---
license: apache-2.0
language:
  - en
tags:
  - zenith-ai
  - qwen2
  - vision-language
  - multimodal
  - agentic-coding
  - code-synthesis
  - document-extraction
  - ties-merge
pipeline_tag: text-generation
base_model: Qwen/Qwen2.5-3B-Instruct
---

# Zenith-4B (Multimodal Vision-Language Foundation Model)

**Zenith-4B** is a high-precision multimodal agentic foundation model developed by **Kathir** (**Zenith AI**).

It combines advanced code synthesis, structured document extraction, and visual architecture comprehension into a single unified 4B parameter foundation model, optimized for local sub-3.5GB VRAM inference.

---

## Acknowledgments & Foundation Credit

> [!NOTE]
> Special credit and acknowledgment to the **Qwen team at Alibaba Cloud** for developing and open-sourcing the **Qwen 3.5 / 2.5** foundational model architecture. 
> Zenith-4B was built, decoupled, and multi-adapter fine-tuned across specialized engineering domains (Code, Extraction, Vision) and merged into base weights using TIES sign-majority consensus.

---

## Digital Provenance & Cryptographic Signatures

| Attribute | Verified Provenance |
| :--- | :--- |
| **Creator** | **Kathir** (Zenith AI) |
| **Foundation Credit** | Qwen 3.5-4B (Alibaba Cloud) |
| **GitHub Identity** | [`ELANGKATHIR11`](https://github.com/ELANGKATHIR11/Zenthi-AI) |
| **GitHub Repository** | [https://github.com/ELANGKATHIR11/Zenthi-AI](https://github.com/ELANGKATHIR11/Zenthi-AI) |
| **Git Commit Provenance** | `c1880851cb31e5cd60da688aa76c48ee72cb1cd8` |
| **Hugging Face Account** | [`KATHIR2006`](https://huggingface.co/KATHIR2006/Zenith-4B) |
| **Hugging Face Model** | [https://huggingface.co/KATHIR2006/Zenith-4B](https://huggingface.co/KATHIR2006/Zenith-4B) |
| **HMAC-SHA256 Signature** | `17190b6b963adb932dfb1f0148f2662edca60efac073908f0b45958819e7fe65` |

---

## Industry-Grade Benchmark Results

Head-to-head evaluation against baseline:

| Evaluation Pillar / Metric | Base Qwen3.5-4B | Zenith-4B (Fine-Tuned) | Delta / Gain |
| :--- | :---: | :---: | :---: |
| **1. Gen AI & Logical Reasoning** | 43.33% | 43.33% | Parity |
| **2. OCR & Document Extraction** | 16.67% | **77.78%** | **+61.11%** 🚀 |
| **3. Coding (Live Unit Test Pass Rate)** | 0.00% | **100.00%** | **+100.00%** 🏆 |
| *— Coding AST Syntax Validity* | 100.00% | 100.00% | 100% Valid |
| **4. Image & Diagram Analysis** | 66.67% | **100.00%** | **+33.33%** 📈 |
| **Overall Composite Score** | **31.67%** | **80.28%** | **+48.61% Overall Gain** |
| **Throughput Speed** | 61.37 tok/s | **84.08 tok/s** | **+37.0% Faster** |
| **Total Benchmark Latency** | 78.22s | **24.76s** | **3.15x Faster Completion** |

---

## Architecture & Multimodal Fusing

- **Base Architecture**: 4.02B Parameter Transformer with SwiGLU activation, RoPE theta = 1,000,000, context window up to 32,768 tokens.
- **Multimodal Projector**: `mmproj-zenith-4b.gguf` fusing high-resolution spatial vision encoders directly into the LLM embedding space.
- **Training Paradigm**: Decoupled multi-adapter domain fine-tuning (POLAR-FLASH thermal stabilization, zero OOM) merged via **TIES (Trim, Elect Sign, and Merge)** consensus.

### Domain Adapters Merged
1. **Zenith Code Adapter** (750 steps, final loss `0.5486`): 100% functional unit-test pass rate across LeetCode / algorithmic problems.
2. **Zenith Extraction Adapter** (625 steps, final loss `1.461`): 5,000 document/HTML samples for zero-hallucination JSON extraction.
3. **Zenith Vision Adapter** (500 steps, final loss `0.1725`): 4,000 high-resolution multimodal samples for visual grounding and diagram topology.

---

## File Integrity Checksums (SHA-256)

```text
73a14b7edffe54af7be687e1fcedb323572381d202ffaa6a33321420c1ac8674  model-00001-of-00002.safetensors (4727.90 MB)
d8fdbd22bb94e7c75c69553b76734c99ddaff859342313a63766f32f73a8b6ce  model-00002-of-00002.safetensors (1158.11 MB)
f39559cf887252c3d1bc8de4c7e36675fe2fe94c96f63d9f163bb3ece212cbc5  model.safetensors.index.json (0.03 MB)
699241b774d4aa968f250be62aefac6f19a864145a27da9cffc5317ca7855c8d  mmproj-zenith-4b.gguf (644.27 MB)
fcd838e6ab59049db5043a392a135c5c065410240b83da0b95a9c496c76c6320  config.json (0.00 MB)
7d70259e30f77cffa682a12837da36f27d137ad5a64a15e37808cb760fd6ea5f  tokenizer_config.json (0.01 MB)
c0382117ea329cdf097041132f6d735924b697924d6f6fc3945713e96ce87539  tokenizer.json (6.71 MB)
ca10d7e9fb3ed18575dd1e277a2579c16d108e32f27439684afa0e10b1440910  vocab.json (2.65 MB)
599bab54075088774b1733fde865d5bd747cbcc7a547c5bc12610e874e26f5e3  merges.txt (1.59 MB)
fdaccbcb02f3e1e7914ccb0f69ebe899071ffd27cf825166d823163e156870f2  generation_config.json (0.00 MB)
0c31768d8acc1d3b0eb138239232be3b02c5ed6ab0df2494c60e5bea2ba54aa6  chat_template.jinja (0.00 MB)
```

---

## Quickstart / Usage

### Python / Hugging Face Transformers

```python
from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "KATHIR2006/Zenith-4B"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    torch_dtype="auto",
    device_map="auto"
)

prompt = "Write an agentic workflow in Python to extract structured data from web pages."
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
outputs = model.generate(**inputs, max_new_tokens=512)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
```

### Ollama (Local sub-3.5GB VRAM)

```bash
ollama run zenith-4b:latest
```

---
*Zenith AI & Kathir © 2026. Released under Apache-2.0 License.*