Instructions to use TheBloke/stable-code-3b-GPTQ with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TheBloke/stable-code-3b-GPTQ with Transformers:

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

pipe = pipeline("text-generation", model="TheBloke/stable-code-3b-GPTQ", trust_remote_code=True)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("TheBloke/stable-code-3b-GPTQ", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use TheBloke/stable-code-3b-GPTQ with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "TheBloke/stable-code-3b-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/stable-code-3b-GPTQ",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/TheBloke/stable-code-3b-GPTQ

SGLang

How to use TheBloke/stable-code-3b-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/stable-code-3b-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/stable-code-3b-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/stable-code-3b-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/stable-code-3b-GPTQ",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use TheBloke/stable-code-3b-GPTQ with Docker Model Runner:
```
docker model run hf.co/TheBloke/stable-code-3b-GPTQ
```

issue loading

by baelof - opened Apr 8, 2024

Discussion

baelof

Apr 8, 2024

10:54:10-928608 INFO Loading "TheBloke_stable-code-3b-GPTQ"
!! Warning, unknown architecture: StableLMEpochForCausalLM
!! Loading as LlamaForCausalLM
10:54:10-931120 ERROR Failed to load the model.
Traceback (most recent call last):
File "D:\ai\installs\text-generation-webui\modules\ui_model_menu.py", line 245, in load_model_wrapper
shared.model, shared.tokenizer = load_model(selected_model, loader)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\ai\installs\text-generation-webui\modules\models.py", line 87, in load_model
output = load_func_maploader
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\ai\installs\text-generation-webui\modules\models.py", line 357, in ExLlamav2_loader
model, tokenizer = Exllamav2Model.from_pretrained(model_name)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\ai\installs\text-generation-webui\modules\exllamav2.py", line 45, in from_pretrained
config.prepare()
File "D:\ai\installs\text-generation-webui\installer_files\env\Lib\site-packages\exllamav2\config.py", line 164, in prepare
self.norm_eps = read(read_config, float, self.arch.norm_eps_key)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\ai\installs\text-generation-webui\installer_files\env\Lib\site-packages\exllamav2\config.py", line 41, in read
raise ValueError(f"Missing any of the following keys: {keys}")
ValueError: Missing any of the following keys: ['rms_norm_eps']

YaTharThShaRma999

Apr 8, 2024

@baelof i believe only transformers(maybe auto-gptq?) supports this model currently. Use llama.cpp(still slower then exllamav2) and the gguf variant if you want faster inference then transformers

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