README.md

---
license: apache-2.0
base_model: HuggingFaceTB/SmolLM2-360M
datasets:
- ambrosfitz/Wikipedia_GraphCoT_Summarization
language:
- en
tags:
- text-generation
- summarization
- chain-of-thought
- graph-reasoning
- fine-tuned
pipeline_tag: text-generation
---

# SmolLM2-360M — GraphCoT Fine-tune

Fine-tuned version of [SmolLM2-360M](https://huggingface.co/HuggingFaceTB/SmolLM2-360M) on the [Wikipedia GraphCoT Summarization](https://huggingface.co/datasets/ambrosfitz/Wikipedia_GraphCoT_Summarization) dataset.

The model learns to perform **semantic graph chain-of-thought (GraphCoT) summarization**: given a raw paragraph, it explicitly constructs a semantic knowledge graph before writing a summary grounded exclusively in that graph. No fact in the summary can appear unless it exists as an edge.

---

## What it does

Given a paragraph wrapped in `<input>` tags, the model generates a structured `<reasoning>` block followed by a `<summary>`:

1. **Content words** — extracts key nouns, verbs, and proper entities
2. **Coreference** — resolves pronouns and aliases to a single primary subject
3. **Relations** — builds `(subject, relation, object)` triples in snake_case
4. **Graph** — organises triples into a rooted ASCII tree
5. **Summary** — writes 1–3 sentences where every clause maps to a graph edge

---

## Example output

**Input:**
```
Alan Turing was a British mathematician and computer scientist who played a
crucial role in breaking German ciphers during World War II. He is widely
regarded as the father of theoretical computer science and artificial intelligence.
```

**Model output:**
```
<reasoning>
<content_words>
  nouns: mathematician, computer, scientist, role, cipher, father, theory, intelligence
  verbs: break, regard
  proper_entities: Alan Turing, British, World War II, German
</content_words>

<coref>
  (none)
</coref>

<relations>
  (Alan Turing, is_a, British mathematician)
  (Alan Turing, is_a, computer scientist)
  (Alan Turing, broke, German ciphers)
  (Alan Turing, broke_during, World War II)
  (Alan Turing, is_the_father_of, theoretical computer science)
  (Alan Turing, is_the_father_of, artificial intelligence)
</relations>

<graph>
ROOT: Alan Turing
├─ is_a -> British mathematician
├─ is_a -> computer scientist
├─ broke -> German ciphers
│  └─ broke_during -> World War II
├─ is_the_father_of -> theoretical computer science
└─ is_the_father_of -> artificial intelligence
</graph>
</reasoning>

<summary>
Alan Turing was a British mathematician and computer scientist who broke German
ciphers during World War II. He is regarded as the father of theoretical computer
science and artificial intelligence.
</summary>
```

---

## Usage

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

model_id = "ambrosfitz/smollm2-graphcot"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.float16, device_map="auto")

paragraph = "Your paragraph here."
prompt = f"<input>\n{paragraph}\n</input>\n\n<reasoning>\n"

inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
with torch.no_grad():
    output_ids = model.generate(
        **inputs,
        max_new_tokens=400,
        do_sample=False,
        repetition_penalty=1.1,
    )

print(tokenizer.decode(output_ids[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True))
```

---

## Training

### Dataset
[ambrosfitz/Wikipedia_GraphCoT_Summarization](https://huggingface.co/datasets/ambrosfitz/Wikipedia_GraphCoT_Summarization) — 6,856 Wikipedia paragraphs processed through a two-stage pipeline:

- **Stage 1 (local):** spaCy scaffold — content word extraction, dependency triples, coreference clustering
- **Stage 2 (LLM):** Gemini 2.5 Flash normalization — semantic edge labelling, tree assembly, grounded summary generation

| Split | Records |
|-------|---------|
| Train | 6,172 |
| Validation | 342 |
| Test | 342 |

### Loss masking
Only `<reasoning>` and `<summary>` tokens contribute to the loss. The `<input>` paragraph is masked (`label = -100`) so the model learns to *generate* the graph and summary, not memorise the input.

### Hyperparameters

| Parameter | Value |
|-----------|-------|
| Base model | HuggingFaceTB/SmolLM2-360M |
| Epochs | 3 |
| Effective batch size | 16 (8 × 2 grad accum) |
| Learning rate | 2e-5 |
| LR schedule | Cosine with 100 warmup steps |
| Max sequence length | 1024 tokens |
| Precision | fp16 (AMP) |
| Gradient checkpointing | Yes |
| Hardware | NVIDIA T4 (Google Colab) |
| Training time | ~2h 18m |

### Training curves

| Step | Train Loss | Eval Loss |
|------|-----------|-----------|
| 100  | 0.520 | 0.497 |
| 300  | 0.369 | 0.367 |
| 500  | 0.315 | 0.335 |
| 700  | 0.310 | 0.320 |
| 900  | 0.260 | 0.314 |
| 1100 | 0.278 | 0.312 |
| 1158 | 0.282 | 0.312 |

Train and validation loss stayed within ~0.03 throughout — no overfitting.

---

## Limitations

- Trained on Wikipedia-style encyclopaedic paragraphs; may produce lower-quality graphs on conversational or highly technical text
- 360M parameters — graph structure may be incomplete or inconsistent on long or complex inputs
- Max context 1024 tokens; paragraphs longer than ~700 words will be truncated