anonymous-2321 commited on
Commit
0df150e
·
verified ·
1 Parent(s): 7f8f89f

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -5
README.md CHANGED
@@ -7,7 +7,6 @@ tags:
7
  - Text2SQL
8
  - Reasoning
9
  licence: apache-2.0
10
- license: apache-2.0
11
  language:
12
  - en
13
  ---
@@ -17,7 +16,7 @@ language:
17
  This model is the reasoning model for the Text-to-SQL task introduced in [Think2SQL: Blueprinting Reward Density and Advantage Scaling for Effective Text-to-SQL Reasoning]()
18
 
19
 
20
- This model is a fine-tuned version of [Qwen/Qwen3-4B](https://huggingface.co/Qwen/Qwen3-4B) on the [BIRD](https://bird-bench.github.io/) dataset.
21
  It has been trained using [TRL](https://github.com/huggingface/trl).
22
 
23
 
@@ -28,9 +27,7 @@ The best model performance is given with its System and User prompts.
28
  The model is intended to be used with three inputs: question, evidence, and the database schema.
29
 
30
 
31
- Starting with `transformers >= 4.43.0` onward, you can run conversational inference using the Transformers `pipeline` abstraction or by leveraging the Auto classes with the `generate()` function.
32
-
33
- Make sure to update your transformers installation via `pip install --upgrade transformers`.
34
 
35
  ```python
36
  import transformers
 
7
  - Text2SQL
8
  - Reasoning
9
  licence: apache-2.0
 
10
  language:
11
  - en
12
  ---
 
16
  This model is the reasoning model for the Text-to-SQL task introduced in [Think2SQL: Blueprinting Reward Density and Advantage Scaling for Effective Text-to-SQL Reasoning]()
17
 
18
 
19
+ This model is a fine-tuned version of [Qwen/Qwen3-4B](https://huggingface.co/Qwen/Qwen3-4B) with thinking disabled on the [BIRD](https://bird-bench.github.io/) dataset.
20
  It has been trained using [TRL](https://github.com/huggingface/trl).
21
 
22
 
 
27
  The model is intended to be used with three inputs: question, evidence, and the database schema.
28
 
29
 
30
+ Required `transformers > 4.51.0` to have Qwen3. Make sure to update your transformers installation via `pip install --upgrade transformers`.
 
 
31
 
32
  ```python
33
  import transformers