Subject-Emu-5259
/

NeuralAI

@@ -1,207 +1,96 @@
 ---
 base_model: HuggingFaceTB/SmolLM2-360M-Instruct
 library_name: peft
-pipeline_tag: text-generation
 tags:
-- base_model:adapter:HuggingFaceTB/SmolLM2-360M-Instruct
 - lora
-- transformers
 ---
-# 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
-<!-- This section is meant to convey both technical and sociotechnical limitations. -->
-[More Information Needed]
-### Recommendations
-<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
-Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
-## How to Get Started with the Model
-Use the code below to get started with the model.
-[More Information Needed]
-## 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
-## Model Examination [optional]
-<!-- Relevant interpretability work for the model goes here -->
-[More Information Needed]
-## Environmental Impact
-<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
-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).
-- **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]
-## Technical Specifications [optional]
-### Model Architecture and Objective
-[More Information Needed]
-### Compute Infrastructure
-[More Information Needed]
-#### Hardware
-[More Information Needed]
-#### Software
-[More Information Needed]
-## Citation [optional]
-<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
-**BibTeX:**
-[More Information Needed]
-**APA:**
-[More Information Needed]
-## Glossary [optional]
-<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
-[More Information Needed]
-## More Information [optional]
-[More Information Needed]
-## Model Card Authors [optional]
-[More Information Needed]
-## Model Card Contact
-[More Information Needed]
-### Framework versions
-- PEFT 0.19.0

 ---
 base_model: HuggingFaceTB/SmolLM2-360M-Instruct
 library_name: peft
+model_name: NeuralAI
+model_type: adapter
+license: apache-2.0
+language:
+- en
 tags:
+- text-generation
+- dpo
 - lora
+- peft
+- smollm2
+- reasoning
+- code-generation
+- debugging
+- multi-step-reasoning
+- edge-ai
+pipeline_tag: text-generation
+inference:
+  parameters:
+    max_new_tokens: 512
+    temperature: 0.7
+    top_p: 0.95
+    repetition_penalty: 1.1
 ---
+# NeuralAI v15.0 — DPO-Aligned LoRA Adapter
+NeuralAI is a DPO-aligned LoRA adapter for [SmolLM2-360M-Instruct](https://huggingface.co/HuggingFaceTB/SmolLM2-360M-Instruct), fine-tuned for expert-level reasoning, code generation, debugging, and multi-step logic tasks.
+## Highlights
+- **597 DPO preference pairs** covering code correctness, logic, reasoning, debugging, and multi-step tasks
+- **Reward margin**: improved from ~0.5 to ~3.5 (model strongly prefers chosen responses)
+- **Final training loss**: 0.305
+- **Edge-optimized**: Runs on CPU with 4GB RAM — no GPU required
+- **Gemini-style alignment**: Helpful, structured, conversational tone with step-by-step explanations
+## Quick start
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+from peft import PeftModel
+base_model = AutoModelForCausalLM.from_pretrained("HuggingFaceTB/SmolLM2-360M-Instruct")
+tokenizer = AutoTokenizer.from_pretrained("HuggingFaceTB/SmolLM2-360M-Instruct")
+model = PeftModel.from_pretrained(base_model, "Subject-Emu-5259/NeuralAI")
+messages = [{"role": "user", "content": "Write a Python function to check API health."}]
+inputs = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt")
+output = model.generate(inputs, max_new_tokens=256, temperature=0.7, top_p=0.95)
+print(tokenizer.decode(output[0][inputs.shape[-1]:], skip_special_tokens=True))
+```
+## Training details
+| Parameter | Value |
+|---|---|
+| Base model | HuggingFaceTB/SmolLM2-360M-Instruct |
+| Method | DPO (Direct Preference Optimization) |
+| Dataset | 597 preference pairs (v15 expanded) |
+| Epochs | 3 |
+| Steps | 450 |
+| Final loss | 0.305 |
+| Reward margin | ~3.5 |
+| LoRA rank | 16 |
+| Hardware | Apple Silicon MPS (MacBook Air M4) |
+| Duration | ~12 minutes |
+| Completed | 2026-07-11 |
+## Framework versions
+- PEFT: 0.17.1
+- TRL: 0.24.0
+- Transformers: 4.57.6
+- PyTorch: 2.8.0
+## Use cases
+- **Code generation and debugging**: Multi-step reasoning for code correctness
+- **Logic and math**: Complex problem decomposition
+- **Edge deployment**: CPU-optimized for local/private AI
+- **Agentic workflows**: Tool-use and multi-step task execution
+## Citation
+```bibtex
+@inproceedings{rafailov2023direct,
+    title        = {{Direct Preference Optimization: Your Language Model is Secretly a Reward Model}},
+    author       = {Rafael Rafailov and Archit Sharma and Eric Mitchell and Christopher D. Manning and Stefano Ermon and Chelsea Finn},
+    year         = 2023,
+    booktitle    = {NeurIPS 2023},
+}
+```