zzman/QWEN2.1-0.5-SFT

README.md

@@ -34,10 +34,10 @@ This model was trained with SFT.
 
 ### Framework versions
 
-- TRL: 0.15.2
-- Transformers: 4.49.0
+- TRL: 0.16.0
+- Transformers: 4.50.0
 - Pytorch: 2.6.0+cu124
-- Datasets: 3.4.1
+- Datasets: 3.5.0
 - Tokenizers: 0.21.1
 
 ## Citations

config.json

@@ -1,5 +1,4 @@
 {
-  "_name_or_path": "Qwen/Qwen2.5-0.5B-Instruct",
   "architectures": [
     "Qwen2ForCausalLM"
   ],
@@ -22,7 +21,7 @@
   "sliding_window": 32768,
   "tie_word_embeddings": true,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.49.0",
+  "transformers_version": "4.50.0",
   "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": "4.49.0"
+  "transformers_version": "4.50.0"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8bd2f69716a38d0c83f47ddc6abb0f256deee9d4da231ae8aee0ede230d8a85a
+oid sha256:49618884170f0f734a09aece2e47c0d3320fa1b21bd299b86747ba6fb2c046af
 size 988097824

tokenizer_config.json

@@ -202,7 +202,6 @@
   "extra_special_tokens": {},
   "model_max_length": 131072,
   "pad_token": "<|endoftext|>",
-  "padding_side": "right",
   "split_special_tokens": false,
   "tokenizer_class": "Qwen2Tokenizer",
   "unk_token": null

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37f618eb0b738d870d555a233ea8422b57aaf99c5d09f24494909f8140affb26
-size 5560
+oid sha256:4b94f36f06c24f4116c23dbc193373bc5f0e13595a32449365770e7102007b86
+size 5624