Instructions to use QuixiAI/samantha-falcon-7b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use QuixiAI/samantha-falcon-7b with Transformers:

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

pipe = pipeline("text-generation", model="QuixiAI/samantha-falcon-7b", trust_remote_code=True)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("QuixiAI/samantha-falcon-7b", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use QuixiAI/samantha-falcon-7b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "QuixiAI/samantha-falcon-7b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "QuixiAI/samantha-falcon-7b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/QuixiAI/samantha-falcon-7b

SGLang

How to use QuixiAI/samantha-falcon-7b 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 "QuixiAI/samantha-falcon-7b" \
    --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": "QuixiAI/samantha-falcon-7b",
		"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 "QuixiAI/samantha-falcon-7b" \
        --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": "QuixiAI/samantha-falcon-7b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use QuixiAI/samantha-falcon-7b with Docker Model Runner:
```
docker model run hf.co/QuixiAI/samantha-falcon-7b
```

How did you manage to get Axolotl to work?

by ashercn97 - opened Jul 9, 2023

Discussion

ashercn97

Jul 9, 2023

I saw the conversation that said you trained this model with Axolotl, but I cant figure out how to get axolotl to work. I am trying to do it in google colab because I do not have enough memory on my personal computer to do it locally. Do you think that could be the problem? I followed the instructions on the Axolotl repo (I think) but I cannot tell what I am doing wrong. So, I have a few questions for you:

Did you train the model on your computer or in the cloud/on google colab
What commands did you use to get it to work?
Could you provide any insight into using Axolotl?

ashercn97

Jul 9, 2023

Follow up:

For some reason, I can only get it to work with open-llama-3b and not w falcon like you did. Any tips?

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