Instructions to use RWKV/v5-Eagle-7B-HF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use RWKV/v5-Eagle-7B-HF with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="RWKV/v5-Eagle-7B-HF", trust_remote_code=True)# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("RWKV/v5-Eagle-7B-HF", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use RWKV/v5-Eagle-7B-HF with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "RWKV/v5-Eagle-7B-HF" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "RWKV/v5-Eagle-7B-HF", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/RWKV/v5-Eagle-7B-HF
- SGLang
How to use RWKV/v5-Eagle-7B-HF 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 "RWKV/v5-Eagle-7B-HF" \ --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": "RWKV/v5-Eagle-7B-HF", "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 "RWKV/v5-Eagle-7B-HF" \ --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": "RWKV/v5-Eagle-7B-HF", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use RWKV/v5-Eagle-7B-HF with Docker Model Runner:
docker model run hf.co/RWKV/v5-Eagle-7B-HF
Fix: encoder and decoder in tokenizer
#13 opened almost 2 years ago
by
JingweiZuo
Adding `safetensors` variant of this model
❤️ 1
#11 opened over 2 years ago
by
SFconvertbot
[AUTOMATED] Model Memory Requirements
#10 opened over 2 years ago
by
model-sizer-bot
Are decode and encode in the tokenizer reversed?
#9 opened over 2 years ago
by
pootow
Update config.json
#8 opened over 2 years ago
by
Muennighoff
Adding _bnb_4bit_dequantize_and_rescale in ` modeling_rwkv5.py ` based on the provided docmentations on github
#7 opened over 2 years ago
by
kaifahmad
Kernel getting crashed
1
#6 opened over 2 years ago
by
Arunmass
Is instruction or chat model coming?
#4 opened over 2 years ago
by
supercharge19
Adding `safetensors` variant of this model
#1 opened over 2 years ago
by
taufiqdp