End of training

README.md

@@ -29,18 +29,17 @@ print(output["generated_text"])
 
 ## Training procedure
 
- 
 
 
 This model was trained with SFT.
 
 ### Framework versions
 
-- TRL: 0.14.0
-- Transformers: 4.47.1
-- Pytorch: 2.5.1+cu124
-- Datasets: 3.2.0
-- Tokenizers: 0.21.0
+- TRL: 0.12.1
+- Transformers: 4.46.3
+- Pytorch: 2.5.1
+- Datasets: 3.1.0
+- Tokenizers: 0.20.3
 
 ## Citations
 

config.json

@@ -27,7 +27,7 @@
   "rope_theta": 100000,
   "tie_word_embeddings": true,
   "torch_dtype": "float32",
-  "transformers_version": "4.47.1",
+  "transformers_version": "4.46.3",
   "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": "4.47.1"
+  "transformers_version": "4.46.3"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c40220acb710b334bb2bade89e9fe6bdcbd7a1e99fad1e5a7637e6487b4f0263
+oid sha256:73031b46c8ccd59b9d9211b0cbc740f67167b1e6e667e894ae9d7180d961288e
 size 538090408

tokenizer.json

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

tokenizer_config.json

@@ -146,7 +146,6 @@
   "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 sha256:9c7c7bf31a4c30cfb0a767ad72422db05a96a72532136cfa8df8a7b7f4169374
+oid sha256:314891272cad9d37d43b9888fd491a45547a7d3efd01753d4d77ec87b0bf9e3e
 size 5560