Instructions to use TheBloke/falcon-40b-instruct-GPTQ with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TheBloke/falcon-40b-instruct-GPTQ with Transformers:

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

pipe = pipeline("text-generation", model="TheBloke/falcon-40b-instruct-GPTQ", trust_remote_code=True)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("TheBloke/falcon-40b-instruct-GPTQ", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use TheBloke/falcon-40b-instruct-GPTQ with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "TheBloke/falcon-40b-instruct-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/falcon-40b-instruct-GPTQ",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/TheBloke/falcon-40b-instruct-GPTQ

SGLang

How to use TheBloke/falcon-40b-instruct-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/falcon-40b-instruct-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/falcon-40b-instruct-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/falcon-40b-instruct-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/falcon-40b-instruct-GPTQ",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use TheBloke/falcon-40b-instruct-GPTQ with Docker Model Runner:
```
docker model run hf.co/TheBloke/falcon-40b-instruct-GPTQ
```

can you upload a falcon-40b-GPTQ?

#18

by Gian-hf - opened Jun 22, 2023

Discussion

Gian-hf

Jun 22, 2023

Hi there,

can you please update a GPTQ version of the falcon-40b (the vanilla pretrained version, not the instruct)?

I would really appreciated and would really democratized the use of the pretrained model

Thank yoU!

TheBloke

Owner Jun 23, 2023

OK. It'll be really slow, but sure it's a good idea. I'll do GGML as well.

Gian-hf

Jun 24, 2023

Thank you so much. To give you the full picture I will be using the weights you will produce with this repo https://github.com/rmihaylov/falcontune that allows fine tuning the 40B on a single 40G-A100 on colab (crazy) and the generation it’s not even that slow with that script.

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