Instructions to use zenlm/zen-5-coder with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use zenlm/zen-5-coder with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="zenlm/zen-5-coder")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("zenlm/zen-5-coder", dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use zenlm/zen-5-coder with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "zenlm/zen-5-coder" # 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-coder", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/zenlm/zen-5-coder
- SGLang
How to use zenlm/zen-5-coder 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 "zenlm/zen-5-coder" \ --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-coder", "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 "zenlm/zen-5-coder" \ --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-coder", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use zenlm/zen-5-coder with Docker Model Runner:
docker model run hf.co/zenlm/zen-5-coder
feat: initial release placeholder 2025-07-01
Browse files
README.md
ADDED
|
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
language:
|
| 4 |
+
- en
|
| 5 |
+
tags:
|
| 6 |
+
- zen
|
| 7 |
+
- zenlm
|
| 8 |
+
- hanzo-ai
|
| 9 |
+
- zen-5
|
| 10 |
+
- coming-soon
|
| 11 |
+
pipeline_tag: text-generation
|
| 12 |
+
library_name: transformers
|
| 13 |
+
---
|
| 14 |
+
|
| 15 |
+
# Zen 5 Coder
|
| 16 |
+
|
| 17 |
+
> **Parameters**: TBA | **Context**: 256K | **Status**: In training — expected 2025-07-01
|
| 18 |
+
|
| 19 |
+
Zen 5 Coder — next-gen code specialist. In training. Expected Q3 2025.
|
| 20 |
+
|
| 21 |
+
Zen 5 builds on Zen MoDE with improved sparse routing, 1M+ context, and enhanced reasoning through extended chain-of-thought training.
|
| 22 |
+
|
| 23 |
+
[Subscribe for updates → zenlm.org](https://zenlm.org)
|
| 24 |
+
|
| 25 |
+
---
|
| 26 |
+
## The Zen LM Family
|
| 27 |
+
|
| 28 |
+
Joint research collaboration:
|
| 29 |
+
- **Hanzo AI** (Techstars '17) — AI infrastructure, API gateway, inference optimization
|
| 30 |
+
- **Zoo Labs Foundation** (501c3) — Open AI research, ZIPs governance, decentralized training
|
| 31 |
+
- **Lux Partners Limited** — Compute coordination and settlement layer
|
| 32 |
+
|
| 33 |
+
All weights Apache 2.0. Download, run locally, fine-tune, deploy commercially.
|
| 34 |
+
|
| 35 |
+
[HuggingFace](https://huggingface.co/zenlm) · [Chat free](https://hanzo.chat) · [API](https://api.hanzo.ai) · [Docs](https://zenlm.org)
|