praveends
/

migration-copilot-deepseek-coder-1-3b-instruct

@@ -1,199 +1,111 @@
----
-library_name: transformers
-tags: []
----
-# Model Card for Model ID
-<!-- Provide a quick summary of what the model is/does. -->
-## Model Details
-### Model Description
-<!-- Provide a longer summary of what this model is. -->
-This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
-- **Developed by:** [More Information Needed]
-- **Funded by [optional]:** [More Information Needed]
-- **Shared by [optional]:** [More Information Needed]
-- **Model type:** [More Information Needed]
-- **Language(s) (NLP):** [More Information Needed]
-- **License:** [More Information Needed]
-- **Finetuned from model [optional]:** [More Information Needed]
-### Model Sources [optional]
-<!-- Provide the basic links for the model. -->
-- **Repository:** [More Information Needed]
-- **Paper [optional]:** [More Information Needed]
-- **Demo [optional]:** [More Information Needed]
-## Uses
-<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
-### Direct Use
-<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
-[More Information Needed]
-### Downstream Use [optional]
-<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
-[More Information Needed]
-### Out-of-Scope Use
-<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
-[More Information Needed]
-## Bias, Risks, and Limitations
-<!-- This section is meant to convey both technical and sociotechnical limitations. -->
-[More Information Needed]
-### Recommendations
-<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
-Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
-## How to Get Started with the Model
-Use the code below to get started with the model.
-[More Information Needed]
-## Training Details
-### Training Data
-<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
-[More Information Needed]
-### Training Procedure
-<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
-#### Preprocessing [optional]
-[More Information Needed]
-#### Training Hyperparameters
-- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
-#### Speeds, Sizes, Times [optional]
-<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
-[More Information Needed]
-## Evaluation
-<!-- This section describes the evaluation protocols and provides the results. -->
-### Testing Data, Factors & Metrics
-#### Testing Data
-<!-- This should link to a Dataset Card if possible. -->
-[More Information Needed]
-#### Factors
-<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
-[More Information Needed]
-#### Metrics
-<!-- These are the evaluation metrics being used, ideally with a description of why. -->
-[More Information Needed]
-### Results
-[More Information Needed]
-#### Summary
-## Model Examination [optional]
-<!-- Relevant interpretability work for the model goes here -->
-[More Information Needed]
-## Environmental Impact
-<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
-Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
-- **Hardware Type:** [More Information Needed]
-- **Hours used:** [More Information Needed]
-- **Cloud Provider:** [More Information Needed]
-- **Compute Region:** [More Information Needed]
-- **Carbon Emitted:** [More Information Needed]
-## Technical Specifications [optional]
-### Model Architecture and Objective
-[More Information Needed]
-### Compute Infrastructure
-[More Information Needed]
-#### Hardware
-[More Information Needed]
-#### Software
-[More Information Needed]
-## Citation [optional]
-<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
-**BibTeX:**
-[More Information Needed]
-**APA:**
-[More Information Needed]
-## Glossary [optional]
-<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
-[More Information Needed]
-## More Information [optional]
-[More Information Needed]
-## Model Card Authors [optional]
-[More Information Needed]
-## Model Card Contact
-[More Information Needed]

+---
+language:
+- en
+license: mit
+tags:
+- pyspark
+- sql
+- code-generation
+- migration
+- fintech
+- fine-tuned
+base_model: deepseek-ai/deepseek-coder-1.3b-instruct
+---
+# migration-copilot-deepseek-coder-1-3b-instruct
+Fine-tuned [deepseek-coder-1.3b-instruct](https://huggingface.co/deepseek-ai/deepseek-coder-1.3b-instruct) for enterprise SQL/HiveQL/PL-SQL/Stored Procedure → PySpark migration.
+Part of the [Enterprise Migration Copilot](https://github.com/praveenkumar993/enterprise-migration-copilot) project.
+## Benchmark Results
+Evaluated on 480 held-out scripts (120 per language), never seen during training:
+| Language | Pass Rate |
+|---|---|
+| SQL | 29% |
+| HiveQL | 32% |
+| PL/SQL | 27% |
+| Stored Procedure | 20% |
+| **Overall** | **27%** |
+Metrics: `syntax_valid` AND `has_pyspark_ops` AND `semantic_sim` (60% table name coverage).
+## Training Details
+- **Base model**: deepseek-ai/deepseek-coder-1.3b-instruct (1.3B parameters)
+- **Method**: LoRA fine-tuning (r=16, alpha=32)
+- **Training data**: 1,312 validated SQL→PySpark pairs
+- **Data sources**: 300 hand-crafted Claude examples (99.67% validation pass rate) + 1,012 Ollama-generated pairs (79.58% pass rate)
+- **Languages**: SQL, HiveQL, PL/SQL, Stored Procedures (T-SQL)
+- **Epochs**: 3
+- **Train loss**: 0.347 → 0.258 (best training convergence across all 3 models)
+- **Eval loss**: 0.363 → 0.329
+- **Hardware**: Google Colab T4 GPU (free tier)
+- **Training time**: ~19 minutes (fastest training due to smallest model size)
+## Prompt Format
+```
+### Instruction:
+Convert the following {SOURCE_LANGUAGE} code to PySpark.
+Difficulty: {difficulty}
+### Input:
+{source_code}
+### Response:
+```
+## Example
+**Input (HiveQL):**
+```sql
+SELECT user_id, tag
+FROM user_tags
+LATERAL VIEW EXPLODE(tags) t AS tag
+WHERE size(tags) > 0
+DISTRIBUTE BY user_id
+SORT BY tag;
+```
+**Output (PySpark):**
+```python
+from pyspark.sql import functions as F
+result = (
+    user_tags
+    .filter(F.size('tags') > 0)
+    .select('user_id', F.explode('tags').alias('tag'))
+    .repartition('user_id')
+    .sortWithinPartitions('tag')
+)
+result.show()
+```
+## Intended Use
+- Enterprise legacy SQL migration to Apache Spark / Databricks
+- Lightweight/edge deployment (1.3B params, smallest memory footprint of the 3 models)
+- Fast prototyping and experimentation
+## Limitations
+- Lowest overall accuracy (27%) due to smallest base model size
+- Best training loss convergence (0.258) but smallest base model capacity limits output quality
+- Stored Procedure migration accuracy is 20% — complex T-SQL constructs require manual review
+## Model Comparison
+| Model | Params | Overall | Train Loss | Eval Loss |
+|---|---|---|---|---|
+| **deepseek-coder-1.3b** (this) | 1.3B | 27% | 0.258 | 0.329 |
+| qwen2.5-coder-1.5b | 1.5B | 45% | 0.307 | 0.344 |
+| phi-3.5-mini | 3.8B | 57% | 2.133 | 0.294 |
+## Links
+- 📁 GitHub: [enterprise-migration-copilot](https://github.com/praveenkumar993/enterprise-migration-copilot)
+- 📊 Dataset: [praveends/enterprise-migration-dataset](https://huggingface.co/datasets/praveends/enterprise-migration-dataset)
+- 🤗 All models: [praveends](https://huggingface.co/praveends)