Zen5 Source Repos
Collection
Source (non-GGUF) Zen 5 safetensor repos. • 4 items • Updated
How to use zenlm/zen-5 with Transformers:
# Use a pipeline as a high-level helper
from transformers import pipeline
pipe = pipeline("text-generation", model="zenlm/zen-5") # Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("zenlm/zen-5", dtype="auto")How to use zenlm/zen-5 with vLLM:
# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "zenlm/zen-5"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
-H "Content-Type: application/json" \
--data '{
"model": "zenlm/zen-5",
"prompt": "Once upon a time,",
"max_tokens": 512,
"temperature": 0.5
}'docker model run hf.co/zenlm/zen-5
How to use zenlm/zen-5 with SGLang:
# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
--model-path "zenlm/zen-5" \
--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": "zenlm/zen-5",
"prompt": "Once upon a time,",
"max_tokens": 512,
"temperature": 0.5
}'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 "zenlm/zen-5" \
--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": "zenlm/zen-5",
"prompt": "Once upon a time,",
"max_tokens": 512,
"temperature": 0.5
}'How to use zenlm/zen-5 with Docker Model Runner:
docker model run hf.co/zenlm/zen-5
Parameters: TBA | Architecture: Zen MoDE (Mixture of Diverse Experts) | Context: 1M | Status: In training
Zen 5 — next-generation flagship. Currently in training.
Zen MoDE is our next-generation architecture: Mixture of Diverse Experts with sparse activation, extended context, and enhanced multi-step reasoning. First introduced with Zen 5.
Joint research between Hanzo AI (Techstars '17), Zoo Labs Foundation (501c3), and Lux Partners Limited.
All weights Apache 2.0. Download, run locally, fine-tune, deploy commercially.
HuggingFace · Chat · API · Docs
docker model run hf.co/zenlm/zen-5