---
base_model: Qwen/Qwen3.5-4B
license: apache-2.0
library_name: peft
tags:
  - base_model:adapter:Qwen/Qwen3.5-4B
  - lora
  - sft
  - transformers
  - knowledge-graph
  - fine-tuning
  - medical
  - financial
pipeline_tag: text-generation
datasets:
  - likhithv/knowledgemesh-benchmark-eval
---

# KnowledgeMesh Full Model — LoRA Adapter

LoRA adapter for `Qwen/Qwen3.5-4B` fine-tuned on **4,361 knowledge graph-guided training samples** generated by the KnowledgeMesh pipeline from financial (Apple 10-K) and medical (PubMed abstracts) documents.

This is the **KM (full)** model from the paper *"Knowledge Graph-Guided Fine-Tuning Data Generation: A Rigorous Benchmark"*.

## Benchmark Results

Evaluated by Gemini 2.5 Flash pointwise judge (1–5 scale, 4 dimensions):

| Eval Set | Base | Meta SDK | **This Model** | Delta |
|---|---|---|---|---|
| Primary (n=473, KM-generated) | 1.79 | 1.93 | **2.47** | **+0.54** |
| Independent (n=955, Gemini-generated) | 1.96 | 2.17 | **2.90** | **+0.72** |

The independent eval set (+0.72, p < 0.0001, Cohen's d = 0.57) is the primary claim — questions were generated by a different model (Gemini) with no access to the KG structure, eliminating question-style bias as an explanation.

## Usage

```python
from transformers import AutoTokenizer, AutoModelForCausalLM
from peft import PeftModel
import torch

base_model_id = "Qwen/Qwen3.5-4B"
adapter_id = "likhithv/km-full-model"

tokenizer = AutoTokenizer.from_pretrained(base_model_id)
base_model = AutoModelForCausalLM.from_pretrained(
    base_model_id,
    torch_dtype=torch.bfloat16,
    device_map="auto",
)
model = PeftModel.from_pretrained(base_model, adapter_id)

messages = [{"role": "user", "content": "What are the main risk factors for type 2 diabetes?"}]
inputs = tokenizer.apply_chat_template(messages, return_tensors="pt", add_generation_prompt=True)
outputs = model.generate(inputs.to(model.device), max_new_tokens=256)
print(tokenizer.decode(outputs[0][inputs.shape[-1]:], skip_special_tokens=True))
```

## Training Details

| Parameter | Value |
|---|---|
| Base model | Qwen/Qwen3.5-4B (4-bit quantized via bitsandbytes) |
| Fine-tuning method | LoRA (rank=16, alpha=16) |
| Training samples | 4,361 (KG-guided: atomic, aggregated, multihop, chain-of-thought) |
| Epochs | 3 |
| Learning rate | 2e-4 |
| Effective batch size | 8 |
| Hardware | Kaggle T4 GPU (16 GB) |
| Domains | Financial (Apple 10-K 2023), Medical (PubMed abstracts) |

## Eval Datasets

- [`likhithv/knowledgemesh-benchmark-eval`](https://huggingface.co/datasets/likhithv/knowledgemesh-benchmark-eval) — both primary (n=473) and independent (n=955) eval sets

## Compared Models

- This model: trained on 4,361 KG-guided samples
- [`likhithv/meta-sdk-baseline`](https://huggingface.co/likhithv/meta-sdk-baseline) — trained on 1,209 chunk-based samples (Meta Synthetic Data Kit)

## Citation

```bibtex
@misc{knowledgemesh2026,
  title={Knowledge Graph-Guided Fine-Tuning Data Generation: A Rigorous Benchmark},
  author={Likhith V},
  year={2026},
  howpublished={https://huggingface.co/likhithv/km-full-model}
}
```