omaratef3221/Qwen2-0.5B-Instruct-SQL-generator

README.md

@@ -27,17 +27,18 @@ print(output["generated_text"])
 
 ## Training procedure
 
+ 
 
 
 This model was trained with SFT.
 
 ### Framework versions
 
-- TRL: 0.12.2
-- Transformers: 4.46.3
+- TRL: 0.13.0
+- Transformers: 4.47.1
 - Pytorch: 2.5.1
-- Datasets: 3.1.0
-- Tokenizers: 0.20.3
+- Datasets: 3.2.0
+- Tokenizers: 0.21.0
 
 ## Citations
 

config.json

@@ -22,7 +22,7 @@
   "sliding_window": null,
   "tie_word_embeddings": true,
   "torch_dtype": "float32",
-  "transformers_version": "4.46.3",
+  "transformers_version": "4.47.1",
   "use_cache": true,
   "use_sliding_window": false,
   "vocab_size": 151936

generation_config.json

@@ -10,5 +10,5 @@
   "temperature": 0.7,
   "top_k": 20,
   "top_p": 0.8,
-  "transformers_version": "4.46.3"
+  "transformers_version": "4.47.1"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9dcdaf48d906b79fdcebc52f4b0080bda4eb1f44fba0acdd69b8c3eafa240743
+oid sha256:7a758bf3ac7275975efbf4808678592654b28812b02ba287f1bc489acdba5c41
 size 1976163472

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bcfe42da0a4497e8b2b172c1f9f4ec423a46dc12907f4349c55025f670422ba9
-size 11418266
+oid sha256:e49bebc2336dd0896ee055aa24e6bb65d80539b16751bb9798d6829db3ac4ea3
+size 11418365

tokenizer_config.json

@@ -35,6 +35,7 @@
   "clean_up_tokenization_spaces": false,
   "eos_token": "<|im_end|>",
   "errors": "replace",
+  "extra_special_tokens": {},
   "model_max_length": 32768,
   "pad_token": "<|endoftext|>",
   "split_special_tokens": false,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a5ec9e128de2409e0646b6089fc8fe3cfccdb81268c7d29ffa23d254b9cc720f
-size 5496
+oid sha256:635a3a666573258d24ad361d5fcc1625bcccbac09181d31348e03011013763f3
+size 5560