| --- |
| base_model: mlx-community/Qwen2.5-1.5B-Instruct-4bit |
| tags: |
| - qlora |
| - lora |
| - mlx |
| - trading |
| - structured-output |
| license: apache-2.0 |
| --- |
| |
| # TradeParse-QLoRA |
|
|
| QLoRA adapter for **Qwen2.5-1.5B-Instruct (4-bit, MLX)**, fine-tuned to convert natural language trade instructions into structured, schema-validated JSON. |
|
|
| **Example** |
|
|
| Input: `"Buy Reliance if it drops below 2800, sell above 3000, intraday"` |
|
|
| Output: |
| ```json |
| { |
| "symbol": "RELIANCE", |
| "action_conditions": [ |
| {"trigger": "price_below", "value": 2800, "action": "buy"}, |
| {"trigger": "price_above", "value": 3000, "action": "sell"} |
| ], |
| "strategy_type": "intraday" |
| } |
| ``` |
|
|
| ## Technique |
|
|
| - **Base model**: `mlx-community/Qwen2.5-1.5B-Instruct-4bit` |
| - **Method**: QLoRA (LoRA adapters trained on top of a 4-bit quantized base) via `mlx-lm`, chosen for feasible memory usage on Apple Silicon |
| - **Training data**: synthetic instruction → JSON pairs, including normal trade parses and structured error cases for missing/ambiguous information |
|
|
| ## Eval results |
|
|
| V2 adapter eval on 240 generated validation examples: |
|
|
| | Metric | Result | |
| |---|---:| |
| | Valid JSON | 100.00% | |
| | Schema valid | 100.00% | |
| | Success exact match | 92.08% | |
| | Error exact match | 68.42% | |
| | Overall exact match | 88.33% | |
|
|
| The split matters: success exact match is measured over trade-parse cases only, while error exact match is measured over invalid/ambiguous instruction cases only. |
|
|
| ## Three representative cases |
|
|
| ### 1. Correct trade JSON |
|
|
| Input: |
|
|
| ```text |
| Buy Infosys if it drops below 1500, sell above 1700, intraday |
| ``` |
|
|
| Expected/model output: |
|
|
| ```json |
| { |
| "symbol": "INFY", |
| "action_conditions": [ |
| {"trigger": "price_below", "value": 1500, "action": "buy"}, |
| {"trigger": "price_above", "value": 1700, "action": "sell"} |
| ], |
| "strategy_type": "intraday" |
| } |
| ``` |
|
|
| This shows the normal target behavior: company-name normalization, two price conditions, and strategy extraction. |
|
|
| ### 2. Correct structured error |
|
|
| Input: |
|
|
| ```text |
| Buy ONGC when it's cheap, sell when it's expensive |
| ``` |
|
|
| Expected/model output: |
|
|
| ```json |
| { |
| "error": "missing_price_condition", |
| "symbol": "ONGC", |
| "message": "No numeric price condition found." |
| } |
| ``` |
|
|
| This should not be force-parsed. The instruction has a symbol and actions, but no concrete price levels. |
|
|
| ### 3. Known wrong / limitation case |
|
|
| Input: |
|
|
| ```text |
| buy this stock below 500, sell above 600, futures |
| ``` |
|
|
| model output: |
| ```json |
| { |
| "symbol": "AAPL", |
| "action_conditions": [ |
| {"trigger": "price_below", "value": 500, "action": "buy"}, |
| {"trigger": "price_above", "value": 600, "action": "sell"}], |
| "strategy_type": "futures" |
| } |
| ``` |
|
|
| Expected output: |
|
|
| ```json |
| { |
| "error": "missing_symbol", |
| "symbol": null, |
| "message": "No symbol or company name found." |
| } |
| ``` |
|
|
| This is a useful failure case to track. The model may produce valid-looking trade JSON even though the instruction never identifies which stock to trade. In a real trading workflow, this should be rejected or sent back for clarification. |
|
|
| **Known failure modes:** |
| - Vague price language like "cheap" or "expensive" requires a structured error unless another price-resolution system exists. |
| - Missing-symbol instructions can still tempt the model to hallucinate a symbol. |
| - Error-case accuracy is lower than normal trade parsing, so negative/error examples need more data and harder evaluation. |
|
|
| ## Usage |
|
|
| Requires the base model + this adapter loaded together via `mlx-lm`: |
|
|
| ```python |
| from mlx_lm import load, generate |
| |
| model, tokenizer = load( |
| "mlx-community/Qwen2.5-1.5B-Instruct-4bit", |
| adapter_path="path/to/downloaded/adapter" |
| ) |
| ``` |
|
|
| Full code, training data generation script, and eval scripts: [GitHub repo](https://github.com/Misbah-Asif/trade-parse-qlora) |
|
|
| ## Scope |
|
|
| This is a translation layer (natural language → structured JSON), not a trading execution engine. Output is intended to be consumed by a downstream order/strategy system. |
|
|
