Instructions to use TheBlokeAI/Mixtral-tiny-GPTQ with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TheBlokeAI/Mixtral-tiny-GPTQ with Transformers:

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

pipe = pipeline("text-generation", model="TheBlokeAI/Mixtral-tiny-GPTQ")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("TheBlokeAI/Mixtral-tiny-GPTQ")
model = AutoModelForCausalLM.from_pretrained("TheBlokeAI/Mixtral-tiny-GPTQ")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use TheBlokeAI/Mixtral-tiny-GPTQ with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "TheBlokeAI/Mixtral-tiny-GPTQ"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "TheBlokeAI/Mixtral-tiny-GPTQ",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/TheBlokeAI/Mixtral-tiny-GPTQ

SGLang

How to use TheBlokeAI/Mixtral-tiny-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 "TheBlokeAI/Mixtral-tiny-GPTQ" \
    --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": "TheBlokeAI/Mixtral-tiny-GPTQ",
		"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 "TheBlokeAI/Mixtral-tiny-GPTQ" \
        --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": "TheBlokeAI/Mixtral-tiny-GPTQ",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use TheBlokeAI/Mixtral-tiny-GPTQ with Docker Model Runner:
```
docker model run hf.co/TheBlokeAI/Mixtral-tiny-GPTQ
```

Seems like the GPTQ versions are broken

by NePe - opened Dec 12, 2023

Discussion

NePe

Dec 12, 2023

•

edited Dec 12, 2023

for the bigger models i get:
RuntimeError: cannot reshape tensor of 0 elements into shape [-1, 1, 0] because the unspecified dimension size -1 can be any value and is ambiguous in self.gate...

for this test one i get:

...
 File "/home/nepe/.local/lib/python3.10/site-packages/transformers/models/mixtral/modeling_mixtral.py", line 708, in forward
    router_logits = self.gate(hidden_states)
  File "/home/nepe/.local/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1518, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
  File "/home/nepe/.local/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1527, in _call_impl
    return forward_call(*args, **kwargs)
  File "/home/nepe/.local/lib/python3.10/site-packages/accelerate/hooks.py", line 165, in new_forward
    output = module._old_forward(*args, **kwargs)
  File "/home/nepe/.local/lib/python3.10/site-packages/auto_gptq/nn_modules/qlinear/qlinear_cuda.py", line 227, in forward
    zeros = zeros.reshape(self.scales.shape)
RuntimeError: shape '[8, 8]' is invalid for input of size 0

The non GPTQ version of the test model works perfectly.

TheBloke

TheBlokeAI org Dec 12, 2023

Yeah, see the READMEs of the proper GPTQs for how to load them - you still need an AutoGPTQ PR at the moment

NePe

Dec 12, 2023

I tried both the old and the fix branches, same error. I even tried to quantize this model, same error.

NePe

Dec 13, 2023

As far as i understand there's still some more things to do.
Based on this:
https://github.com/PanQiWei/AutoGPTQ/pull/480
Have to apply this:
https://github.com/huggingface/transformers/pull/27956
And maybe this one too:
https://github.com/huggingface/optimum/pull/1585

NePe

Dec 13, 2023

My mistake, tried it with AutoModelForCausalLM.from_pretrained instead of AutoGPTQForCausalLM.from_quantized

NePe changed discussion status to closed Dec 13, 2023

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