Instructions to use pfnet/plamo-13b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use pfnet/plamo-13b with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="pfnet/plamo-13b", trust_remote_code=True)# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("pfnet/plamo-13b", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use pfnet/plamo-13b with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "pfnet/plamo-13b" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "pfnet/plamo-13b", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/pfnet/plamo-13b
- SGLang
How to use pfnet/plamo-13b 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 "pfnet/plamo-13b" \ --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": "pfnet/plamo-13b", "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 "pfnet/plamo-13b" \ --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": "pfnet/plamo-13b", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use pfnet/plamo-13b with Docker Model Runner:
docker model run hf.co/pfnet/plamo-13b
[feature request] Open LLM Leaderboardにはuse_remote_codeを使用しない
#3
by ke99L - opened
https://www.preferred.jp/ja/news/pr20230928/
モデルアーキテクチャの変更はないみたい、なぜuse_remote_codeを使用だろう??
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard
-> Submit here!
モデルにuse_remote_code=Trueが必要な場合、Open LLM Leaderboardはまだこのオプションをサポートしていません
revision branchやsafetensorsおすすめ
ELYZA 7b
mistral 7b
なとのもリストで評価できる
Thank you for your interest!
As we have outlined in our tech blog, the model architecture and tokenizer have been updated compared to the original transformers' implementation. Therefore, use_remote_code is required.
dhigurashi changed discussion status to closed