Upload README.md with huggingface_hub

README.md

@@ -1,209 +1,178 @@
 ---
-base_model: LiquidAI/LFM2-2.6B-Exp
 library_name: peft
-pipeline_tag: text-generation
+base_model: LiquidAI/LFM2-2.6B-Exp
 tags:
-- base_model:adapter:LiquidAI/LFM2-2.6B-Exp
 - lora
 - sft
-- transformers
 - trl
+- code-agent
+- smolagents
+license: apache-2.0
+language:
+- en
+pipeline_tag: text-generation
 ---
 
-# Model Card for Model ID
-
-<!-- Provide a quick summary of what the model is/does. -->
-
-
-
-## Model Details
-
-### Model Description
-
-<!-- Provide a longer summary of what this model is. -->
-
-
-
-- **Developed by:** [More Information Needed]
-- **Funded by [optional]:** [More Information Needed]
-- **Shared by [optional]:** [More Information Needed]
-- **Model type:** [More Information Needed]
-- **Language(s) (NLP):** [More Information Needed]
-- **License:** [More Information Needed]
-- **Finetuned from model [optional]:** [More Information Needed]
-
-### Model Sources [optional]
-
-<!-- Provide the basic links for the model. -->
-
-- **Repository:** [More Information Needed]
-- **Paper [optional]:** [More Information Needed]
-- **Demo [optional]:** [More Information Needed]
-
-## Uses
-
-<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
-
-### Direct Use
-
-<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
-
-[More Information Needed]
-
-### Downstream Use [optional]
-
-<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
-
-[More Information Needed]
-
-### Out-of-Scope Use
-
-<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
-
-[More Information Needed]
-
-## Bias, Risks, and Limitations
+# LFM2-2.6B-CodeAgent-LoRA
 
-<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+A LoRA fine-tuned adapter for [LiquidAI/LFM2-2.6B-Exp](https://huggingface.co/LiquidAI/LFM2-2.6B-Exp) trained to follow the [smolagents](https://github.com/huggingface/smolagents) CodeAgent format.
 
-[More Information Needed]
+## Model Description
 
-### Recommendations
+This adapter teaches LFM2-2.6B-Exp to respond in the structured Thought + Code format required by smolagents CodeAgent:
 
-<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+```
+Thought: I need to calculate this.
+```python
+result = 2 + 2
+final_answer(result)
+```
+```
 
-Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+### Key Features
 
-## How to Get Started with the Model
-
-Use the code below to get started with the model.
-
-[More Information Needed]
+- **Base Model**: LiquidAI/LFM2-2.6B-Exp (2.6B parameter hybrid architecture with LIV convolution + GQA)
+- **Format Compliance**: 100% with minimal prompt
+- **Answer Accuracy**: 80% on evaluation tasks
+- **Adapter Size**: ~49MB (LoRA rank=8, alpha=16)
 
 ## Training Details
 
 ### Training Data
 
-<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
-
-[More Information Needed]
-
-### Training Procedure
-
-<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
-
-#### Preprocessing [optional]
-
-[More Information Needed]
-
-
-#### Training Hyperparameters
-
-- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
-
-#### Speeds, Sizes, Times [optional]
-
-<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
-
-[More Information Needed]
-
-## Evaluation
-
-<!-- This section describes the evaluation protocols and provides the results. -->
-
-### Testing Data, Factors & Metrics
-
-#### Testing Data
-
-<!-- This should link to a Dataset Card if possible. -->
-
-[More Information Needed]
-
-#### Factors
-
-<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
-
-[More Information Needed]
-
-#### Metrics
-
-<!-- These are the evaluation metrics being used, ideally with a description of why. -->
-
-[More Information Needed]
-
-### Results
-
-[More Information Needed]
-
-#### Summary
+- **130 successful CodeAgent trajectories** generated using Claude 3.5 Sonnet 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 | 8 |
+| LoRA Alpha | 16 |
+| Target Modules | q_proj, v_proj |
+| Trainable Parameters | 12.2M (0.47% of base) |
+| Training Steps | 30 |
+| Learning Rate | 2e-4 |
+| Batch Size | 4 |
+| Max Sequence Length | 2048 |
+| Hardware | NVIDIA RTX 3090 (24GB) |
+| Training Time | ~5.5 hours |
 
-## Model Examination [optional]
+### Training Framework
 
-<!-- Relevant interpretability work for the model goes here -->
+- [TRL](https://github.com/huggingface/trl) SFTTrainer
+- [PEFT](https://github.com/huggingface/peft) for LoRA
 
-[More Information Needed]
+## Evaluation Results
 
-## Environmental Impact
+### Prompt Mode Comparison
 
-<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+| Prompt Mode | Format Compliance | Answer Accuracy |
+|-------------|-------------------|-----------------|
+| **Minimal** | 100% | 80% |
+| Default | 80% | 80% |
+| None | 0% | 0% |
 
-Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+The model performs best with the **minimal prompt** (~95 tokens), demonstrating successful prompt distillation.
 
-- **Hardware Type:** [More Information Needed]
-- **Hours used:** [More Information Needed]
-- **Cloud Provider:** [More Information Needed]
-- **Compute Region:** [More Information Needed]
-- **Carbon Emitted:** [More Information Needed]
+### Minimal Prompt Template
 
-## Technical Specifications [optional]
+```text
+You are a CodeAgent that solves tasks by writing and executing Python code.
 
-### Model Architecture and Objective
+Always respond with Thought + Python code block. Example:
 
-[More Information Needed]
+Thought: I need to calculate this.
+```python
+result = 2 + 2
+final_answer(result)
+```
 
-### Compute Infrastructure
+Call final_answer(result) when done. Now Begin!
+```
 
-[More Information Needed]
+## Usage
 
-#### Hardware
+### With PEFT
 
-[More Information Needed]
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+from peft import PeftModel
 
-#### Software
+# Load base model
+base_model = AutoModelForCausalLM.from_pretrained(
+    "LiquidAI/LFM2-2.6B-Exp",
+    device_map="auto",
+    torch_dtype="bfloat16",
+)
+tokenizer = AutoTokenizer.from_pretrained("LiquidAI/LFM2-2.6B-Exp")
 
-[More Information Needed]
+# Load LoRA adapter
+model = PeftModel.from_pretrained(base_model, "krzysztofwos/LFM2-2.6B-CodeAgent-LoRA")
 
-## Citation [optional]
+# 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)
 
-<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+outputs = model.generate(
+    **inputs,
+    max_new_tokens=512,
+    temperature=0.3,
+    min_p=0.15,
+)
+print(tokenizer.decode(outputs[0], skip_special_tokens=True))
+```
 
-**BibTeX:**
+### With smolagents
 
-[More Information Needed]
+```python
+from smolagents import CodeAgent, FinalAnswerTool, TransformersModel
 
-**APA:**
+model = TransformersModel(
+    model_id="LiquidAI/LFM2-2.6B-Exp",
+    peft_model="krzysztofwos/LFM2-2.6B-CodeAgent-LoRA",
+)
 
-[More Information Needed]
+agent = CodeAgent(
+    tools=[FinalAnswerTool()],
+    model=model,
+)
 
-## Glossary [optional]
+result = agent.run("What is 15 * 23?")
+print(result)
+```
 
-<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+## Intended Use
 
-[More Information Needed]
+- Code-assisted problem solving
+- Mathematical reasoning tasks
+- Automated code generation following structured formats
+- Research into prompt distillation and small model fine-tuning
 
-## More Information [optional]
+## Limitations
 
-[More Information Needed]
+- **Requires specific prompt format**: Works best with minimal prompt template
+- **Limited reasoning depth**: 2.6B parameter hybrid architecture with LIV convolution + GQA model has constrained reasoning capabilities compared to larger models
+- **English only**: Trained on English-language tasks
 
-## Model Card Authors [optional]
+## Citation
 
-[More Information Needed]
+If you use this model, please cite:
 
-## Model Card Contact
+```bibtex
+@misc{lfm2_2.6b_codeagent_lora,
+  author = {krzysztofwos},
+  title = {LFM2-2.6B-CodeAgent-LoRA},
+  year = {2025},
+  publisher = {Hugging Face},
+  url = {https://huggingface.co/krzysztofwos/LFM2-2.6B-CodeAgent-LoRA}
+}
+```
 
-[More Information Needed]
-### Framework versions
+## Acknowledgments
 
-- PEFT 0.18.0
+- [LiquidAI](https://www.liquid.ai/) for the LFM2-2.6B-Exp base model
+- [Hugging Face](https://huggingface.co/) for smolagents, TRL, and PEFT
+- Training performed as part of CodeAgent prompt distillation research