llama-3.2-1b-fc-dpo/README.md

---
base_model: meta-llama/Llama-3.2-1B-Instruct
library_name: transformers
tags:
- function-calling
- tool-use
- llama
- dpo
- preference-optimization
- bfcl
license: llama3.2
language:
- en
---

# Llama-3.2-1B-Instruct — Function Calling (DPO)

The [v1 SFT model](https://huggingface.co/Keitsuna123/llama-3.2-1b-fc-sft-full) further trained with **DPO (Direct Preference Optimization)** to recover an irrelevance-detection regression. DPO is a *preference optimization* method — not reinforcement learning — that optimizes a model to prefer "chosen" over "rejected" responses directly, without a reward model or sampling. This is one of six models in a study comparing supervised, preference, and RL post-training for small-model function calling.

**Code & writeup:** https://github.com/keitake123/llama-function-calling-study

## Results (BFCL v4)

| Category | Base | v1 SFT | GRPO (RL) | DPO (pref.) | Path B (SFT) |
|---|---|---|---|---|---|
| irrelevance | 35.8 | 5.8 | 5.4 | **8.3** | 21.7 |
| live_irrelevance | 67.3 | 16.9 | 17.2 | **28.6** | 36.8 |
| simple_python | 75.0 | 77.5 | 77.2 | 77.5 | 78.2 |
| multiple | 50.5 | 74.0 | 74.0 | 73.5 | 72.0 |
| live_simple | 31.8 | 57.0 | 56.2 | 58.5 | 54.3 |
| live_multiple | 7.3 | 38.8 | 39.4 | 37.0 | 35.7 |
| live_relevance | 43.8 | 93.8 | 93.8 | 81.2 | 81.2 |

**Finding:** DPO produced **partial** irrelevance recovery (5.8→8.3 non-live; 16.9→28.6 live) — clearly better than GRPO (which showed no recovery) but below refusal-SFT. This fits a clean pattern across the three methods:

> Recovery scaled with how *directly* each method exposed the model to the target behavior.
> **GRPO** never samples a refusal (the SFT always-call prior is too strong) → no signal → no recovery.
> **DPO** is *shown* refusals as the "chosen" response → partial recovery, at low cost to call categories.
> **Refusal-SFT** trains *directly* on refusals → strongest recovery.
>
> Ordering: imitation (SFT) > preference (DPO) > RL (GRPO). RL recovers least because it cannot reinforce a behavior absent from the policy's sampling distribution.

Notably, DPO preserved call-required categories well (simple_python, live_simple held up), giving arguably the best precision/recall balance despite a lower raw irrelevance score than Path B.

## Training details

- **Base:** v1 SFT model, cleanly merged (see note below)
- **Method:** DPO (TRL `DPOTrainer`), LoRA (r=16, α=32)
- **Data:** ~1,600 preference pairs, 50/50 mix:
  - *Irrelevance pairs:* chosen = natural refusal, rejected = v1's hallucinated call (generated by running v1 on the irrelevance prompts)
  - *Call-required pairs:* chosen = correct call, rejected = wrong-function call
- **Config:** 1 epoch, effective batch 8, lr 5e-6, **beta (KL) 0.3**, bf16
- **Hardware:** 1× RTX A6000

**Note on stability:** an initial run with beta=0.1 and a stacked (unmerged) reference adapter caused output-format drift (the model emitted a malformed call schema and occasionally code). Fixed by (1) cleanly merging the v1 adapter into the base before DPO so the reference model is well-formed, and (2) raising beta to 0.3 for a stronger anchor. See the repo's LESSONS.md.

## Usage

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

tokenizer = AutoTokenizer.from_pretrained("Keitsuna123/llama-3.2-1b-fc-dpo")
model = AutoModelForCausalLM.from_pretrained(
    "Keitsuna123/llama-3.2-1b-fc-dpo", torch_dtype=torch.bfloat16, device_map="auto"
)

messages = [{"role": "user", "content": "What's the weather in Tokyo?"}]
tools = [{"type": "function", "function": {
    "name": "get_weather", "description": "Get the weather for a location",
    "parameters": {"type": "object", "properties": {"location": {"type": "string"}}, "required": ["location"]}
}}]

text = tokenizer.apply_chat_template(messages, tools=tools, tokenize=False, add_generation_prompt=True)
inputs = tokenizer(text, return_tensors="pt").to(model.device)
out = model.generate(**inputs, max_new_tokens=128, do_sample=False)
print(tokenizer.decode(out[0][inputs['input_ids'].shape[1]:], skip_special_tokens=True))
```

## Limitations

- Residual irrelevance failures concentrate in short, factual-seeming queries ("what's 2+2", "capital of France") — the same sub-case that beat every method in this study.
- Parallel calls near-zero (single-call training only).

## Part of a series

| Model | Method | Description |
|---|---|---|
| [fc-sft-full](https://huggingface.co/Keitsuna123/llama-3.2-1b-fc-sft-full) | SFT | v1 SFT on xLAM |
| [fc-sft-v2-merged](https://huggingface.co/Keitsuna123/llama-3.2-1b-fc-sft-v2-merged) | SFT | + distilabel (data-scaling ablation) |
| [fc-grpo](https://huggingface.co/Keitsuna123/llama-3.2-1b-fc-grpo) | RL | GRPO (no recovery) |
| [fc-pathb](https://huggingface.co/Keitsuna123/llama-3.2-1b-fc-pathb) | SFT | refusal-SFT (best recovery) |
| [fc-dpo](https://huggingface.co/Keitsuna123/llama-3.2-1b-fc-dpo) | DPO | preference optimization (this model) |

## References & Acknowledgements

- **Base model:** Llama 3.2 (Meta AI) — [meta-llama/Llama-3.2-1B-Instruct](https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct)
- **Training data:** Salesforce xLAM — [xlam-function-calling-60k](https://huggingface.co/datasets/Salesforce/xlam-function-calling-60k); preference pairs constructed for this study
- **Method:** DPO (Rafailov et al., "Direct Preference Optimization")
- **Benchmark:** Berkeley Function Calling Leaderboard (BFCL) — [Gorilla project](https://github.com/ShishirPatil/gorilla)
- **Frameworks:** HuggingFace TRL (DPOTrainer), PEFT, Transformers

## Citation

```bibtex
@misc{taketsuna2026_fc_smallmodel,
  title  = {Small-Model Function Calling: Comparing SFT, Data Scaling, GRPO, and DPO Post-Training},
  author = {Taketsuna, Keiichi},
  year   = {2026},
  howpublished = {\url{https://github.com/keitake123/llama-function-calling-study}},
  note   = {Llama-3.2-1B function-calling post-training study on BFCL v4}
}
```