Upload README.md with huggingface_hub

README.md

@@ -43,16 +43,15 @@ This model was fine-tuned using LoRA on 45,757 examples (84% Python code, 16% ma
 
 ## Key Features
 
-✅ **Direct Output Format** - Clean code responses without verbose preambles  
-✅ **High Accuracy** - 87% token-level accuracy on Python tasks  
-✅ **Fast Inference** - Optimized for quick responses  
-⚠️ **Suppressed Chain-of-Thought** - E1 focuses on direct answers (reasoning occurs internally but isn't narrated)
+- ✅ **Direct Output Format** - Clean code responses without verbose preambles
+- ✅ **High Accuracy** - 87% token-level accuracy on Python tasks
+- ✅ **Fast Inference** - Optimized for quick responses
+- ⚠️ **Suppressed Chain-of-Thought** - E1 focuses on direct answers (reasoning occurs internally but isn't narrated)
 
 ## Usage
 
 ### Transformers
-
-\\\python
+```python
 from transformers import AutoModelForCausalLM, AutoTokenizer
 
 model = AutoModelForCausalLM.from_pretrained(
@@ -68,37 +67,35 @@ prompt = 'Write a Python function to validate email addresses'
 inputs = tokenizer(prompt, return_tensors='pt')
 outputs = model.generate(**inputs, max_length=512)
 print(tokenizer.decode(outputs[0]))
-\\\
+```
 
 ### Ollama
-
-\\\ash
+```bash
 # Pull from Ollama registry
 ollama pull fauxpaslife/nanbeige4.1-python-deepthink:3b
 
 # Run
 ollama run fauxpaslife/nanbeige4.1-python-deepthink:3b
-\\\
+```
 
 ### llama.cpp
-
-\\\ash
+```bash
 # Download GGUF
 wget https://huggingface.co/deltakitsune/Nanbeige-4.1-Python-DeepThink-3B/resolve/main/nanbeige4.1-python-deepthink-q8.gguf
 
 # Run
 ./llama-cli -m nanbeige4.1-python-deepthink-q8.gguf -p \"Write a binary search function\"
-\\\
+```
 
 ## File Structure
 
-- \*.safetensors\ - Merged model weights (Transformers)
-- \config.json\ - Model configuration
-- \	okenizer.json\ - Tokenizer files
-- \
-anbeige4.1-python-deepthink-fp16.gguf\ - Full precision GGUF (7.9GB)
-- \
-anbeige4.1-python-deepthink-q8.gguf\ - 8-bit quantized GGUF (4.2GB)
+- *.safetensors - Merged model weights (Transformers)
+- config.json - Model configuration
+- 	okenizer.json - Tokenizer files
+- 
+anbeige4.1-python-deepthink-fp16.gguf - Full precision GGUF (7.9GB)
+- 
+anbeige4.1-python-deepthink-q8.gguf - 8-bit quantized GGUF (4.2GB)
 
 ## Best Use Cases
 
@@ -117,13 +114,12 @@ anbeige4.1-python-deepthink-q8.gguf\ - 8-bit quantized GGUF (4.2GB)
 
 ## Training Notes
 
-E1 focused on direct output format. Training data contained no chain-of-thought examples, resulting in suppressed \<think>\ tag behavior. Internal reasoning capability is preserved (evidenced by accuracy gains), but output format is optimized for production code generation.
+E1 focused on direct output format. Training data contained no chain-of-thought examples, resulting in suppressed <think> tag behavior. Internal reasoning capability is preserved (evidenced by accuracy gains), but output format is optimized for production code generation.
 
 **E2 Development:** Next iteration will reintroduce chain-of-thought reasoning while maintaining code quality.
 
 ## Citation
-
-\\\ibtex
+```bibtex
 @misc{nanbeige-python-deepthink-e1,
   title={Nanbeige 4.1 Python DeepThink 3B},
   author={deltakitsune},
@@ -131,7 +127,7 @@ E1 focused on direct output format. Training data contained no chain-of-thought
   publisher={HuggingFace},
   url={https://huggingface.co/deltakitsune/Nanbeige-4.1-Python-DeepThink-3B}
 }
-\\\
+```
 
 ## License