mirror of
https://github.com/zenlm/zen-docs.git
synced 2026-10-30 14:58:13 +00:00
zeekay
8ef8f3e801
Updated 8 existing stubs and added 4 new model pages: - zen-nano: 0.6B edge model specs, throughput table, benchmarks - zen-scribe: 4B writing model, multilingual, use cases - zen-omni: 30B hypermodal Thinker-Talker MoE, speech-to-speech - zen-vl: 4B/8B/30B VL family with function calling and agent variants - zen-embedding: MTEB #1 multilingual (70.58), MRL support - zen-coder: 4B/31B/480B MoE family, FIM, 358 languages - zen-designer: 235B VL MoE, document parsing, GUI interaction - zen-max: 1T+ MoE, 256K context, 200+ tool calls, heavy mode - zen-pro: 8B instruct/thinking/agent variants - zen-reranker: 8B dual-task, native 7680-dim for DSO - zen-translator: real-time translation pipeline with voice cloning - zen-guard: removed upstream model reference No upstream model names in any page (Zen MoDE branding throughout).
76 lines
2.6 KiB
Plaintext
76 lines
2.6 KiB
Plaintext
---
|
|
title: Zen Scribe
|
|
description: 4B professional content writing model for long-form generation and structured documents
|
|
---
|
|
|
|
# Zen Scribe
|
|
|
|
Zen Scribe is a 4B parameter language model from the Zen MoDE family, fine-tuned for writing tasks. It produces coherent, well-structured prose across extended contexts with consistent voice — suitable for blog posts, technical documentation, reports, creative writing, and automated content pipelines.
|
|
|
|
## Specifications
|
|
|
|
| Property | Value |
|
|
|----------|-------|
|
|
| Parameters | 4B |
|
|
| Architecture | Zen MoDE (transformer, decoder-only) |
|
|
| Context Window | 32,768 tokens |
|
|
| Languages | English, Chinese, Japanese, Korean, French, German, Spanish, Portuguese, Italian, Russian |
|
|
| License | Apache 2.0 |
|
|
| Formats | SafeTensors (BF16), GGUF, MLX |
|
|
|
|
## Quick Start
|
|
|
|
```python
|
|
from transformers import AutoModelForCausalLM, AutoTokenizer
|
|
import torch
|
|
|
|
model = AutoModelForCausalLM.from_pretrained(
|
|
"zenlm/zen-scribe",
|
|
torch_dtype=torch.bfloat16,
|
|
device_map="auto"
|
|
)
|
|
tokenizer = AutoTokenizer.from_pretrained("zenlm/zen-scribe")
|
|
|
|
messages = [
|
|
{"role": "system", "content": "You are a technical writer. Write clearly and concisely."},
|
|
{"role": "user", "content": "Write a 500-word introduction to Kubernetes networking."}
|
|
]
|
|
|
|
text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
|
|
inputs = tokenizer(text, return_tensors="pt").to(model.device)
|
|
outputs = model.generate(**inputs, max_new_tokens=600, temperature=0.7, top_p=0.9, repetition_penalty=1.1)
|
|
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True))
|
|
```
|
|
|
|
## Use Cases
|
|
|
|
- **Technical documentation** — API references, guides, READMEs
|
|
- **Blog and editorial** — Long-form articles, opinion pieces, explainers
|
|
- **Business writing** — Reports, proposals, executive summaries
|
|
- **Creative writing** — Fiction, screenplays, narrative content
|
|
- **Structured output** — Templated content, form letters, product descriptions
|
|
|
|
## Formats
|
|
|
|
- **SafeTensors** (BF16) — native PyTorch/Transformers
|
|
- **MLX** — `mlx_lm.generate --model zenlm/zen-scribe --max-tokens 500`
|
|
- **GGUF** — `llama-cli -m zen-scribe-q4_k_m.gguf -n 512`
|
|
|
|
### Hanzo API
|
|
|
|
```bash
|
|
curl https://api.hanzo.ai/v1/chat/completions \
|
|
-H "Authorization: Bearer $HANZO_API_KEY" \
|
|
-H "Content-Type: application/json" \
|
|
-d '{
|
|
"model": "zen-scribe",
|
|
"messages": [{"role": "user", "content": "Write a product announcement for a new AI API:"}],
|
|
"max_tokens": 400
|
|
}'
|
|
```
|
|
|
|
## Get Started
|
|
|
|
- [HuggingFace](https://huggingface.co/zenlm/zen-scribe)
|
|
- [GitHub](https://github.com/zenlm/zen-scribe)
|