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
```

Default eos_token_id=2 is incorrect, needs to be 11

by mike-ravkine - opened May 31, 2023

Discussion

mike-ravkine

May 31, 2023

•

edited May 31, 2023

This issue affects all the falcon repositories.

Default eos_token_id=2 is specified here: https://huggingface.co/TheBloke/falcon-40b-instruct-GPTQ/blob/main/configuration_RW.py#L41

Looking at https://huggingface.co/TheBloke/falcon-40b-instruct-GPTQ/raw/main/tokenizer.json, token=2 is >>INTRODUCTION<< and we're looking for token=11 <|endoftext|>

If we dont want to update the default (this is upstream code right?), the eos_token_id parameter can also be correctly passed at generation time:

model.generate(input_ids=tokens, max_new_tokens=512, do_sample=True, eos_token_id=11, temperature=0.8)

This solves the issue of the model output continuing right past <|endoftext|> tokens :D

TheBloke

Owner May 31, 2023

Oh interesting! I assume you've told them about it too?

If this is materially affecting inference and has been reported upstream then I'll change it.

Would you mind PRing the fix to this repo?

mike-ravkine changed discussion status to closed May 31, 2023

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