README.md

---
license: apache-2.0
tags:
- materialsanalyst-ai-7b
- MaterialsAnalyst-AI-7B
- materials-science
- computational-materials
- materials-analysis
- chain-of-thought
- reasoning-model
- property-prediction
- materials-discovery
- crystal-structure
- materials-informatics
- scientific-ai
- 7b
- text-generation
- gguf
- quantized
- fine-tuned
- lora
- peft
- json-mode
- structured-output
- materials-engineering
- band-gap-prediction
- computational-chemistry
- materials-characterization
base_model:
- Qwen/Qwen2.5-7B-Instruct
language:
- en
---

![MaterialsAnalyst-AI Logo](Model_Logo.png)
MaterialsAnalyst-AI-7B transforms raw materials data into actionable insights. This **open source** model delivers transparent, step-by-step reasoning followed by structured analysis and practical application recommendations.

## Key Capabilities
- **Structured Reasoning**: Shows step-by-step analysis before delivering conclusions
- **Property Correlation**: Identifies relationships between material properties and their implications  
- **Application Prediction**: Suggests practical applications based on material characteristics

# See It In Action

Input Example:

```json
{
"material_id": "mp-8062",
"formula": "SiC",
"elements": ["Si", "C"],
"spacegroup": "P63mc",
"band_gap": 3.26,
"formation_energy_per_atom": -0.73,
"density": 3.21,
"volume": 41.2,
"nsites": 8,
"is_stable": true,
"elastic_modulus": 448,
"bulk_modulus": 220,
"thermal_expansion": 4.2e-06,
"electron_affinity": 4.0,
"ionization_energy": 6.7,
"crystal_system": "Hexagonal",
"magnetic_property": "Non-magnetic",
"thermal_conductivity": 490,
"specific_heat": 0.69,
"is_superconductor": false,
"band_gap_type": "Indirect"
}
```
Output Example:

The model produces structured output with two components:

#### 1. Step-by-Step Reasoning
~~~
<think>
I need to think through how to interpret this SiC entry and assess its characteristics.
First, I should examine the composition and structure. This material contains silicon (Si) and carbon (C) in a hexagonal crystal structure with space group P63mc. This structure suggests high symmetry and anisotropic properties, typical for wide-bandgap materials like SiC.
Next, I should analyze the electronic properties. With a band gap of 3.26 eV that is indirect, this material would be classified as a wide-bandgap semiconductor. This suggests applications in optoelectronics, high-power electronics, and transparent conductive oxides.
For thermodynamic stability, the formation energy per atom of -0.73 eV indicates strong bonding and thermodynamic favorability. The material is stable according to the data, which means it can be synthesized and used under practical conditions without decomposition.
The mechanical properties show a high elastic modulus (448 GPa) and bulk modulus (220 GPa). This suggests the material would be very stiff and resistant to deformation when subjected to stress or pressure.
Regarding thermal behavior, the thermal conductivity of 490 W/m·K and expansion coefficient of 4.2e-6 K^-1 indicate excellent heat dissipation and dimensional stability under temperature changes. This would make it suitable for high-temperature applications like thermal management in electronics or coatings.
The magnetic properties are listed as non-magnetic, which means it won't interact significantly with magnetic fields. This would affect applications in magneto-electronics but is generally beneficial for general semiconductor uses.
Additionally, the material is marked as not superconducting, which is significant because it rules out cryogenic or quantum computing applications where superconductivity is required.
Considering all these properties together, this material would be particularly valuable for high-power electronics, optoelectronics, and thermal management due to its combination of wide bandgap, high thermal conductivity, and mechanical robustness. It might compete with other materials like GaN or AlN but offers advantages in cost (Si-based) and thermal stability.
</think>
~~~

#### 2. Comprehensive Analysis
~~~
<answer>
**Summary of SiC (ID: mp-8062):**
1. **Material Type & Composition**
   - Silicon carbide (SiC), a widely studied wide-bandgap semiconductor compound.
2. **Crystal Structure**
   - Hexagonal structure with space group P63mc, indicating anisotropic properties and high symmetry.
3. **Electronic Properties**
   - Indirect bandgap of 3.26 eV, suitable for optoelectronics and high-power devices.
4. **Thermodynamic Stability**
   - Highly stable (formation energy: -0.73 eV/atom), making it practical for synthesis and use.
5. **Mechanical Properties**
   - Exceptional stiffness (elastic modulus: 448 GPa) and resistance to compression (bulk modulus: 220 GPa).
6. **Thermal Properties**
   - Outstanding thermal conductivity (490 W/m·K) and low expansion coefficient (4.2e-6 K^-1), ideal for heat dissipation.
7. **Magnetic & Conductive Properties**
   - Non-magnetic and non-superconducting, limiting use in magnetic applications but beneficial for general electronics.
8. **Applications**
   - High-power electronics, optoelectronics, thermal management systems, and abrasion-resistant coatings.
**Verdict**: SiC is a high-performance material with exceptional thermal, mechanical, and electronic properties, making it ideal for demanding applications like power devices and high-temperature environments. Its stability and robustness give it an edge over competing wide-bandgap materials.
</answer>
~~~

# Getting Started

## 1. Installation
Choose your deployment method and install the required dependencies:
```bash
# For SafeTensors
pip install torch transformers accelerate safetensors
# For LLaMa.cpp
pip install llama-cpp-python
```

## 2. Configuration
<u>Download</u> and edit your chosen inference script to customize the analysis:
- **Input data**: Update the `JSON_INPUT` variable with your materials data
- **Model location**: Set the `model_path` variable to your downloaded model directory

## 3. Running Analysis
Run your script and the analysis results will appear in the terminal:
```bash
# For SafeTensors
python Inference_safetensors.py
# For LLaMa.cpp
python Inference_llama.cpp.py
```

## Repository Contents

- **Model_Weights/** - All model weights in various formats
  - `llama.cpp/` - LLaMA.cpp compatible weights with various quantization options available
  - `safetensors/` - SafeTensors format models
  - `LoRA_adapter/` - LoRA adapter weights
- **Scripts/** - <u>Ready-to-use inference scripts</u>
  - `Inference_llama.cpp.py` - For LLaMA.cpp deployment
  - `Inference_safetensors.py` - For SafeTensors deployment
- **Data/** - Training data
  - `Dataset.jsonl` - Complete JSONL training dataset
- **Training/** - Training documentation and logs
  - `Training_Logs.txt` - Complete terminal logs from the training process
  - `Training_Documentation.txt` - Detailed training specifications and parameters

## Attribution
MaterialsAnalyst-AI-7B was developed by *Raymond Lee*. If you use this model in your work, please include a reference to this repository.