Instructions to use TheBloke/StableBeluga2-70B-GPTQ with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TheBloke/StableBeluga2-70B-GPTQ with Transformers:

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

pipe = pipeline("text-generation", model="TheBloke/StableBeluga2-70B-GPTQ")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("TheBloke/StableBeluga2-70B-GPTQ")
model = AutoModelForCausalLM.from_pretrained("TheBloke/StableBeluga2-70B-GPTQ", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use TheBloke/StableBeluga2-70B-GPTQ with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "TheBloke/StableBeluga2-70B-GPTQ"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "TheBloke/StableBeluga2-70B-GPTQ",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/TheBloke/StableBeluga2-70B-GPTQ

SGLang

How to use TheBloke/StableBeluga2-70B-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/StableBeluga2-70B-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": "TheBloke/StableBeluga2-70B-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 "TheBloke/StableBeluga2-70B-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": "TheBloke/StableBeluga2-70B-GPTQ",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use TheBloke/StableBeluga2-70B-GPTQ with Docker Model Runner:
```
docker model run hf.co/TheBloke/StableBeluga2-70B-GPTQ
```

Is this model TGI compatible?

#14

by MrAiran - opened Jul 31, 2023

Discussion

MrAiran

Jul 31, 2023

Whenever I try to load it in TGI I end up with this error, llama2 managed to load without problems
https://github.com/huggingface/text-generation-inference

text-generation-inference    |   File "/opt/conda/lib/python3.9/site-packages/text_generation_server/utils/weights.py", line 129, in <listcomp>
text-generation-inference    |     w = [self.get_tensor(f"{p}.g_idx") for p in prefixes]
text-generation-inference    |   File "/opt/conda/lib/python3.9/site-packages/text_generation_server/utils/weights.py", line 66, in get_tensor
text-generation-inference    |     filename, tensor_name = self.get_filename(tensor_name)
text-generation-inference    |   File "/opt/conda/lib/python3.9/site-packages/text_generation_server/utils/weights.py", line 53, in get_filename
text-generation-inference    |     raise RuntimeError(f"weight {tensor_name} does not exist")
text-generation-inference    | RuntimeError: weight model.layers.0.self_attn.q_proj.g_idx does not exist
text-generation-inference    |

MrAiran changed discussion status to closed Jul 31, 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