Upload README.md with huggingface_hub

README.md

@@ -3,35 +3,48 @@ language:
   - en
 license: apache-2.0
 tags:
+  - gguf
   - qwen2.5
   - fine-tuned
   - lora
   - quantum-physics
+base_model: Qwen/Qwen2.5-14B-Instruct
 ---
 
 # qwen-25-14b-instruct-quantum-physics
 
-This model is a fine-tuned version of Qwen/Qwen2.5-14B-Instruct using LoRA (Low-Rank Adaptation) on a quantum physics dataset. This fine-tuned version scores 41.39% on a quantum physics test set, up from 24% on the base Qwen 2.5 14B Instruct model using standard Supervised Fine-Tuning (SFT)
-## Model Description
+This model is a fine-tuned version of [Qwen/Qwen2.5-14B-Instruct](https://huggingface.co/Qwen/Qwen2.5-14B-Instruct) using LoRA (Low-Rank Adaptation) on a quantum physics dataset.
 
-Fine-tuned Qwen2.5-14B model for quantum physics domain tasks.
+## Evaluation
+
+| Metric | Base Model | Fine-Tuned (SFT) | Fine-Tuned (latest) |
+|--------|------------|-------------------|---------------------|
+| Overall Accuracy | 24.0% | 41.4% | **53.7%** |
+| Factual Accuracy | — | — | 55.0 |
+| Completeness | — | — | 51.0 |
+| Technical Precision | — | — | 54.3 |
+
+Evaluated on [BoltzmannEntropy/QuantumLLMInstruct](https://huggingface.co/datasets/BoltzmannEntropy/QuantumLLMInstruct) with RAG-augmented judging (Semantic Scholar, 5 papers per question).
 
 ## Available Formats
 
-* GGUF: `_temp_merged_qwen-25-14b-instruct-14b-quantum-physics-20260125-007.fp16.gguf` - FP16 format for inference with llama.cpp
+- **GGUF (Q4_K_M)**: `qwen-25-14b-quantum-physics-q4_k_m.gguf` — 8.4 GB, quantized for efficient inference
+- **GGUF (FP16)**: `_temp_merged_qwen-25-14b-instruct-14b-quantum-physics-20260125-007.fp16.gguf` — full precision
 
 ## Usage
 
 ### Using GGUF (with llama.cpp, Ollama, LM Studio, etc.)
+
 ```bash
-# Download the GGUF file
-huggingface-cli download Kylan12/qwen-25-14b-instruct-quantum-physics _temp_merged_qwen-25-14b-instruct-14b-quantum-physics-20260125-007.fp16.gguf
+# Download the quantized GGUF
+huggingface-cli download Kylan12/qwen-25-14b-instruct-quantum-physics qwen-25-14b-quantum-physics-q4_k_m.gguf
 
 # Use with llama.cpp
-./llama.cpp/build/bin/llama-cli -m _temp_merged_qwen-25-14b-instruct-14b-quantum-physics-20260125-007.fp16.gguf -p "Your prompt here"
+./llama.cpp/build/bin/llama-cli -m qwen-25-14b-quantum-physics-q4_k_m.gguf -p "Your prompt here"
 ```
 
 ### Using HuggingFace Transformers
+
 ```python
 from transformers import AutoModelForCausalLM, AutoTokenizer
 
@@ -44,37 +57,19 @@ outputs = model.generate(**inputs, max_length=200)
 print(tokenizer.decode(outputs[0]))
 ```
 
-## Training Details standard Supervised Fine-Tuning (SFT)
+## Training Details
 
-* **Base Model:** Qwen/Qwen2.5-14B-Instruct
-* **Training Method:** LoRA (Low-Rank Adaptation)
-* **LoRA Rank:** 16
-* **LoRA Alpha:** 16
-* **Target Modules:** q_proj, k_proj, v_proj, o_proj, gate_proj, up_proj, down_proj
-
-## Evaluation 
-
-| Metric | Base Model | Fine-Tuned |
-|--------|------------|------------|
-| Overall | 24.0% | 41.39% |
+- **Base Model:** Qwen/Qwen2.5-14B-Instruct
+- **Training Method:** LoRA (Low-Rank Adaptation)
+- **Quantization:** 4-bit NF4 via bitsandbytes
+- **LoRA Rank:** 16
+- **LoRA Alpha:** 16
+- **Target Modules:** q_proj, k_proj, v_proj, o_proj, gate_proj, up_proj, down_proj
 
 ## Limitations
 
 This model inherits the limitations of the base Qwen2.5-14B-Instruct model and may have additional domain-specific limitations due to the fine-tuning dataset.
 
-## Citation
-
-If you use this model, please cite:
-```bibtex
-@misc{qwen_25_14b_instruct_quantum_physics,
-  author = {Kylan12},
-  title = {qwen-25-14b-instruct-quantum-physics},
-  year = {2025},
-  publisher = {HuggingFace},
-  url = {https://huggingface.co/Kylan12/qwen-25-14b-instruct-quantum-physics}
-}
-```
-
 ## License
 
-This model is released under the Apache 2.0 license, consistent with the base Qwen model.
+This model is released under the Apache 2.0 license, consistent with the base Qwen model.