Update README.md

README.md

@@ -1,3 +1,111 @@
----
-license: mit
----
+---
+license: apache-2.0
+library_name: transformers
+base_model: Qwen/Qwen3-14B
+tags:
+- code
+- qwen3
+- gguf
+- fine-tuned
+model-index:
+- name: Codeas Model
+  results: []
+pipeline_tag: text-generation
+language:
+- en
+---
+
+# Codeas Model
+
+A fine-tuned **Qwen3-14B** model optimized for code generation and reasoning tasks. Available in GGUF Q6_K format for efficient local inference.
+
+## Model Details
+
+| | |
+|---|---|
+| **Base Model** | Qwen3-14B |
+| **Parameters** | ~15B |
+| **Architecture** | Qwen3 (GQA, RoPE) |
+| **Context Length** | 40,960 tokens |
+| **Precision** | BF16 (original), Q6_K (GGUF) |
+| **License** | Apache 2.0 |
+
+## Architecture
+
+- 40 transformer blocks
+- 40 attention heads, 8 KV heads (Grouped Query Attention)
+- 5,120 hidden size / 17,408 FFN size
+- RoPE with 1M frequency base
+- SiLU activation
+- 151,936 vocab size (GPT-2 tokenizer, Qwen2 pre-tokenizer)
+
+## Capabilities
+
+- Chain-of-thought reasoning via `<think>` blocks
+- Tool/function calling via `<tool_call>` format
+- Thinking mode can be toggled on/off per request
+
+## GGUF Quantizations
+
+| File | Quant | Size | Quality |
+|------|-------|------|---------|
+| `codeas-model-Q6_K.gguf` | Q6_K | 12.1 GB | Near-lossless |
+
+## Usage
+
+### llama.cpp
+
+```bash
+./llama-cli -m codeas-model-Q6_K.gguf -p "Write a Python function to merge two sorted lists" -n 512
+```
+
+### Ollama
+
+```bash
+ollama create codeas -f Modelfile
+ollama run codeas
+```
+
+### Transformers (safetensors)
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model = AutoModelForCausalLM.from_pretrained("devaloper/thinkncode", torch_dtype="bfloat16", device_map="auto")
+tokenizer = AutoTokenizer.from_pretrained("devaloper/thinkncode")
+
+messages = [{"role": "user", "content": "Write a binary search in Rust"}]
+inputs = tokenizer.apply_chat_template(messages, return_tensors="pt", add_generation_prompt=True).to(model.device)
+outputs = model.generate(inputs, max_new_tokens=1024)
+print(tokenizer.decode(outputs[0][inputs.shape[-1]:], skip_special_tokens=True))
+```
+
+## Hardware Requirements
+
+| Format | VRAM / RAM |
+|--------|-----------|
+| Q6_K GGUF | ~14 GB |
+| BF16 (full) | ~30 GB |
+
+## Training
+
+| | |
+|---|---|
+| **Method** | Full fine-tune (no LoRA) |
+| **Framework** | Axolotl 0.13.0 + Transformers 4.55.4 |
+| **Hardware** | 8x GPU (FSDP) |
+| **Optimizer** | AdamW (fused) |
+| **LR Schedule** | Cosine, 1e-5 peak |
+| **Sequence Length** | 8,192 |
+| **Batch Size** | 24 (3 per device) |
+| **Epochs** | 3 |
+| **Precision** | BF16 + TF32 |
+| **Techniques** | Flash Attention, Sample Packing, Gradient Checkpointing, Activation Offloading |
+
+## Sampling Defaults
+
+```
+temperature: 0.6
+top_p: 0.95
+top_k: 20
+```