Update README.md

README.md

@@ -1,20 +1,49 @@
-# Canis.teach — Qwen3‑4B Instruct (Science)
+---
+license: apache-2.0
+language:
+- en
+base_model:
+- Qwen/Qwen3-4B-Instruct-2507
+base_model_relation: adapter
+library_name: peft
+tags:
+- canis-teach
+- qwen3
+- education
+- lora
+- transformers
+- science
+- tutoring
+pipeline_tag: text-generation
+datasets:
+- CanisAI/teach-science-v1
+---
+
+# Canis.teach - Qwen3-4B Instruct (Science)
 
 LoRA adapters for the Science tutor in the Canis.teach suite.
 
-- Base: Qwen/Qwen3-4B-Instruct-2507
-- Release: CanisAI/teach-science-qwen3-4b-2507-r1
-- Project: Canis.teach, Learning that fits.
-- Tags: canis-teach, qwen3, education, lora, transformers
+- **Base Model**: Qwen/Qwen3-4B-Instruct-2507
+- **Release**: CanisAI/teach-science-qwen3-4b-2507-r1
+- **Project**: Canis.teach - Learning that fits.
+- **Subject**: Science
 
 ## What is this?
 
-This repository provides LoRA adapters fine‑tuned on Science tutoring dialogues. Apply these adapters to the base model to enable subject‑aware, didactic behavior without downloading a full merged checkpoint.
+This repository provides LoRA adapters fine-tuned on Science tutoring dialogues. Apply these adapters to the base model to enable subject-aware, didactic behavior without downloading a full merged checkpoint.
 
-For a ready‑to‑run merged model or an Ollama‑friendly GGUF build, see “Related.”
+The model is designed to **teach, not just answer** - providing step-by-step explanations, hints, and pedagogically structured responses.
 
-## Usage (LoRA)
+For ready-to-run merged models or Ollama-friendly GGUF quantizations, see the "Related Models" section.
 
+## Quick Start
+
+### Installation
+```bash
+pip install transformers peft torch
+```
+
+### Usage (LoRA)
 ```python
 from transformers import AutoTokenizer, AutoModelForCausalLM
 from peft import PeftModel
@@ -22,58 +51,102 @@ from peft import PeftModel
 base = "Qwen/Qwen3-4B-Instruct-2507"
 adapter = "CanisAI/teach-science-qwen3-4b-2507-r1"
 
-tok = AutoTokenizer.from_pretrained(base, use_fast=True)
-model = AutoModelForCausalLM.from_pretrained(base, device_map="auto")
+tokenizer = AutoTokenizer.from_pretrained(base, use_fast=True)
+model = AutoModelForCausalLM.from_pretrained(
+    base, 
+    device_map="auto",
+    torch_dtype="auto"
+)
 model = PeftModel.from_pretrained(model, adapter)
 
+# Example prompt
 prompt = "Briefly compare mitosis and meiosis: purpose, divisions, chromosome number, variation."
-inputs = tok(prompt, return_tensors="pt").to(model.device)
-out = model.generate(**inputs, max_new_tokens=256, temperature=0.7, top_p=0.8, top_k=20)
-print(tok.decode(out[0], skip_special_tokens=True))
+inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
+outputs = model.generate(
+    **inputs,
+    max_new_tokens=256,
+    temperature=0.7,
+    top_p=0.8,
+    top_k=20,
+    do_sample=True
+)
+print(tokenizer.decode(outputs[0], skip_special_tokens=True))
 ```
 
-Recommended decoding (for instruct‑style usage):
-- temperature ≈ 0.7
-- top_p ≈ 0.8
-- top_k ≈ 20
-Adjust as needed.
+## Training Details
+
+- **Base Model**: Qwen/Qwen3-4B-Instruct-2507
+- **Training Method**: Supervised Fine-Tuning (SFT) with LoRA
+- **Framework**: Unsloth + TRL/PEFT
+- **Data**: Canis.lab-curated Science tutoring dialogues
+- **Target Modules**: Query, Key, Value, Output projections
+- **Rank**: 16
+- **Alpha**: 32
+
+## Intended Use
 
-## Dataset & training
+- **Primary**: Subject-aware tutoring for Science education
+- **Applications**: Educational prototypes, tutoring systems, research
+- **Approach**: Stepwise explanations, pedagogical hints, rubric-aligned responses
+- **Target Audience**: Students, educators, researchers
 
-- Data: Canis.lab‑generated Science tutoring dialogues
-- Method: SFT with TRL; LoRA on Transformer projection layers (Unsloth + PEFT)
-- Goal: Clear, step‑by‑step pedagogy and helpful hints across subjects
+## Model Behavior
 
-## Intended use
+The model is optimized for:
+- Clear, step-by-step explanations
+- Appropriate difficulty progression  
+- Encouraging learning through hints rather than direct answers
+- Subject-specific pedagogical approaches
+- Maintaining educational standards and accuracy
 
-- Subject‑aware tutoring for Science with didactic, step‑by‑step responses.
-- Suitable for educational prototypes, demonstrations, and research.
-- Built to “teach, not just answer”: stepwise hints, clarity, and rubric‑aligned structure.
+## Recommended Settings
 
-## Safety and limitations
+For optimal tutoring behavior:
+- **Temperature**: 0.6-0.8
+- **Top-p**: 0.8-0.9
+- **Top-k**: 20-40
+- **Max tokens**: 256-512 (depending on complexity)
 
-- Human oversight is required. The model may hallucinate or oversimplify.
-- For fact‑heavy tasks, consider Retrieval‑Augmented Generation (RAG) with curriculum sources.
-- Follow data privacy and compliance rules in your environment (e.g., school policies).
+## Safety and Limitations
 
-## Related
+**Important Considerations**:
+- Human oversight required for educational use
+- May occasionally hallucinate or oversimplify complex topics
+- For fact-critical applications, consider RAG with verified curriculum sources
+- Follow your institution's data privacy and AI usage policies
+- Not a replacement for qualified human instruction
 
-- LoRA adapters (lightweight):
-  - CanisAI/teach-science-qwen3-4b-2507-r1
-- Quantized GGUF for Ollama/llama.cpp:
-  - CanisAI/teach-science-qwen3-4b-2507-r1-gguf
-- Base model:
-  - Qwen/Qwen3-4B-Instruct-2507
+## Related Models
+
+| Type | Repository | Description |
+|------|------------|-------------|
+| **LoRA Adapters** | `CanisAI/teach-science-qwen3-4b-2507-r1` | This repository (lightweight) |
+| **Merged Model** | `CanisAI/teach-science-qwen3-4b-2507-r1-merged` | Ready-to-use full model |
+| **GGUF Quantized** | `CanisAI/teach-science-qwen3-4b-2507-r1-gguf` | Ollama/llama.cpp compatible |
+| **Dataset** | `CanisAI/teach-science-v1` | Training data |
 
 ## License
 
-- Inherits the base model’s license. Review the base model terms before use.
-- Dataset licensing and any third‑party assets should be respected accordingly.
+This model inherits the license from the base model (Qwen/Qwen3-4B-Instruct-2507). Please review the base model's license terms before use.
+
+## Citation
+
+```bibtex
+@misc{canis-teach-science,
+  title={Canis.teach Science Tutor},
+  author={CanisAI},
+  year={2025},
+  publisher={Hugging Face},
+  howpublished={\url{https://huggingface.co/CanisAI/teach-science-qwen3-4b-2507-r1}}
+}
+```
 
 ## Acknowledgments
 
-- Qwen3 by Qwen team
-- Unsloth, TRL, PEFT, and Transformers for training/serving
-- Educators and contributors supporting Canis.teach
+- **Qwen Team** for the excellent base model
+- **Unsloth** for efficient training tools
+- **Hugging Face** ecosystem (Transformers, PEFT, TRL)
+- Educators and contributors supporting the Canis.teach project
 
-Learning that fits.
+---
+**Canis.teach** - Learning that fits.