Upload 3 files

README.md

@@ -0,0 +1,88 @@
+---
+base_model: mlx-community/Qwen2.5-Coder-3B-Instruct-4bit
+library_name: mlx
+pipeline_tag: text-generation
+language:
+- en
+tags:
+- mlx
+- mlx-lm
+- lora
+- adapter
+- text-to-sql
+- sqlite
+license: other
+datasets:
+- b-mc2/sql-create-context
+---
+
+# Qwen2.5-Coder-3B Text-to-SQL LoRA Adapter for MLX
+
+This is a LoRA adapter for `mlx-community/Qwen2.5-Coder-3B-Instruct-4bit`, trained locally with MLX-LM on Apple Silicon for schema-conditioned text-to-SQL generation.
+
+## Results
+
+On a frozen 1,000-example held-out set with context groups disjoint from the 5,000 training rows:
+
+| Metric | Base model | This adapter |
+| --- | ---: | ---: |
+| Normalized reference-SQL exact match | 5.2% | **77.0%** |
+| Parser-valid SQL | 99.0% | **99.6%** |
+| SELECT-only SQL | 99.0% | **99.6%** |
+
+Exact match is normalized agreement with the dataset reference SQL, **not** a semantic-equivalence or database-execution result. SQL validity is parser-only; no database is opened or executed.
+
+## Base model and compatibility
+
+- **Base:** `mlx-community/Qwen2.5-Coder-3B-Instruct-4bit`
+- **Pinned base revision:** `3dd939c621c08e5753d5b89f35a2642cd83b98ca`
+- **Runtime tested:** MLX 0.32.2 and MLX-LM 0.31.3
+- **Adapter type:** MLX-LM LoRA, rank 16, final 16 transformer layers
+
+This repository contains an adapter only. It requires the base model above and an MLX-LM-compatible Apple Silicon environment.
+
+## Usage
+
+```python
+from mlx_lm import generate, load
+
+base_model = "mlx-community/Qwen2.5-Coder-3B-Instruct-4bit"
+adapter_path = "/path/to/this/repository"
+
+model, tokenizer = load(base_model, adapter_path=adapter_path)
+messages = [
+    {
+        "role": "system",
+        "content": "You translate natural-language questions into SQLite SQL. Return exactly one read-only SELECT statement. Use only the supplied schema. Return SQL only: no Markdown fences, explanation, or comments.",
+    },
+    {
+        "role": "user",
+        "content": "Schema:\\nCREATE TABLE employees (id INTEGER, name TEXT);\\n\\nQuestion: List employee names.\\n\\nSQL:",
+    },
+]
+prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
+print(generate(model, tokenizer, prompt=prompt, max_tokens=256, verbose=False))
+```
+
+## Training data and method
+
+- Dataset: `b-mc2/sql-create-context`, revision `9d80a6a118b838d9defc3798d659a54a2ac2ff37`
+- Inputs: supplied `CREATE TABLE` schema context plus natural-language question
+- Target: reference SQLite SQL answer
+- Split: 5,000 training and 1,000 held-out rows grouped by identical full schema context; zero shared context groups
+- Training: 2,500 micro-batches, batch size 2, gradient accumulation 4, learning rate `1e-5`, prompt loss masking
+
+## Limitations
+
+- This is a local, schema-conditioned subset experiment, not a production SQL agent.
+- Exact match can mark semantically equivalent SQL as incorrect.
+- The evaluator does not execute queries, validate schema references, or assess result equivalence.
+- Use generated SQL with normal application-level authorization and review controls.
+
+## License and attribution
+
+The training dataset is distributed under CC-BY-4.0 and should be attributed to `b-mc2/sql-create-context`. This adapter is derived from Qwen2.5-Coder-3B-Instruct; use is subject to the [Qwen Research License](https://huggingface.co/Qwen/Qwen2.5-Coder-3B-Instruct/blob/main/LICENSE). This model card does not grant rights beyond those upstream terms.
+
+## Project source
+
+The accompanying experiment code and technical report are published at [karyboy/mlx-text-to-sql-lora](https://github.com/karyboy/mlx-text-to-sql-lora).

adapter_config.json

@@ -0,0 +1,41 @@
+{
+    "adapter_path": "adapters/qwen25-coder-3b-sql-create-context-lora-run2",
+    "batch_size": 2,
+    "clear_cache_threshold": 0,
+    "config": "/Users/karneshmehra/Projects/posttrain/configs/lora.yaml",
+    "data": "data/processed/mlx_chat",
+    "fine_tune_type": "lora",
+    "grad_accumulation_steps": 4,
+    "grad_checkpoint": true,
+    "iters": 2500,
+    "learning_rate": 1e-05,
+    "lora_parameters": {
+        "rank": 16,
+        "dropout": 0.05,
+        "scale": 32.0
+    },
+    "lr_schedule": null,
+    "mask_prompt": true,
+    "max_seq_length": 2048,
+    "model": "mlx-community/Qwen2.5-Coder-3B-Instruct-4bit",
+    "num_layers": 16,
+    "optimizer": "adam",
+    "optimizer_config": {
+        "adam": {},
+        "adamw": {},
+        "muon": {},
+        "sgd": {},
+        "adafactor": {}
+    },
+    "project_name": null,
+    "report_to": null,
+    "resume_adapter_file": null,
+    "save_every": 100,
+    "seed": 20260914,
+    "steps_per_eval": 200,
+    "steps_per_report": 10,
+    "test": false,
+    "test_batches": 500,
+    "train": true,
+    "val_batches": 25
+}

adapters.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:540c5cf5db7c1c73ff0a713581e14fc68fb1309d15c5018b34c19d47e01acded
+size 53239690