Instructions to use TheBloke/Mistral-7B-Instruct-v0.2-AWQ with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TheBloke/Mistral-7B-Instruct-v0.2-AWQ with Transformers:

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

pipe = pipeline("text-generation", model="TheBloke/Mistral-7B-Instruct-v0.2-AWQ")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("TheBloke/Mistral-7B-Instruct-v0.2-AWQ")
model = AutoModelForCausalLM.from_pretrained("TheBloke/Mistral-7B-Instruct-v0.2-AWQ")
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 TheBloke/Mistral-7B-Instruct-v0.2-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-v0.2-AWQ"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "TheBloke/Mistral-7B-Instruct-v0.2-AWQ",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/TheBloke/Mistral-7B-Instruct-v0.2-AWQ

SGLang

How to use TheBloke/Mistral-7B-Instruct-v0.2-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-v0.2-AWQ" \
    --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": "TheBloke/Mistral-7B-Instruct-v0.2-AWQ",
		"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 "TheBloke/Mistral-7B-Instruct-v0.2-AWQ" \
        --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": "TheBloke/Mistral-7B-Instruct-v0.2-AWQ",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use TheBloke/Mistral-7B-Instruct-v0.2-AWQ with Docker Model Runner:
```
docker model run hf.co/TheBloke/Mistral-7B-Instruct-v0.2-AWQ
```

RAG issue | loading the model in RetrievalQASourceChain

by iammano - opened Jan 7, 2024

Discussion

iammano

Jan 7, 2024

•

edited Jan 7, 2024

Hi there,

I'm getting this error when I try to pass the model to the llm parameter in langchain's RetrievalQASourceChain parameter, Below is my code.

def __init__(self, **kwargs):
        """
        Initializes the QA bot with a Qdrant client, embeddings, and a language model.

        Parameters:
        - **kwargs: Additional keyword arguments for configuration.
        """
        
        self.client = QdrantClient(url=HOST_NAME,api_key=API_KEY)
        self.embedding = get_embedding()
        self.device = "cuda:0" 
        if torch.cuda.is_available():
            print("Inside GPU")
            
            self.llm = AutoModelForCausalLM.from_pretrained(
                                HF_MODEL,
                                low_cpu_mem_usage=True,
                                device_map=self.device
                            )
        else:
            self.llm = CTransformers(model=MODEL_PATH,
                                    model_type=MODEL_TYPE, 
                                    config=MODEL_PARAMETERS)


def answer(query):
qa = RetrievalQAWithSourcesChain.from_chain_type(
                                llm=self.llm,
                                retriever=retriever,
                                chain_type_kwargs={
                                    "prompt": my_prompt
                                },
                                device_map=self.device,
                                reduce_k_below_max_tokens=True,
                                return_source_documents=True)

These are methods of a class that I have shared partial code here. Thanks for your understanding.

Error Message:

Traceback (most recent call last):
  File "/home/manoranjan.n/doc_test/backend/main.py", line 68, in ask_model
    result = qabot.answer(data['question'])
  File "/home/manoranjan.n/doc_test/backend/qa_bot.py", line 227, in answer
    qa = RetrievalQAWithSourcesChain.from_chain_type(
  File "/home/manoranjan.n/.local/lib/python3.8/site-packages/langchain/chains/qa_with_sources/base.py", line 85, in from_chain_type
    combine_documents_chain = load_qa_with_sources_chain(
  File "/home/manoranjan.n/.local/lib/python3.8/site-packages/langchain/chains/qa_with_sources/loading.py", line 183, in load_qa_with_sources_chain
    return _func(llm, verbose=verbose, **kwargs)
  File "/home/manoranjan.n/.local/lib/python3.8/site-packages/langchain/chains/qa_with_sources/loading.py", line 62, in _load_stuff_chain
    llm_chain = LLMChain(llm=llm, prompt=prompt, verbose=verbose)
  File "/home/manoranjan.n/.local/lib/python3.8/site-packages/langchain_core/load/serializable.py", line 107, in __init__
    super().__init__(**kwargs)
  File "pydantic/main.py", line 341, in pydantic.main.BaseModel.__init__
pydantic.error_wrappers.ValidationError: 2 validation errors for LLMChain
llm
  instance of Runnable expected (type=type_error.arbitrary_type; expected_arbitrary_type=Runnable)
llm
  instance of Runnable expected (type=type_error.arbitrary_type; expected_arbitrary_type=Runnable)

Somekind of validation error, please help me on this.

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