Update checkpoint from thanhdath/FINER-SQL-3B-BIRD + add GitHub link (#3)

- Update checkpoint from thanhdath/FINER-SQL-3B-BIRD + add GitHub link (9684f35e81de47e77d90683bdee359237b4040a4)
- Replace README with minimal version (GitHub link + citation) (362452528c6fdae9c8a21c5de1041b71a38bad82)

README.md

@@ -1,17 +1,13 @@
----
-base_model:
-- griffith-bigdata/Qwen-2.5-Coder-3B-SQL-Writer
----
-
-# FINER-SQL-3B-BIRD
-
-Trained from [`griffith-bigdata/Qwen-2.5-Coder-3B-SQL-Writer`](https://huggingface.co/griffith-bigdata/Qwen-2.5-Coder-3B-SQL-Writer) using GRPO with two dense rewards from the FINER-SQL paper:
-
-🧠 Memory Reward — aligns reasoning with verified traces  
-⚙️ Atomic Reward — measures operation-level SQL overlap  
-
-✅ 67.5% EX on BIRD when training only on BIRD train dataset; infer on a single 12-24 GB GPU  
-
-📄 See other models: https://huggingface.co/collections/griffith-bigdata/finer-sql
-
-📄 Github: https://github.com/thanhdath/finer-sql/tree/main
+📄 GitHub: https://github.com/thanhdath/finer-sql
+
+## Citation
+
+```bibtex
+@inproceedings{finersql,
+  author       = {Thanh Dat Hoang and Thanh Trung Huynh and Matthias Weidlich and Thanh Tam Nguyen and Tong Chen and Hongzhi Yin and Quoc Viet Hung Nguyen},
+  title        = {Boosting Small Language Models for Text-to-SQL with Fine-Grained Execution Feedback and Cost-Efficient Rewards},
+  booktitle    = {ICDE},
+  publisher    = {IEEE},
+  year         = {2026},
+}
+```

config.json

@@ -59,7 +59,7 @@
   "rope_theta": 1000000.0,
   "sliding_window": null,
   "tie_word_embeddings": true,
-  "transformers_version": "4.57.0",
+  "transformers_version": "4.57.3",
   "use_cache": false,
   "use_sliding_window": false,
   "vocab_size": 151936

generation_config.json

@@ -9,5 +9,5 @@
   "temperature": 0.7,
   "top_k": 20,
   "top_p": 0.8,
-  "transformers_version": "4.57.0"
+  "transformers_version": "4.57.3"
 }

model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9164dea2c8426fe370018e57fc618e8fec599ab28db5e887a6c94c0c72a25e3a
+oid sha256:ee02a3811c46f66e0b9fb703a474b9996ea71d30b822aa900ea3b46c0e609cf1
 size 4957560304

model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:edf6bbb1ddf2cfcd40825761b6153571a0a0b704cbb6302ce2d29a1d9b9fcfec
+oid sha256:cb660d6e329abcb9105a8183eb58798c4937d2a33e2e1e2c8ee43fa622fe888e
 size 1214366696

tokenizer_config.json

@@ -201,12 +201,14 @@
   "extra_special_tokens": {},
   "max_length": 6192,
   "model_max_length": 32768,
+  "pad_to_multiple_of": null,
   "pad_token": "<|endoftext|>",
+  "pad_token_type_id": 0,
   "padding_side": "left",
   "split_special_tokens": false,
   "stride": 0,
   "tokenizer_class": "Qwen2Tokenizer",
-  "truncation_side": "right",
+  "truncation_side": "left",
   "truncation_strategy": "longest_first",
   "unk_token": null
 }