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).
136 lines
4.1 KiB
Plaintext
136 lines
4.1 KiB
Plaintext
---
|
|
title: Zen Pro
|
|
description: Professional-grade 8B model with instruct, thinking, and agent variants
|
|
---
|
|
|
|
# Zen Pro
|
|
|
|
Zen Pro is Zen LM's 8B professional model from the Zen MoDE family, designed for production workloads requiring strong instruction following, multi-step reasoning, and tool use. Three specialized variants cover general chat, extended reasoning, and agentic tool use. Runs on a single 16GB GPU.
|
|
|
|
## Specifications
|
|
|
|
| Property | Value |
|
|
|----------|-------|
|
|
| Parameters | 8B |
|
|
| Architecture | Zen MoDE (transformer, decoder-only) |
|
|
| Context Window | 32,768 tokens |
|
|
| Languages | English, Chinese, Japanese, Korean, French, German, Spanish, Italian, Portuguese, Russian |
|
|
| License | Apache 2.0 |
|
|
| Formats | SafeTensors (BF16), GGUF, MLX |
|
|
|
|
## Model Variants
|
|
|
|
| Variant | Best For |
|
|
|---------|----------|
|
|
| [zen-pro-instruct](https://huggingface.co/zenlm/zen-pro-instruct) | Chat, Q&A, summarization, drafting |
|
|
| [zen-pro-thinking](https://huggingface.co/zenlm/zen-pro-thinking) | Complex reasoning, math, analysis |
|
|
| [zen-pro-agent](https://huggingface.co/zenlm/zen-pro-agent) | Tool use, API calls, automation |
|
|
|
|
## Quick Start
|
|
|
|
### Instruct
|
|
|
|
```python
|
|
from transformers import AutoModelForCausalLM, AutoTokenizer
|
|
import torch
|
|
|
|
model = AutoModelForCausalLM.from_pretrained(
|
|
"zenlm/zen-pro-instruct",
|
|
torch_dtype=torch.bfloat16,
|
|
device_map="auto"
|
|
)
|
|
tokenizer = AutoTokenizer.from_pretrained("zenlm/zen-pro-instruct")
|
|
|
|
messages = [
|
|
{"role": "system", "content": "You are Zen Pro, a professional AI assistant."},
|
|
{"role": "user", "content": "Summarize the key differences between REST and GraphQL APIs."}
|
|
]
|
|
|
|
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=512, temperature=0.6)
|
|
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True))
|
|
```
|
|
|
|
### Thinking (extended reasoning)
|
|
|
|
```python
|
|
messages = [
|
|
{"role": "user", "content": "What are the market shares after 3 years if products start at 40%, 35%, 25% and grow at 10%, -5%, 20% annually?"}
|
|
]
|
|
|
|
text = tokenizer.apply_chat_template(
|
|
messages,
|
|
tokenize=False,
|
|
add_generation_prompt=True,
|
|
enable_thinking=True
|
|
)
|
|
inputs = tokenizer(text, return_tensors="pt").to(model.device)
|
|
outputs = model.generate(**inputs, max_new_tokens=2048, temperature=0.6)
|
|
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True))
|
|
```
|
|
|
|
### Agent (tool use)
|
|
|
|
```python
|
|
tools = [
|
|
{
|
|
"type": "function",
|
|
"function": {
|
|
"name": "search_web",
|
|
"description": "Search the web for current information",
|
|
"parameters": {
|
|
"type": "object",
|
|
"properties": {
|
|
"query": {"type": "string", "description": "Search query"}
|
|
},
|
|
"required": ["query"]
|
|
}
|
|
}
|
|
}
|
|
]
|
|
|
|
messages = [{"role": "user", "content": "What's the latest in quantum computing research?"}]
|
|
text = tokenizer.apply_chat_template(messages, tools=tools, tokenize=False, add_generation_prompt=True)
|
|
```
|
|
|
|
## Use Cases
|
|
|
|
- Production chat and Q&A APIs
|
|
- Multi-step reasoning and analysis (thinking variant)
|
|
- Automated workflows with tool integration (agent variant)
|
|
- Summarization, drafting, and content tasks
|
|
- Customer support and enterprise applications
|
|
|
|
## Formats
|
|
|
|
| Format | VRAM | Speed |
|
|
|--------|------|-------|
|
|
| BF16 (full) | 16 GB | Fast |
|
|
| GGUF Q8_0 | 10 GB | Fast |
|
|
| GGUF Q4_K_M | 6 GB | Moderate |
|
|
| MLX 4-bit | 6 GB (Apple Silicon) | Native Metal |
|
|
|
|
### vLLM (production)
|
|
|
|
```bash
|
|
vllm serve zenlm/zen-pro-instruct \
|
|
--dtype bfloat16 \
|
|
--max-model-len 32768 \
|
|
--tensor-parallel-size 1
|
|
```
|
|
|
|
### 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-pro", "messages": [{"role": "user", "content": "Explain ACID transactions."}]}'
|
|
```
|
|
|
|
## Get Started
|
|
|
|
- [HuggingFace](https://huggingface.co/zenlm/zen-pro-instruct)
|
|
- [GitHub](https://github.com/zenlm/zen-pro)
|