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: 0.14.0.dev0
+- Transformers: 4.48.0.dev0
 - Pytorch: 2.5.1
-- Datasets: 3.1.0
-- Tokenizers: 0.20.3
+- Datasets: 2.21.0
+- 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.dev0",
   "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.dev0"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05b5ae63ae527abb6edecbf0fe032c127342567b98a50a126d6f5dacacd6c690
+oid sha256:c6a892594a01494d33bcf0a665b451c5f9d9dcd312acd315641952bcb93ef34a
 size 538090408

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:dfa44356426dbd5153920233bb983c44c76f683d784b433e5bf849cd8315366b
+oid sha256:d41eabf6ba3a9d3f552ded37a026db8a4bd42d6f1afba8ca07799b53ad47e5bb
 size 5560