---
library_name: peft
base_model: LiquidAI/LFM2.5-1.2B-Instruct
tags:
  - lora
  - sft
  - trl
  - code-agent
  - smolagents
license: apache-2.0
language:
  - en
pipeline_tag: text-generation
---

# LFM25-1.2B-CodeAgent-opus4-default

A LoRA fine-tuned adapter for [LiquidAI/LFM2.5-1.2B-Instruct](https://huggingface.co/LiquidAI/LFM2.5-1.2B-Instruct) trained to follow the [smolagents](https://github.com/huggingface/smolagents) CodeAgent format.

## Model Description

This adapter teaches LFM2.5-1.2B to respond in the structured Thought + Code format required by smolagents CodeAgent:

````
Thought: I need to calculate this.
```python
result = 2 + 2
final_answer(result)
```
````

### Key Features

- **Base Model**: LiquidAI/LFM2.5-1.2B-Instruct (1.17B parameters)
- **Token Accuracy**: 90.2% on training data
- **Single-Turn Rate**: 53.8% of tasks solved in one turn
- **Adapter Size**: ~42MB (LoRA rank=16, alpha=32)

## Training Details

### Training Data

- **130 successful CodeAgent trajectories** generated using Claude Opus 4.5
- Tasks include mathematical reasoning, string manipulation, file operations, and general problem-solving
- Each trajectory demonstrates the Thought → Code → Observation → final_answer pattern
- Average trajectory length: 2971 tokens

### Training Configuration

| Parameter            | Value                                                 |
| -------------------- | ----------------------------------------------------- |
| LoRA Rank            | 16                                                    |
| LoRA Alpha           | 32                                                    |
| Target Modules       | w1, w2, w3, q_proj, k_proj, v_proj, out_proj, in_proj |
| Trainable Parameters | 11.1M (0.94% of base model)                           |
| Epochs               | 3                                                     |
| Learning Rate        | 1e-4                                                  |
| Batch Size           | 2 (effective 8 with gradient accumulation)            |
| Max Sequence Length  | 8192                                                  |
| Hardware             | NVIDIA RTX 3090 (24GB)                                |
| Training Time        | 260s                                                  |

### Training Framework

- [TRL](https://github.com/huggingface/trl) SFTTrainer
- [PEFT](https://github.com/huggingface/peft) for LoRA

## Ablation Study Results

This model is part of a teacher ablation study comparing different Claude models and prompting strategies:

| Teacher Config  | Token Accuracy | Training Time | Avg Trajectory Tokens |
| --------------- | -------------- | ------------- | --------------------- |
| haiku-default   | 73.8%          | 461s          | 2,957                 |
| sonnet-default  | 90.6%          | 260s          | 3,054                 |
| opus4-default   | 90.2%          | 260s          | 2,971                 |
| sonnet4-terse   | 94.9%          | 93s           | 632                   |
| **opus4-terse** | **95.0%**      | **76s**       | **613**               |

**Key Finding**: Terse, focused trajectories from capable teachers transfer significantly better to small models.

## Usage

### With PEFT

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

# Load base model
base_model = AutoModelForCausalLM.from_pretrained(
    "LiquidAI/LFM2.5-1.2B-Instruct",
    device_map="auto",
    torch_dtype="bfloat16",
)
tokenizer = AutoTokenizer.from_pretrained("LiquidAI/LFM2.5-1.2B-Instruct")

# Load LoRA adapter
model = PeftModel.from_pretrained(base_model, "krzysztofwos/LFM25-1.2B-CodeAgent-opus4-default")

# Generate
messages = [{"role": "user", "content": "What is 15 * 23?"}]
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)

outputs = model.generate(
    **inputs,
    max_new_tokens=512,
    temperature=0.1,
    top_p=0.1,
)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
```

### With smolagents

```python
from smolagents import CodeAgent, FinalAnswerTool, TransformersModel

model = TransformersModel(
    model_id="LiquidAI/LFM2.5-1.2B-Instruct",
    peft_model="krzysztofwos/LFM25-1.2B-CodeAgent-opus4-default",
)

agent = CodeAgent(
    tools=[FinalAnswerTool()],
    model=model,
)

result = agent.run("What is 15 * 23?")
print(result)
```

## Intended Use

- Code-assisted problem solving with small, efficient models
- Mathematical reasoning tasks
- Automated code generation following structured formats
- Research into prompt distillation and teacher model selection

## Limitations

- **1.2B model constraints**: Limited reasoning depth compared to larger models
- **English only**: Trained on English-language tasks
- **CodeAgent format specific**: Optimized for smolagents Thought/Code/final_answer pattern

## Citation

If you use this model, please cite:

```bibtex
@misc{lfm25-codeagent-opus4_default-2025,
  author = {krzysztofwos},
  title = {LFM25-1.2B-CodeAgent-opus4-default},
  year = {2025},
  publisher = {Hugging Face},
  url = {https://huggingface.co/krzysztofwos/LFM25-1.2B-CodeAgent-opus4-default}
}
```

## Acknowledgments

- [LiquidAI](https://www.liquid.ai/) for the LFM2.5 base model
- [Anthropic](https://www.anthropic.com/) for Claude Opus 4.5 (teacher model)
- [Hugging Face](https://huggingface.co/) for smolagents, TRL, and PEFT