Instructions to use MetaIX/GPT4-X-Alpasta-30b-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use MetaIX/GPT4-X-Alpasta-30b-4bit with Transformers:

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

pipe = pipeline("text-generation", model="MetaIX/GPT4-X-Alpasta-30b-4bit")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("MetaIX/GPT4-X-Alpasta-30b-4bit")
model = AutoModelForCausalLM.from_pretrained("MetaIX/GPT4-X-Alpasta-30b-4bit")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use MetaIX/GPT4-X-Alpasta-30b-4bit with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "MetaIX/GPT4-X-Alpasta-30b-4bit"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "MetaIX/GPT4-X-Alpasta-30b-4bit",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/MetaIX/GPT4-X-Alpasta-30b-4bit

SGLang

How to use MetaIX/GPT4-X-Alpasta-30b-4bit 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 "MetaIX/GPT4-X-Alpasta-30b-4bit" \
    --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": "MetaIX/GPT4-X-Alpasta-30b-4bit",
		"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 "MetaIX/GPT4-X-Alpasta-30b-4bit" \
        --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": "MetaIX/GPT4-X-Alpasta-30b-4bit",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use MetaIX/GPT4-X-Alpasta-30b-4bit with Docker Model Runner:
```
docker model run hf.co/MetaIX/GPT4-X-Alpasta-30b-4bit
```

Error when running generate in text generation ui

by droidriz - opened May 19, 2023

Discussion

droidriz

May 19, 2023

hi i am getting "AttributeError: 'LlamaForCausalLM' object has no attribute 'generate_with_streaming'" error with following run

python server.py --model MetaIX_GPT4-X-Alpasta-30b-4bit --model_type llama --wbits 4 --groupsize 128 --auto-devices
INFO:Loading MetaIX_GPT4-X-Alpasta-30b-4bit...
INFO:Found the following quantized model: models/MetaIX_GPT4-X-Alpasta-30b-4bit/gpt4-x-alpasta-30b-128g-4bit.safetensors
INFO:Loaded the model in 29.45 seconds.

droidriz

May 19, 2023

--no-stream gives this error
raise ValueError(
ValueError: The following model_kwargs are not used by the model: ['context', 'token_count'] (note: typos in the generate arguments will also show up in this list)

Limbicnation

Jun 14, 2023

Hi I am getting the same error when trying to run the model with oobabooga webui

ValueError: The following `model_kwargs` are not used by the model: ['context', 'token_count'] (note: typos in the generate arguments will also show up in this list)
Output generated in 0.01 seconds (0.00 tokens/s, 0 tokens, context 36, seed 16471360)```

brunokreiner

Jun 15, 2023

Same error for me with the MetaIX_OpenAssistant-Llama-30b-4bit model

brunokreiner

Jun 15, 2023

Ok, so for the other model I'm using I got it to work again. I downgraded the transformers_version in "config.json" to "4.28.0.dev0" based on another working model. Then i got the error that not all tensors are on the same device, so i disabled autodevice, cpu and disk settings in textgeneration webui. Just a quick fix.

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