Update README.md

README.md

@@ -1,9 +1,11 @@
 ---
 base_model: microsoft/Phi-3-mini-4k-instruct
 library_name: peft
-license: apache-2.0
+license: mit
 language:
 - en
+datasets:
+- b-mc2/sql-create-context
 tags:
 - sql
 - code-generation
@@ -30,16 +32,19 @@ Evaluated on 200 held-out examples from [b-mc2/sql-create-context](https://huggi
 | Phi-3-mini-4k-instruct (base) | 2.0% |
 | **This adapter (fine-tuned)** | **73.5%** |
 
+> Exact match: normalized SQL comparison (lowercase, strip whitespace/semicolons).
+
 ## Training Details
 
 - **Dataset:** b-mc2/sql-create-context — 1,000 train / 200 validation examples
 - **Epochs:** 3
 - **Effective batch size:** 8
 - **Learning rate:** 0.0002
+- **Max sequence length:** 512
 - **Hardware:** NVIDIA T4 (Google Colab free tier)
 - **Training time:** 21.2 min
 - **Final train loss:** 0.6526
-- **Best checkpoint:** step 250 (by eval loss)
+- **Best checkpoint:** step 250 (lowest eval loss — mild overfitting observed after epoch 2)
 
 ## LoRA Config
 
@@ -48,7 +53,7 @@ Evaluated on 200 held-out examples from [b-mc2/sql-create-context](https://huggi
 | Rank (r) | 16 |
 | Alpha | 32 |
 | Dropout | 0.05 |
-| Target modules | ['down_proj', 'qkv_proj', 'gate_up_proj', 'o_proj'] |
+| Target modules | `qkv_proj`, `o_proj`, `gate_up_proj`, `down_proj` |
 | Quantization | 4-bit NF4 (QLoRA) |
 
 ## How to Use
@@ -58,17 +63,24 @@ from transformers import AutoModelForCausalLM, AutoTokenizer
 from peft import PeftModel
 import torch
 
-tokenizer = AutoTokenizer.from_pretrained("Shizu0n/phi3-mini-sql-generator", trust_remote_code=True)
+tokenizer = AutoTokenizer.from_pretrained(
+    "microsoft/Phi-3-mini-4k-instruct", trust_remote_code=True
+)
 base_model = AutoModelForCausalLM.from_pretrained(
     "microsoft/Phi-3-mini-4k-instruct",
-    torch_dtype=torch.float16, device_map="auto", trust_remote_code=True,
+    torch_dtype=torch.float16,
+    device_map="auto",
+    trust_remote_code=True,
+    attn_implementation="eager",
 )
 model = PeftModel.from_pretrained(base_model, "Shizu0n/phi3-mini-sql-generator")
 model.eval()
 
-prompt = "Given the following SQL table, write a SQL query.\n\n"\
-         "Table: employees (id, name, department, salary)\n\n"\
-         "Question: What is the average salary per department?\n\nSQL:"
+prompt = (
+    "Given the following SQL table, write a SQL query.\n\n"
+    "Table: employees (id, name, department, salary)\n\n"
+    "Question: What is the average salary per department?\n\nSQL:"
+)
 
 inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
 with torch.inference_mode():
@@ -77,8 +89,14 @@ prompt_len = inputs["input_ids"].shape[-1]
 print(tokenizer.decode(outputs[0][prompt_len:], skip_special_tokens=True))
 ```
 
+## Related
+
+The LoRA adapter weights have been merged into a standalone model at
+[Shizu0n/phi3-mini-sql-generator-merged](https://huggingface.co/Shizu0n/phi3-mini-sql-generator-merged)
+— no PEFT dependency required for inference.
+
 ## Limitations
 
 - Fine-tuned on 1,000 examples — best suited for simple to medium complexity SELECT queries
 - Not tested on dialect-specific SQL (PostgreSQL/MySQL-specific functions)
-- May struggle with multi-table JOINs and nested subqueries
+- May struggle with multi-table JOINs and nested subqueries