---
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-terse

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-Instruct 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 (1.2B parameter)
- **Format Compliance**: N/A with minimal prompt
- **Answer Accuracy**: N/A on evaluation tasks
- **Adapter Size**: ~47MB (LoRA rank=16, alpha=32)

## Training Details

### Training Data

- **130 successful CodeAgent trajectories** generated using Claude Opus 4.5 (terse prompt) as the teacher model
- Tasks include mathematical reasoning, string manipulation, and general problem-solving
- Each trajectory demonstrates the Thought → Code → Observation → final_answer pattern

### 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 | ~25M |
| Training Steps       | 3 epochs   |
| Learning Rate        | 1e-4    |
| Batch Size           | 2 (grad accum 4)       |
| Max Sequence Length  | 8192   |
| Hardware             | GPU         |
| Training Time        | see ablation report    |

### Training Framework

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

## Evaluation Results

### Prompt Mode Comparison

| Prompt Mode | Format Compliance           | Answer Accuracy           |
| ----------- | --------------------------- | ------------------------- |
| **Minimal** | N/A         | N/A         |
| Default     | N/A | N/A |
| None        | N/A    | N/A    |

The model performs best with the **minimal prompt** (~95 tokens), demonstrating successful prompt distillation.

### Minimal Prompt Template

````text
You are a CodeAgent that solves tasks by writing and executing Python code.

Always respond with Thought + Python code block. Example:

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

Call final_answer(result) when done. Now Begin!
````

## 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-terse")

# 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=0.3,
    min_p=0.15,
)
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-terse",
)

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

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

## Intended Use

- Code-assisted problem solving
- Mathematical reasoning tasks
- Automated code generation following structured formats
- Research into prompt distillation and small model fine-tuning

## Limitations

- **Requires specific prompt format**: Works best with minimal prompt template
- **Limited reasoning depth**: 1.2B parameter model has constrained reasoning capabilities compared to larger models
- **English only**: Trained on English-language tasks

## Citation

If you use this model, please cite:

```bibtex
@misc{lfm25_1.2b_codeagent_opus4_terse,
  author = {krzysztofwos},
  title = {LFM25-1.2B-CodeAgent-opus4-terse},
  year = {2025},
  publisher = {Hugging Face},
  url = {https://huggingface.co/krzysztofwos/LFM25-1.2B-CodeAgent-opus4-terse}
}
```

## Acknowledgments

- [LiquidAI](https://www.liquid.ai/) for the LFM2.5-1.2B-Instruct base model
- [Hugging Face](https://huggingface.co/) for smolagents, TRL, and PEFT
- Training performed as part of CodeAgent prompt distillation research