update README.md

README.md

@@ -1,3 +1,75 @@
----
-license: apache-2.0
----
+---
+license: apache-2.0
+---
+
+---
+base_model: Qwen/Qwen3-8B
+tags:
+  - adaptive-teaching
+  - reinforcement-learning
+  - educational
+datasets:
+  - Arc-Intelligence/Arc-ATLAS-Teach-v0
+language:
+  - en
+library_name: transformers
+---
+
+# ATLAS-Teach-8B-Instruct
+
+An adaptive teaching model trained using the Reinforcement Collaborative Learning (RCL) framework. This is the supervised fine-tuning (SFT) checkpoint before reinforcement learning.
+
+## Model Details
+
+- **Base Model**: Qwen/Qwen3-8B
+- **Model Size**: 8B parameters
+- **Training Stage**: Supervised Fine-tuning (Pre-RL)
+- **Framework**: RCL (Reinforcement Collaborative Learning)
+
+## Training Data
+
+Trained on `Arc-Intelligence/Arc-ATLAS-Teach-v0` dataset with RCL-specific formatting for adaptive teaching.
+
+## Intended Use
+
+This model is designed for:
+- Adaptive teaching based on student capability assessment
+- Educational content generation
+- Problem-solving assistance with tailored explanations
+
+## Training Configuration
+
+- **Hardware**: 8x H100 GPUs
+- **Framework**: RCL
+- **Mixed Precision**: BF16
+
+## Adaptive Teaching Protocol
+
+The model implements a two-pass teaching approach:
+
+1. **Diagnostic Probing**: Assesses student understanding with minimal interaction
+2. **Adaptive Teaching**: Generates tailored teaching based on diagnosed capability
+
+## Usage
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model = AutoModelForCausalLM.from_pretrained("Arc-Intelligence/ATLAS-Teach-8B-Instruct")
+tokenizer = AutoTokenizer.from_pretrained("Arc-Intelligence/ATLAS-Teach-8B-Instruct")
+
+# Format your input according to the RCL teaching protocol
+prompt = "Question: {your_question}\n\nProvide adaptive teaching:"
+inputs = tokenizer(prompt, return_tensors="pt")
+outputs = model.generate(**inputs)
+response = tokenizer.decode(outputs[0], skip_special_tokens=True)
+```
+
+## Limitations
+
+- This is a pre-RL checkpoint; the full RCL training includes an additional RL phase
+- Performance metrics on specific benchmarks are being evaluated
+
+## License
+
+Apache 2.0