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

Libraries

How to use TheBloke/Mistral-7B-OpenOrca-GPTQ with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("TheBloke/Mistral-7B-OpenOrca-GPTQ")
model = AutoModelForCausalLM.from_pretrained("TheBloke/Mistral-7B-OpenOrca-GPTQ", device_map="auto")
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-OpenOrca-GPTQ with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "TheBloke/Mistral-7B-OpenOrca-GPTQ"
# 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-OpenOrca-GPTQ",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/TheBloke/Mistral-7B-OpenOrca-GPTQ

SGLang

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

Docker Model Runner
How to use TheBloke/Mistral-7B-OpenOrca-GPTQ with Docker Model Runner:
```
docker model run hf.co/TheBloke/Mistral-7B-OpenOrca-GPTQ
```

ValueError: If `eos_token_id` is defined, make sure that `pad_token_id` is defined.

by Ayenem - opened Oct 6, 2023

Discussion

Ayenem

Oct 6, 2023

•

edited Oct 7, 2023

Traceback (most recent call last):
  File ".../demo.py", line 168, in docker_pipeline
    llm_output = rag_chain(instruction)
                 ^^^^^^^^^^^^^^^^^^^^^^
  File ".../langchain/chains/base.py", line 306, in __call__
    raise e
  File ".../langchain/chains/base.py", line 300, in __call__
    self._call(inputs, run_manager=run_manager)
  File ".../langchain/chains/retrieval_qa/base.py", line 139, in _call
    answer = self.combine_documents_chain.run(
             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File ".../langchain/chains/base.py", line 506, in run
    return self(kwargs, callbacks=callbacks, tags=tags, metadata=metadata)[
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File ".../langchain/chains/base.py", line 306, in __call__
    raise e
  File ".../langchain/chains/base.py", line 300, in __call__
    self._call(inputs, run_manager=run_manager)
  File ".../langchain/chains/combine_documents/base.py", line 119, in _call
    output, extra_return_dict = self.combine_docs(
                                ^^^^^^^^^^^^^^^^^^
  File ".../langchain/chains/combine_documents/stuff.py", line 171, in combine_docs
    return self.llm_chain.predict(callbacks=callbacks, **inputs), {}
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File ".../langchain/chains/llm.py", line 257, in predict
    return self(kwargs, callbacks=callbacks)[self.output_key]
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File ".../langchain/chains/base.py", line 306, in __call__
    raise e
  File ".../langchain/chains/base.py", line 300, in __call__
    self._call(inputs, run_manager=run_manager)
  File ".../langchain/chains/llm.py", line 93, in _call
    response = self.generate([inputs], run_manager=run_manager)
               ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File ".../langchain/chains/llm.py", line 103, in generate
    return self.llm.generate_prompt(
           ^^^^^^^^^^^^^^^^^^^^^^^^^
  File ".../langchain/llms/base.py", line 498, in generate_prompt
    return self.generate(prompt_strings, stop=stop, callbacks=callbacks, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File ".../langchain/llms/base.py", line 647, in generate
    output = self._generate_helper(
             ^^^^^^^^^^^^^^^^^^^^^^
  File ".../langchain/llms/base.py", line 535, in _generate_helper
    raise e
  File ".../langchain/llms/base.py", line 522, in _generate_helper
    self._generate(
  File ".../langchain/llms/huggingface_pipeline.py", line 183, in _generate
    responses = self.pipeline(batch_prompts)
                ^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File ".../transformers/pipelines/text_generation.py", line 208, in __call__
    return super().__call__(text_inputs, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File ".../transformers/pipelines/base.py", line 1121, in __call__
    outputs = list(final_iterator)
              ^^^^^^^^^^^^^^^^^^^^
  File ".../transformers/pipelines/pt_utils.py", line 124, in __next__
    item = next(self.iterator)
           ^^^^^^^^^^^^^^^^^^^
  File ".../transformers/pipelines/pt_utils.py", line 125, in __next__
    processed = self.infer(item, **self.params)
                ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File ".../transformers/pipelines/base.py", line 1046, in forward
    model_outputs = self._forward(model_inputs, **forward_params)
                    ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File ".../transformers/pipelines/text_generation.py", line 271, in _forward
    generated_sequence = self.model.generate(input_ids=input_ids, attention_mask=attention_mask, **generate_kwargs)
                         ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File ".../torch/utils/_contextlib.py", line 115, in decorate_context
    return func(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^
  File ".../transformers/generation/utils.py", line 1652, in generate
    return self.sample(
           ^^^^^^^^^^^^
  File ".../transformers/generation/utils.py", line 2775, in sample
    raise ValueError("If `eos_token_id` is defined, make sure that `pad_token_id` is defined.")
ValueError: If `eos_token_id` is defined, make sure that `pad_token_id` is defined.

I looked up https://huggingface.co/TheBloke/Mistral-7B-OpenOrca-GPTQ/blob/main/tokenizer_config.json#L52 and it is indeed null. Is that what it's supposed to be? And if so, how can I deal with this error?

KiranMP

Dec 11, 2023

model.generate(**input_ids, pad_token_id=tokenizer.eos_token_id, ...) Did you tried replacing pad token with eos token? This should work.

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