fredrezones55/ Jan-v3

35 Downloads Updated 3 weeks ago

Jan-v3 is a compact 4B-parameter model that leverages distillation from a larger teacher to maintain strong general performance and broad applicability while avoiding typical capacity limitations.

tools

ollama run fredrezones55/Jan-v3

curl http://localhost:11434/api/chat \
  -d '{
    "model": "fredrezones55/Jan-v3",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='fredrezones55/Jan-v3',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'fredrezones55/Jan-v3',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Applications

Claude Code

Claude Code ollama launch claude --model fredrezones55/Jan-v3

Codex

Codex ollama launch codex --model fredrezones55/Jan-v3

OpenCode

OpenCode ollama launch opencode --model fredrezones55/Jan-v3

OpenClaw

OpenClaw ollama launch openclaw --model fredrezones55/Jan-v3

Models

Name

4 models

Size

Context

Input

Jan-v3:latest

4.7GB · 256K context window · Text · 3 weeks ago

Jan-v3:latest

4.7GB

256K

Text

Jan-v3:Q4_K_M

2.7GB · 256K context window · Text · 3 weeks ago

Jan-v3:Q4_K_M

2.7GB

256K

Text

Jan-v3:Q5_K_M

3.2GB · 256K context window · Text · 3 weeks ago

Jan-v3:Q5_K_M

3.2GB

256K

Text

Jan-v3:Q8_0

4.7GB · 256K context window · Text · 3 weeks ago

Jan-v3:Q8_0

4.7GB

256K

Text

Readme

Hugging face Source

Jan-v3-4B-base-instruct: a 4B baseline model for fine-tuning

Overview

Jan-v3-4B-base-instruct is a 4B-parameter model obtained via post-training distillation from a larger teacher, transferring capabilities while preserving general-purpose performance on standard benchmarks. The result is a compact, ownable base that is straightforward to fine-tune, broadly applicable and minimizing the usual capacity–capability trade-offs.

Building on this base, Jan-Code, a code-tuned variant, will be released soon.

Model Overview

This repo contains the BF16 version of Jan-v3-4B-base-instruct, which has the following features: - Type: Causal Language Models - Training Stage: Pretraining & Post-training - Number of Parameters: 4B in total - Number of Layers: 36 - Number of Attention Heads (GQA): 32 for Q and 8 for KV - Context Length: 262,144 natively.

Intended Use

A better small base for downstream work: improved instruction following out of the box, strong starting point for fine-tuning, and effective lightweight coding assistance.

Performance

Quick Start

Integration with Jan Apps

Jan-v3 demo is hosted on Jan Browser at chat.jan.ai. It is also optimized for direct integration with Jan Desktop, select the model in the app to start using it.

Local Deployment

Using vLLM:

vllm serve janhq/Jan-v3-4B-base-instruct \
    --host 0.0.0.0 \
    --port 1234 \
    --enable-auto-tool-choice \
    --tool-call-parser hermes

Using llama.cpp:

llama-server --model Jan-v3-4B-base-instruct-Q8_0.gguf \
    --host 0.0.0.0 \
    --port 1234 \
    --jinja \
    --no-context-shift

Recommended Parameters

For optimal performance in agentic and general tasks, we recommend the following inference parameters:

temperature: 0.7
top_p: 0.8
top_k: 20

🤝 Community & Support

Discussions: Hugging Face Community
Jan App: Learn more about the Jan App at jan.ai

📄 Citation

Updated Soon

Hugging face [Source](https://huggingface.co/janhq/Jan-v3-4B-base-instruct-gguf)
# Jan-v3-4B-base-instruct: a 4B baseline model for fine-tuning

![image](https://cdn-uploads.huggingface.co/production/uploads/655e3b59d5c0d3db5359ca3c/A65FII_r3rAi9wZtK5P_v.png)

## Overview

**Jan-v3-4B-base-instruct** is a 4B-parameter model obtained via post-training distillation from a larger teacher, transferring capabilities while preserving general-purpose performance on standard benchmarks. The result is a compact, ownable base that is straightforward to fine-tune, broadly applicable and minimizing the usual capacity–capability trade-offs.

Building on this base, **Jan-Code**, a code-tuned variant, **will be released soon.**

## Model Overview

This repo contains the BF16 version of **Jan-v3-4B-base-instruct**, which has the following features:
- Type: Causal Language Models
- Training Stage: Pretraining & Post-training
- Number of Parameters: 4B in total
- Number of Layers: 36
- Number of Attention Heads (GQA): 32 for Q and 8 for KV
- Context Length: **262,144 natively**.

**Intended Use**

* A better small base for downstream work: improved instruction following out of the box, strong starting point for fine-tuning, and effective lightweight coding assistance.

## Performance

![image](https://cdn-uploads.huggingface.co/production/uploads/655e3b59d5c0d3db5359ca3c/XD5IjuTl4wrw8R43BFOkj.png)

## Quick Start

### Integration with Jan Apps

Jan-v3 demo is hosted on **Jan Browser** at **[chat.jan.ai](https://chat.jan.ai/)**. It is also optimized for direct integration with [Jan Desktop](https://jan.ai/), select the model in the app to start using it.

### Local Deployment

**Using vLLM:**
```bash
vllm serve janhq/Jan-v3-4B-base-instruct \
    --host 0.0.0.0 \
    --port 1234 \
    --enable-auto-tool-choice \
    --tool-call-parser hermes 
    
```

**Using llama.cpp:**
```bash
llama-server --model Jan-v3-4B-base-instruct-Q8_0.gguf \
    --host 0.0.0.0 \
    --port 1234 \
    --jinja \
    --no-context-shift
```

### Recommended Parameters
For optimal performance in agentic and general tasks, we recommend the following inference parameters:
```yaml
temperature: 0.7
top_p: 0.8
top_k: 20
```

## 🤝 Community & Support

- **Discussions**: [Hugging Face Community](https://huggingface.co/janhq/Jan-v2-VL-8B/discussions) 
- **Jan App**: Learn more about the Jan App at [jan.ai](https://jan.ai/)

## 📄 Citation
```bibtex
Updated Soon
```

Paste, drop or click to upload images (.png, .jpeg, .jpg, .svg, .gif)