Instructions to use OpenAssistant/falcon-40b-sft-mix-1226 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use OpenAssistant/falcon-40b-sft-mix-1226 with Transformers:

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

pipe = pipeline("text-generation", model="OpenAssistant/falcon-40b-sft-mix-1226", trust_remote_code=True)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("OpenAssistant/falcon-40b-sft-mix-1226", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use OpenAssistant/falcon-40b-sft-mix-1226 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "OpenAssistant/falcon-40b-sft-mix-1226"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "OpenAssistant/falcon-40b-sft-mix-1226",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/OpenAssistant/falcon-40b-sft-mix-1226

SGLang

How to use OpenAssistant/falcon-40b-sft-mix-1226 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 "OpenAssistant/falcon-40b-sft-mix-1226" \
    --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": "OpenAssistant/falcon-40b-sft-mix-1226",
		"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 "OpenAssistant/falcon-40b-sft-mix-1226" \
        --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": "OpenAssistant/falcon-40b-sft-mix-1226",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use OpenAssistant/falcon-40b-sft-mix-1226 with Docker Model Runner:
```
docker model run hf.co/OpenAssistant/falcon-40b-sft-mix-1226
```

How to use few-shot learning correctly?

by 0kopr - opened Jul 3, 2023

Discussion

0kopr

Jul 3, 2023

•

edited Jul 3, 2023

What is the most correct way to do few-shot learning in the prompting of this model.

Do I have to use a special token for it?

ThatOneShortGuy

Jul 15, 2023

I don't think there is an official method. I make use of the <|system|>, <|prefix_begin|>, and <|endoftext|> tokens. I haven't tried few shot learning frequently because it doesn't seem super effective for me.
One think worth trying if you were wanting to answer the question in either "yes" or "no":

<|system|>Answer the questions with "yes" or "no"<|endoftext|>
<|prompter|>Is the sky blue?<|endoftext|>
<|assistant|>yes<|endoftext|>
<|prompter|>Is it ok to mock people?<|endoftext|>
<|assistant|>no<|endoftext|>
<|prompter|>

and then you ask your question followed by an <|endoftext|><|assistant|>.

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