Instructions to use Sakuna/LLaMaCoderAll with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Sakuna/LLaMaCoderAll with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Sakuna/LLaMaCoderAll")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("Sakuna/LLaMaCoderAll") model = AutoModelForCausalLM.from_pretrained("Sakuna/LLaMaCoderAll") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use Sakuna/LLaMaCoderAll with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Sakuna/LLaMaCoderAll" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Sakuna/LLaMaCoderAll", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Sakuna/LLaMaCoderAll
- SGLang
How to use Sakuna/LLaMaCoderAll 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 "Sakuna/LLaMaCoderAll" \ --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": "Sakuna/LLaMaCoderAll", "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 "Sakuna/LLaMaCoderAll" \ --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": "Sakuna/LLaMaCoderAll", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use Sakuna/LLaMaCoderAll with Docker Model Runner:
docker model run hf.co/Sakuna/LLaMaCoderAll
What is this model?
What model is this? Is this llama 2 13b? What data set was this trained on? Please include all coding datasets, What type of model is this (fp16, 8-bit)? Please at least answer this post, or at most update the model card with this and more information about the model
Hi, Updated the model card. Thanks for the comment.
If you have the recourses you should try training llama2-7b or even llama-2-13b on my coding dataset. Ive been waiting to see how well ai can code trained on my dataset but i dont have the hardware to train them myself
Link to my dataset:
https://huggingface.co/datasets/rombodawg/MegaCodeTraining112k