Instructions to use amd/AMD-Llama-135m-code with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use amd/AMD-Llama-135m-code with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="amd/AMD-Llama-135m-code")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("amd/AMD-Llama-135m-code") model = AutoModelForCausalLM.from_pretrained("amd/AMD-Llama-135m-code") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use amd/AMD-Llama-135m-code with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "amd/AMD-Llama-135m-code" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "amd/AMD-Llama-135m-code", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/amd/AMD-Llama-135m-code
- SGLang
How to use amd/AMD-Llama-135m-code 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 "amd/AMD-Llama-135m-code" \ --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": "amd/AMD-Llama-135m-code", "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 "amd/AMD-Llama-135m-code" \ --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": "amd/AMD-Llama-135m-code", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use amd/AMD-Llama-135m-code with Docker Model Runner:
docker model run hf.co/amd/AMD-Llama-135m-code
Code completion functionality
#1
by Smorty100 - opened
The Llama2 template does not include a code-completion or fill-in-the-middle syntax. In the instruction format, it also does not really generate anything useful, as it puts some equals signs on page and adds some vague python code.
What usecases would this small model have? It doesn't seem able to integrate into anything really.
Am I missing something here? Or am I maybe using the wrong template?