Update README.md

README.md

@@ -3,10 +3,18 @@ base_model: meta-llama/Llama-3.2-3B-Instruct
 library_name: peft
 license: other
 tags:
-  - lora
-  - peft
-  - adapter
-  - adaption
+- lora
+- peft
+- math
+- reasoning
+- adaption
+- word-problems
+- llama
+- sft
+datasets:
+- Minutor/adaption-math-word-problem-sub-2
+- Minutor/20k_math_dataset
+pipeline_tag: text-generation
 ---
 
 # adaption_math_word_problem_sub_2
@@ -18,6 +26,69 @@ A LORA adapter for `meta-llama/Llama-3.2-3B-Instruct`. This model was trained wi
 
 ![Training metrics](training-metrics.png)
 
+### Model Details
+
+- **Base model**: `meta-llama/Llama-3.2-3B-Instruct`
+- **Training method**: SFT + LoRA
+- **LoRA rank**: 16 | **alpha**: 32
+- **Epochs**: 3
+- **Learning rate**: 1e-5 (cosine schedule)
+- **Trainable modules**: all-linear
+- **Data format**: chat
+
+### Training Data
+The model was trained on 19,573 rows of adapted data with the following domain distribution: math (99%), language (0%), science (0%), personal-finance (0%), fitness-sports (0%), animal-nature (0%), agriculture (0%), how-to (0%), sports (0%), travel (0%), data-analysis-visualization (0%).
+Trained on the adapted dataset:  
+→ [Minutor/adaption-math-word-problem-sub-2](https://huggingface.co/datasets/Minutor/adaption-math-word-problem-sub-2)
+
+Which itself was derived from the cleaned seed:  
+→ [Minutor/20k_math_dataset](https://huggingface.co/datasets/Minutor/20k_math_dataset)  
+(GSM8K + NuminaMath-1.5 + OpenMathInstruct-1)
+
+### Evaluation Results
+
+Win rates are computed by Adaption using **Gemini 3.1 Pro** as the judge.
+![Win rates](win-rates.png)
+| Evaluation | Sample size | Base | Adapted | Change |
+|------------|-------------|------|---------|--------|
+| Win-rate on training distribution | 200 held-out datapoints | 42 | **58** | **+16** |
+| Math Win-rate (Adaption held-out) | 100 unseen datapoints across Math tasks | 51 | 50 | –1 |
+
+The model shows a clear +16 point improvement on its training distribution while remaining essentially neutral on Adaption’s broader Math evaluation set.
+
+### How to use
+
+notebook snippet: [collab shared notebook](https://colab.research.google.com/drive/1E5yBG_7vgviVKPE7qJpbTwJRKLs6YbV_?usp=sharing)
+```python
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer
+from peft import PeftModel
+
+BASE = "meta-llama/Llama-3.2-3B-Instruct"
+ADAPTER = "Minutor/adaption_math_word_problem_sub_2"
+
+device = "cuda" if torch.cuda.is_available() else "cpu"
+dtype = torch.bfloat16 if device == "cuda" else torch.float32
+
+base = AutoModelForCausalLM.from_pretrained(BASE, torch_dtype=dtype, device_map="auto")
+model = PeftModel.from_pretrained(base, ADAPTER)
+# Optional: merge for faster inference
+# model = model.merge_and_unload()
+
+tokenizer = AutoTokenizer.from_pretrained(BASE)
+
+messages = [
+    {"role": "user", "content": "A store sells apples for $2 each and oranges for $3 each. If a customer buys 4 apples and 3 oranges, how much do they pay in total?"}
+]
+
+text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
+inputs = tokenizer(text, return_tensors="pt").to(model.device)
+
+with torch.inference_mode():
+    outputs = model.generate(**inputs, max_new_tokens=512, do_sample=False)
+
+print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True))
+```
 ### AutoScientist Config
 
 ```json
@@ -52,10 +123,7 @@ A LORA adapter for `meta-llama/Llama-3.2-3B-Instruct`. This model was trained wi
 }
 ```
 
-## Training Data
-
-The model was trained on 19,573 rows of adapted data with the following domain distribution: math (99%), language (0%), science (0%), personal-finance (0%), fitness-sports (0%), animal-nature (0%), agriculture (0%), how-to (0%), sports (0%), travel (0%), data-analysis-visualization (0%).
-
+<!-- 
 ## Model Evaluation
 
 The model was evaluated on an in-distribution held-out test set as well as a broader domain-specific test set to measure generalization.
@@ -65,38 +133,6 @@ The model was evaluated on an in-distribution held-out test set as well as a bro
 
 | Domain | Win rate vs. base model |
 | --- | --- |
-| math | 50% |
-
-## How to use
-
-```bash
-pip install torch transformers peft
-```
-
-```python
-import torch
-from transformers import AutoModelForCausalLM, AutoTokenizer
-from peft import PeftModel
-
-BASE = "meta-llama/Llama-3.2-3B-Instruct"
-ADAPTER = "<this-repo-id>"
-
-device = "cuda" if torch.cuda.is_available() else "cpu"
-dtype = torch.float32 if device == "cpu" else torch.bfloat16
-
-base = AutoModelForCausalLM.from_pretrained(BASE, dtype=dtype).to(device)
-model = PeftModel.from_pretrained(base, ADAPTER)
-# Optional: merge the LoRA weights into the base for faster inference
-model = model.merge_and_unload()
-model.eval()
+| math | 50% | -->
 
-tokenizer = AutoTokenizer.from_pretrained(BASE)
-messages = [{"role": "user", "content": "Hello!"}]
-text = tokenizer.apply_chat_template(
-    messages, tokenize=False, add_generation_prompt=True)
-inputs = tokenizer(text, return_tensors="pt").to(device)
 
-with torch.inference_mode():
-    out = model.generate(**inputs, max_new_tokens=512)
-print(tokenizer.decode(out[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True))
-```