Instructions to use mxz/llama3-8b-ppo with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use mxz/llama3-8b-ppo with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="mxz/llama3-8b-ppo")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("mxz/llama3-8b-ppo") model = AutoModelForCausalLM.from_pretrained("mxz/llama3-8b-ppo") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use mxz/llama3-8b-ppo with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "mxz/llama3-8b-ppo" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "mxz/llama3-8b-ppo", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/mxz/llama3-8b-ppo
- SGLang
How to use mxz/llama3-8b-ppo 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 "mxz/llama3-8b-ppo" \ --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": "mxz/llama3-8b-ppo", "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 "mxz/llama3-8b-ppo" \ --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": "mxz/llama3-8b-ppo", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use mxz/llama3-8b-ppo with Docker Model Runner:
docker model run hf.co/mxz/llama3-8b-ppo
[WIP] Upload folder using huggingface_hub (multi-commit 43b96fecf7b78709127f50d39b748c0d6ef04f16f787edd63dc9df6bfc8dbfec)
#1
by mxz - opened
Upload folder using huggingface_hub
Multi commit ID: 43b96fecf7b78709127f50d39b748c0d6ef04f16f787edd63dc9df6bfc8dbfec
Scheduled commits:
- Upload 1 file(s) totalling 5.0G (da017f0f911579069bc803bcfd4ded1c801b7ed834c28b1e1f40d1db5bdaf965)
- Upload 1 file(s) totalling 4.9G (7062e283639ba0907949d37221b55d413c788c555df031259fef379f765fdec8)
- Upload 1 file(s) totalling 4.9G (dab9a0e110390b244dc17f9dbc6be9f98adcf33ab1a40aca6718e04b9189dd94)
- Upload 1 file(s) totalling 2.6G (0288da582b9f03a32ee0f53932edb91cda650d52966134a996d77cd6a2cb68ce)
- Upload 6 file(s) totalling 9.2M (f69b71e6c260b9eceee69dc47b8b419648f2e6de8c7ebc60c05b03e3b58c3e29)
This is a PR opened using the huggingface_hub library in the context of a multi-commit. PR can be commented as a usual PR. However, please be aware that manually updating the PR description, changing the PR status, or pushing new commits, is not recommended as it might corrupt the commit process. Learn more about multi-commits in this guide.
mxz changed pull request status to open
mxz changed pull request status to merged