Instructions to use blockblockblock/Code-Mistral-7B-bpw3.7 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use blockblockblock/Code-Mistral-7B-bpw3.7 with Transformers:

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

pipe = pipeline("text-generation", model="blockblockblock/Code-Mistral-7B-bpw3.7")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("blockblockblock/Code-Mistral-7B-bpw3.7")
model = AutoModelForCausalLM.from_pretrained("blockblockblock/Code-Mistral-7B-bpw3.7")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use blockblockblock/Code-Mistral-7B-bpw3.7 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "blockblockblock/Code-Mistral-7B-bpw3.7"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "blockblockblock/Code-Mistral-7B-bpw3.7",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/blockblockblock/Code-Mistral-7B-bpw3.7

SGLang

How to use blockblockblock/Code-Mistral-7B-bpw3.7 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 "blockblockblock/Code-Mistral-7B-bpw3.7" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "blockblockblock/Code-Mistral-7B-bpw3.7",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "blockblockblock/Code-Mistral-7B-bpw3.7" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "blockblockblock/Code-Mistral-7B-bpw3.7",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use blockblockblock/Code-Mistral-7B-bpw3.7 with Docker Model Runner:
```
docker model run hf.co/blockblockblock/Code-Mistral-7B-bpw3.7
```

ValueError: Unknown quantization type, got exl2 - supported types are: ['awq', 'bitsandbytes_4bit', 'bitsandbytes_8bit', 'gptq', 'aqlm', 'quanto', 'eetq', 'hqq']

by Pierre918 - opened May 20, 2024

Discussion

Pierre918

May 20, 2024

Hello !
When i run : pipe = pipeline("text-generation", model="blockblockblock/Code-Mistral-7B-bpw3.7")
i get the error in the title. I have also imported : from transformers import pipeline
I am beginner so maybe it is just something i didn't install.

Thank you for your help

blockblockblock

Owner May 21, 2024

Hello !
When i run : pipe = pipeline("text-generation", model="blockblockblock/Code-Mistral-7B-bpw3.7")
i get the error in the title. I have also imported : from transformers import pipeline
I am beginner so maybe it is just something i didn't install.

Thank you for your help

Hi, the models are in exl2 format and are to be used with aphro or exllama.

Pierre918

May 22, 2024

Hello !
When i run : pipe = pipeline("text-generation", model="blockblockblock/Code-Mistral-7B-bpw3.7")
i get the error in the title. I have also imported : from transformers import pipeline
I am beginner so maybe it is just something i didn't install.

Thank you for your help

Hi, the models are in exl2 format and are to be used with aphro or exllama.

Hi ! Thank you very much for your answer.
So concretely, what do you have to do in my command shell (i'm on windows) or in the python file ?
I am very beginner.

Thank you for your help.

blockblockblock

Owner May 28, 2024

Hello !
When i run : pipe = pipeline("text-generation", model="blockblockblock/Code-Mistral-7B-bpw3.7")
i get the error in the title. I have also imported : from transformers import pipeline
I am beginner so maybe it is just something i didn't install.

Thank you for your help

Hi, the models are in exl2 format and are to be used with aphro or exllama.

Hi ! Thank you very much for your answer.
So concretely, what do you have to do in my command shell (i'm on windows) or in the python file ?
I am very beginner.

Thank you for your help.
No problem.
in order to use exl2 quant you need to use exllama.

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment