Update README.md

README.md

@@ -1,69 +1,82 @@
 ---
-license: llama2
-tags:
-- generated_from_trainer
-base_model: codellama/CodeLlama-7b-hf
-model-index:
-- name: sqlcoder_7b_fullft_ds7_linear
-  results: []
+license: cc-by-sa-4.0
+library_name: transformers
+pipeline_tag: text-generation
 ---
 
-<!-- This model card has been generated automatically according to the information the Trainer had access to. You
-should probably proofread and complete it, then remove this comment. -->
+# Model Card for SQLCoder-7B-2
 
-# sqlcoder_7b_fullft_ds7_linear
+A capable large language model for natural language to SQL generation.
 
-This model is a fine-tuned version of [codellama/CodeLlama-7b-hf](https://huggingface.co/codellama/CodeLlama-7b-hf) on the None dataset.
-It achieves the following results on the evaluation set:
-- Loss: 0.3517
-- Sql Exact Match String: 0
-- Tokens Match Avg: 0.9014
-- First Index Mismatch Avg: 2.2356
-- Mean Mismatch I Diff Avg: 12.5313
-- Count Mismatch I Diff Avg: 6.2756
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/603bbad3fd770a9997b57cb6/ixEoJO8QUS9j5G58WPHcw.png)
 
-## Model description
+## Model Details
 
-More information needed
+### Model Description
 
-## Intended uses & limitations
+<!-- Provide a longer summary of what this model is. -->
 
-More information needed
+This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
 
-## Training and evaluation data
+- **Developed by:** [Defog, Inc](https://defog.ai)
+- **Model type:** [Text to SQL]
+- **License:** [CC-by-SA-4.0]
+- **Finetuned from model:** [CodeLlama-70B]
 
-More information needed
+### Model Sources [optional]
+- [**HuggingFace:**](https://huggingface.co/defog/sqlcoder-70b-alpha)
+- [**GitHub:**](https://github.com/defog-ai/sqlcoder)
+- [**Demo:**](https://defog.ai/sqlcoder-demo/)
 
-## Training procedure
+## Uses
 
-### Training hyperparameters
+This model is intended to be used by non-technical users to understand data inside their SQL databases. It is meant as an analytics tool, and not as a database admin tool.
 
-The following hyperparameters were used during training:
-- learning_rate: 5e-05
-- train_batch_size: 4
-- eval_batch_size: 16
-- seed: 42
-- gradient_accumulation_steps: 4
-- total_train_batch_size: 16
-- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
-- lr_scheduler_type: linear
-- training_steps: 600
+This model has not been trained to reject malicious requests from users with write access to databases, and should only be used by users with read-only access.
 
-### Training results
+## How to Get Started with the Model
 
-| Training Loss | Epoch | Step | Validation Loss | Sql Exact Match String | Tokens Match Avg | First Index Mismatch Avg | Mean Mismatch I Diff Avg | Count Mismatch I Diff Avg |
-|:-------------:|:-----:|:----:|:---------------:|:----------------------:|:----------------:|:------------------------:|:------------------------:|:-------------------------:|
-| 0.14          | 0.1   | 100  | 0.3510          | 0                      | 0.8940           | 2.0844                   | 11.4371                  | 6.88                      |
-| 0.1083        | 0.2   | 200  | 0.3677          | 0                      | 0.8930           | 2.1733                   | 11.3445                  | 6.6044                    |
-| 0.0912        | 0.3   | 300  | 0.3710          | 0                      | 0.8953           | 2.2444                   | 12.0020                  | 6.44                      |
-| 0.0699        | 0.4   | 400  | 0.3598          | 0                      | 0.8996           | 2.1778                   | 12.3582                  | 6.3289                    |
-| 0.0619        | 0.5   | 500  | 0.3516          | 0                      | 0.9010           | 2.2489                   | 12.6065                  | 6.2756                    |
-| 0.0766        | 0.6   | 600  | 0.3517          | 0                      | 0.9014           | 2.2356                   | 12.5313                  | 6.2756                    |
+Use the code [here](https://github.com/defog-ai/sqlcoder/blob/main/inference.py) to get started with the model.
 
+## Prompt
 
-### Framework versions
+Please use the following prompt for optimal results:
 
-- Transformers 4.37.2
-- Pytorch 2.1.2+cu121
-- Datasets 2.16.1
-- Tokenizers 0.15.1
+```
+### Task
+Generate a SQL query to answer [QUESTION]{user_question}[/QUESTION]
+
+### Database Schema
+The query will run on a database with the following schema:
+{table_metadata_string_DDL_statements}
+
+### Answer
+Given the database schema, here is the SQL query that [QUESTION]{user_question}[/QUESTION]
+[SQL]
+```
+
+## Evaluation
+
+This model was evaluated on [SQL-Eval](https://github.com/defog-ai/sql-eval), a PostgreSQL based evaluation framework developed by Defog for testing and alignment of model capabilities.
+
+You can read more about the methodology behind SQLEval [here](https://defog.ai/blog/open-sourcing-sqleval/).
+
+### Results
+
+We classified each generated question into one of 6 categories. The table displays the percentage of questions answered correctly by each model, broken down by category.
+
+|                | date | group_by | order_by | ratio | join | where |
+| -------------- | ---- | -------- | -------- | ----- | ---- | ----- |
+| sqlcoder-70b   | 96   | 91.4     | 97.1     | 85.7  | 97.1 | 91.4  |
+| sqlcoder-7b    | 96   | 85.7     | 97.1     | 85.7  | 82.8 | 77.1  |
+| sqlcoder-34b   | 80   | 94.3     | 85.7     | 77.1  | 85.7 | 80    |
+| gpt-4          | 72   | 94.3     | 97.1     | 80    | 91.4 | 80    |
+| gpt-4-turbo    | 76   | 91.4     | 91.4     | 62.8  | 88.6 | 77.1  |
+| natural-sql-7b | 56   | 88.6     | 85.7     | 60    | 88.6 | 80    |
+| sqlcoder-7b    | 64   | 82.9     | 74.3     | 54.3  | 74.3 | 74.3  |
+| gpt-3.5        | 72   | 77.1     | 82.8     | 34.3  | 65.7 | 71.4  |
+| claude-2       | 52   | 71.4     | 74.3     | 57.1  | 65.7 | 62.9  |
+
+## Model Card Contact
+
+Contact us on X at [@defogdata](https://twitter.com/defogdata), or on email at [[email protected]](mailto:[email protected])