Instructions to use jinaai/falcon-40b-code-alpaca with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use jinaai/falcon-40b-code-alpaca with Transformers:

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

pipe = pipeline("text-generation", model="jinaai/falcon-40b-code-alpaca", trust_remote_code=True)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("jinaai/falcon-40b-code-alpaca", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use jinaai/falcon-40b-code-alpaca with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/jinaai/falcon-40b-code-alpaca

SGLang

How to use jinaai/falcon-40b-code-alpaca 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 "jinaai/falcon-40b-code-alpaca" \
    --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": "jinaai/falcon-40b-code-alpaca",
		"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 "jinaai/falcon-40b-code-alpaca" \
        --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": "jinaai/falcon-40b-code-alpaca",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use jinaai/falcon-40b-code-alpaca with Docker Model Runner:
```
docker model run hf.co/jinaai/falcon-40b-code-alpaca
```

Better coding dataset

by rombodawg - opened Jul 21, 2023

Discussion

rombodawg

Jul 21, 2023

If you need a bigger dataset than codealpaca thats formatted in very similar way i have one made and you are free to use it.
link bellow

https://huggingface.co/datasets/rombodawg/MegaCodeTraining112k/tree/main

bwang0911

Jul 22, 2023

@samsja @alaeddine-13 @sebaweis

samsja

Jul 22, 2023

you rock @rombodawg will try it out

rombodawg

Jul 22, 2023

•

edited Jul 22, 2023

Let me know if you train a model with my dataset please! Ive been waiting to try that type of model, i just dont have the recourses to train one myself

rombodawg

Aug 16, 2023

@bwang0911 @samsja If you guys are interested I have made a version 3 of my megacode dataset and this one is the most promising one yet. Feel free to use to to train your future models:

https://huggingface.co/datasets/rombodawg/LosslessMegaCodeTrainingV3_2.2m_Evol

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