thanhdathoang commited on
Commit
905d378
·
verified ·
1 Parent(s): 3a36c7b

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -10,7 +10,7 @@ Trained from [`griffith-bigdata/Qwen-2.5-Coder-3B-SQL-Writer`](https://huggingfa
10
  🧠 Memory Reward — aligns reasoning with verified traces
11
  ⚙️ Atomic Reward — measures operation-level SQL overlap
12
 
13
- ✅ 67.5% EX on BIRD with a single 24 GB GPU
14
 
15
  📄 See other models: https://huggingface.co/collections/griffith-bigdata/finer-sql
16
 
 
10
  🧠 Memory Reward — aligns reasoning with verified traces
11
  ⚙️ Atomic Reward — measures operation-level SQL overlap
12
 
13
+ ✅ 67.5% EX on BIRD when training only on BIRD train dataset; infer on a single 12-24 GB GPU
14
 
15
  📄 See other models: https://huggingface.co/collections/griffith-bigdata/finer-sql
16