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

Libraries

How to use TheBloke/starchat-beta-GPTQ with Transformers:

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

pipe = pipeline("text-generation", model="TheBloke/starchat-beta-GPTQ")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("TheBloke/starchat-beta-GPTQ")
model = AutoModelForCausalLM.from_pretrained("TheBloke/starchat-beta-GPTQ", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use TheBloke/starchat-beta-GPTQ with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/TheBloke/starchat-beta-GPTQ

SGLang

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

Docker Model Runner
How to use TheBloke/starchat-beta-GPTQ with Docker Model Runner:
```
docker model run hf.co/TheBloke/starchat-beta-GPTQ
```

gptq_model-4bit--1g.safetensors does not contain metadata.

by kenM1 - opened Jun 14, 2023

Discussion

kenM1

Jun 14, 2023

Does anyone know how do i fix this issue?
Im getting:
2023-06-14 12:21:02 WARNING:The safetensors archive passed at models\TheBloke_starchat-beta-GPTQ\gptq_model-4bit--1g.safetensors does not contain metadata. Make sure to save your model with the save_pretrained method. Defaulting to 'pt' metadata.
2023-06-14 12:21:07 WARNING:GPTBigCodeGPTQForCausalLM hasn't fused attention module yet, will skip inject fused attention.
2023-06-14 12:21:07 WARNING:GPTBigCodeGPTQForCausalLM hasn't fused mlp module yet, will skip inject fused mlp.
When i try to load the model i get:

Traceback (most recent call last): File “C:\Users\me\text-generation-webui\server.py”, line 70, in load_model_wrapper shared.model, shared.tokenizer = load_model(shared.model_name) File “C:\Users\me\text-generation-webui\modules\models.py”, line 94, in load_model output = load_func(model_name) File “C:\Users\me\text-generation-webui\modules\models.py”, line 296, in AutoGPTQ_loader return modules.AutoGPTQ_loader.load_quantized(model_name) File “C:\Users\me\text-generation-webui\modules\AutoGPTQ_loader.py”, line 60, in load_quantized model.embed_tokens = model.model.model.embed_tokens File “C:\Users\me\miniconda3\envs\textgen\lib\site-packages\torch\nn\modules\module.py”, line 1614, in getattr raise AttributeError(“‘{}’ object has no attribute ‘{}’”.format( AttributeError: ‘GPTBigCodeForCausalLM’ object has no attribute ‘model’

Any help would be appreciated.

TheBloke

Owner Jun 14, 2023

This is a new bug in text-generation-webui

Until a proper fix is introduced, please follow the instructions at the end of this issue thread: https://github.com/oobabooga/text-generation-webui/issues/2655#issuecomment-1590895961

kenM1

Jun 14, 2023

This is a new bug in text-generation-webui

Until a proper fix is introduced, please follow the instructions at the end of this issue thread: https://github.com/oobabooga/text-generation-webui/issues/2655#issuecomment-1590895961

Successfully loaded TheBloke_starchat-beta-GPTQ

Here's a easy guide for anyone looking for a way to find file name: AutoGPTQ_loader.py
My was located at: C:\Users\me\text-generation-webui\modules
this line is located at the bottom of the file:

# These lines fix the multimodal extension when used with AutoGPTQ
# if not hasattr(model, 'dtype'):
#     model.dtype = model.model.dtype

# if not hasattr(model, 'embed_tokens'):
#     model.embed_tokens = model.model.model.embed_tokens

# if not hasattr(model.model, 'embed_tokens'):
#     model.model.embed_tokens = model.model.model.embed_tokens

after its been edited i simply loaded the model and:

Successfully loaded TheBloke_starchat-beta-GPTQ

TheBloke

Owner Jun 16, 2023

Thanks for the guide, kenM1.

Future users: note that the bug in text-generation-webui has now been fixed, so all that is required to get it to working now is to update to the latest version of text-generation-webui

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