Instructions to use TheBloke/CodeLlama-7B-GGML with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use TheBloke/CodeLlama-7B-GGML with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="TheBloke/CodeLlama-7B-GGML")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("TheBloke/CodeLlama-7B-GGML", dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use TheBloke/CodeLlama-7B-GGML with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "TheBloke/CodeLlama-7B-GGML" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "TheBloke/CodeLlama-7B-GGML", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/TheBloke/CodeLlama-7B-GGML
- SGLang
How to use TheBloke/CodeLlama-7B-GGML 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 "TheBloke/CodeLlama-7B-GGML" \ --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": "TheBloke/CodeLlama-7B-GGML", "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 "TheBloke/CodeLlama-7B-GGML" \ --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": "TheBloke/CodeLlama-7B-GGML", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use TheBloke/CodeLlama-7B-GGML with Docker Model Runner:
docker model run hf.co/TheBloke/CodeLlama-7B-GGML
Little to no output
#2
by webslug - opened
Hi I tried codellama-7b.ggmlv3.Q2_K.bin in the text generation web ui but I get little to no output on Instruct mode. Chat mode barely works. I've increased the threads.
Not sure why it's not working but the model seems incapable of generating code.
This is the base model so it's not been fine tuned I believe, so it won't necessarily be great at answering questions. Try one the -Instruct or -Python model with the prompt template which I just added to their READMEs:
[INST] Write code to solve the following coding problem that obeys the constraints and
passes the example test cases. Please wrap your code answer using ```:
{PROMPT}
[/INST]
Thank you very much, I will try that.