LLAMA3 Finetune By Alphacode
Collection
2 items • Updated
How to use from
SGLangUse 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 "Alphacode-AI/Alphallama3-8B" \
--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": "Alphacode-AI/Alphallama3-8B",
"prompt": "Once upon a time,",
"max_tokens": 512,
"temperature": 0.5
}'Quick Links
Configuration Parsing Warning:Config file tokenizer_config.json cannot be fetched (too big)
This model is a version of Meta-Llama-3-8B that has been fine-tuned with Our In House CustomData.
Train Spec : We utilized an A100x4 * 1 for training our model with DeepSpeed / HuggingFace TRL Trainer / HuggingFace Accelerate
- Downloads last month
- 14
Install from pip and serve model
# Install SGLang from pip: pip install sglang# Start the SGLang server: python3 -m sglang.launch_server \ --model-path "Alphacode-AI/Alphallama3-8B" \ --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": "Alphacode-AI/Alphallama3-8B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'