Update README.md

README.md

@@ -11,12 +11,58 @@ language:
 - en
 ---
 
-# Uploaded  model
 
-- **Developed by:** Daemontatox
-- **License:** apache-2.0
-- **Finetuned from model :** unsloth/qwen3-32b-bnb-4bit
+![image](./image.png)
+# Manticore-32B
 
-This qwen3 model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
+**Developed by:** Daemontatox  
+**License:** Apache-2.0  
+**Finetuned from:** [unsloth/qwen3-32b-unsloth](https://huggingface.co/unsloth/qwen3-32b-unsloth)
 
-[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
+## Model Overview
+
+**Manticore-32B** is a fine-tuned version of Qwen3-32B using the high-quality **OpenThoughts2-1M** dataset. Fine-tuned with Unsloth’s TRL-compatible framework and LoRA for efficient performance, this model is optimized for **advanced reasoning tasks**, including **math**, **logic puzzles**, **code generation**, and **step-by-step problem solving**.
+
+## Training Dataset
+
+- **Dataset:** [OpenThoughts2-1M](https://huggingface.co/datasets/open-thoughts/OpenThoughts2-1M)  
+- **Source:** A synthetic dataset curated and expanded by the OpenThoughts team  
+- **Volume:** ~1.1M high-quality examples  
+- **Content Type:** Multi-turn reasoning, math proofs, algorithmic code generation, logical deduction, and structured conversations  
+- **Tools Used:** [Curator Viewer](https://curator.bespokelabs.ai/)  
+
+This dataset builds upon OpenThoughts-114k and integrates strong reasoning-centric data sources like OpenR1-Math and KodCode.
+
+## Intended Use
+
+This model is particularly suited for:
+
+- Chain-of-thought and step-by-step reasoning  
+- Code generation with logical structure  
+- Educational tools for math and programming  
+- AI agents requiring multi-turn problem-solving  
+
+## Limitations
+
+- English-only focus (does not generalize well to other languages)  
+- May hallucinate factual content despite reasoning depth  
+- Inherits possible biases from synthetic pretraining data  
+
+## Example Usage
+
+```python
+# Use a pipeline as a high-level helper
+from transformers import pipeline
+
+messages = [
+    {"role": "user", "content": "Who are you?"},
+]
+pipe = pipeline("text-generation", model="Daemontatox/Manticore-32B")
+pipe(messages)
+```
+
+### Training Details
+## Framework: TRL + LoRA with Unsloth acceleration
+## Epochs/Steps: Custom fine-tuning on ~1M samples
+## Hardware: Single-node A100 80GB / similar high-VRAM setup
+## Objective: Enhance multi-domain reasoning under compute-efficient constraints