Instructions to use replit/replit-code-v1-3b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use replit/replit-code-v1-3b with Transformers:

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

pipe = pipeline("text-generation", model="replit/replit-code-v1-3b", trust_remote_code=True)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("replit/replit-code-v1-3b", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("replit/replit-code-v1-3b", trust_remote_code=True)

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use replit/replit-code-v1-3b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "replit/replit-code-v1-3b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "replit/replit-code-v1-3b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/replit/replit-code-v1-3b

SGLang

How to use replit/replit-code-v1-3b 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 "replit/replit-code-v1-3b" \
    --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": "replit/replit-code-v1-3b",
		"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 "replit/replit-code-v1-3b" \
        --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": "replit/replit-code-v1-3b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use replit/replit-code-v1-3b with Docker Model Runner:
```
docker model run hf.co/replit/replit-code-v1-3b
```

Fine-tuned model

by lentan - opened May 3, 2023

Discussion

lentan

May 3, 2023

Will the fine-tuned model be released as well?

pirroh

Replit org May 3, 2023

Currently not on our roadmap, but happy to provide guidance on how to fine-tune this base model!
We can't wait to see what the community will do with it :)

lentan

May 8, 2023

•

edited May 8, 2023

Pretty new to all of this but I'm working on fine-tuning it with LLaMA-Adapter.

I've finished adding the adapter prompts but I'm having trouble figuring out what loss function was used in replit-code-v1-3b finetuning since the output only returns logits.

I understand it was probably finetuned using Composer but there are lots of options in there, do you think you could share the options used for finetuning?

brianjking

May 8, 2023

@pirroh What was fine tuned in your fine tuned version?

Will you be providing instructions and/or colab notebook for fine tuning?

Thanks!

pirroh

Replit org Jun 5, 2023

Hey @lentan and @brianjking , thanks for your patience!

We just released a detailed guide on how to fine-tune replit-code-v1-3b -- check the README file on our ReplitLM GitHub repo.
Let us know in case of any issues. Otherwise, happy hacking and post here your results and derivative models 🚀

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