Instructions to use TheBloke/Augmental-13B-GPTQ with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TheBloke/Augmental-13B-GPTQ with Transformers:

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

pipe = pipeline("text-generation", model="TheBloke/Augmental-13B-GPTQ")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("TheBloke/Augmental-13B-GPTQ")
model = AutoModelForCausalLM.from_pretrained("TheBloke/Augmental-13B-GPTQ", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use TheBloke/Augmental-13B-GPTQ with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "TheBloke/Augmental-13B-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/Augmental-13B-GPTQ",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/TheBloke/Augmental-13B-GPTQ

SGLang

How to use TheBloke/Augmental-13B-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/Augmental-13B-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/Augmental-13B-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/Augmental-13B-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/Augmental-13B-GPTQ",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use TheBloke/Augmental-13B-GPTQ with Docker Model Runner:
```
docker model run hf.co/TheBloke/Augmental-13B-GPTQ
```

Error with the CLI tool

by Dekriel - opened Oct 25, 2023

Discussion

Dekriel

Oct 25, 2023

I'm getting an error with running the command >huggingface-cli download TheBloke/Augmental-13B-GPTQ --local-dir Augmental-13B-GPTQ --local-dir-use-symlinks False

huggingface-cli: error: argument {env,login,whoami,logout,repo,lfs-enable-largefiles,lfs-multipart-upload,scan-cache,delete-cache}: invalid choice: 'download' (choose from 'env', 'login', 'whoami', 'logout', 'repo', 'lfs-enable-largefiles', 'lfs-multipart-upload', 'scan-cache', 'delete-cache')

TheBloke

Owner Oct 25, 2023

You need to update huggingface-hub to version 0.17 or later; latest is 0.18.0, which is what I'd recommend

Antho2422

Feb 14, 2024

I also get the same error with huggingface-hub on version 0.20.3

Antho2422

Feb 14, 2024

Actually it is solved. My huggingface-cli was not installed in the correct env. I updated the correct one and it works now.

GabrielFreeze-2

Mar 6, 2024

Had the same issue with huggingface-hub==0.21.3. Fixed it by re-installing with the -U flag in pip

pip install -U huggingface-hub

ang3l0

May 29, 2024

Hmm on Version: 0.23.2, tried pip install -U in my env, and running into same issue.

ypatra2

May 29, 2024

Hmm on Version: 0.23.2, tried pip install -U in my env, and running into same issue.

Same issue encountered

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