B-Instruct-v0.1-AWQ")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("TheBloke/Mistral-7B-Instruct-v0.1-AWQ")
model = AutoModelForCausalLM.from_pretrained("TheBloke/Mistral-7B-Instruct-v0.1-AWQ")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use TheBloke/Mistral-7B-Instruct-v0.1-AWQ with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "TheBloke/Mistral-7B-Instruct-v0.1-AWQ"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "TheBloke/Mistral-7B-Instruct-v0.1-AWQ",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/TheBloke/Mistral-7B-Instruct-v0.1-AWQ

SGLang

How to use TheBloke/Mistral-7B-Instruct-v0.1-AWQ with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "TheBloke/Mistral-7B-Instruct-v0.1-AWQ" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "TheBloke/Mistral-7B-Instruct-v0.1-AWQ",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "TheBloke/Mistral-7B-Instruct-v0.1-AWQ" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "TheBloke/Mistral-7B-Instruct-v0.1-AWQ",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use TheBloke/Mistral-7B-Instruct-v0.1-AWQ with Docker Model Runner:
```
docker model run hf.co/TheBloke/Mistral-7B-Instruct-v0.1-AWQ
```

TheBloke commited on Sep 29, 2023

Commit

b1c0cfa

1 Parent(s): 1e3e5b0

Update README.md

Browse files

Files changed (1) hide show

README.md +3 -2

README.md CHANGED Viewed

@@ -49,7 +49,9 @@ AWQ is an efficient, accurate and blazing-fast low-bit weight quantization metho
 These are experimental first AWQs for the brand-new model format, Mistral.
-They will not work from vLLM or TGI. They can only be used from AutoAWQ, and they require installing both AutoAWQ and Transformers from Github. More details are below.
 <!-- description end -->
 <!-- repositories-available start -->
@@ -66,7 +68,6 @@ They will not work from vLLM or TGI. They can only be used from AutoAWQ, and the
 ```
 <s>[INST] {prompt} [/INST]
 ```
 <!-- prompt-template end -->

 These are experimental first AWQs for the brand-new model format, Mistral.
+As of September 29th 2023, they are supported by AutoAWQ, and vLLM (version 0.2).
+To use from AutoAW£Q requires installing both AutoAWQ and Transformers from Github. More details are below.
 <!-- description end -->
 <!-- repositories-available start -->
 ```
 <s>[INST] {prompt} [/INST]
 ```
 <!-- prompt-template end -->