End of training

README.md

@@ -29,17 +29,18 @@ print(output["generated_text"])
 
 ## Training procedure
 
+ 
 
 
 This model was trained with SFT.
 
 ### Framework versions
 
-- TRL: 0.12.1
-- Transformers: 4.46.3
+- TRL: 0.13.0
+- Transformers: 4.48.0
 - Pytorch: 2.5.1
-- Datasets: 3.1.0
-- Tokenizers: 0.20.3
+- Datasets: 3.2.0
+- Tokenizers: 0.21.0
 
 ## Citations
 

config.json

@@ -27,7 +27,7 @@
   "rope_theta": 100000,
   "tie_word_embeddings": true,
   "torch_dtype": "float32",
-  "transformers_version": "4.46.3",
+  "transformers_version": "4.48.0",
   "use_cache": true,
   "vocab_size": 49152
 }

generation_config.json

@@ -3,5 +3,5 @@
   "bos_token_id": 1,
   "eos_token_id": 2,
   "pad_token_id": 2,
-  "transformers_version": "4.46.3"
+  "transformers_version": "4.48.0"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d72588f5f7e68e0a77d9d58a0a520bcee7d5bc5361580f1ac7007ce7d45b8fd3
+oid sha256:5869564fc98e8c817bb3259acee67d509c4161b594a2b57c61ca83f7aab07109
 size 538090408

tokenizer.json

@@ -1,6 +1,11 @@
 {
   "version": "1.0",
-  "truncation": null,
+  "truncation": {
+    "direction": "Right",
+    "max_length": 1024,
+    "strategy": "LongestFirst",
+    "stride": 0
+  },
   "padding": null,
   "added_tokens": [
     {

tokenizer_config.json

@@ -146,6 +146,7 @@
   "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
   "clean_up_tokenization_spaces": false,
   "eos_token": "<|im_end|>",
+  "extra_special_tokens": {},
   "model_max_length": 8192,
   "pad_token": "<|im_end|>",
   "tokenizer_class": "GPT2Tokenizer",

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ac9763369deee0b56ae016ac06cde75c33813551e9df43e30e012f80d5da817
-size 5560
+oid sha256:210c7ede970dcf902a0bd65ba35e79047a790bff78b36a9b3be02b3d40bf78af
+size 5624