End of training

README.md

@@ -4,8 +4,8 @@ library_name: transformers
 model_name: sft_model
 tags:
 - generated_from_trainer
-- trl
 - sft
+- trl
 licence: license
 ---
 
@@ -30,11 +30,12 @@ print(output["generated_text"])
  
 
 
+
 This model was trained with SFT.
 
 ### Framework versions
 
-- TRL: 0.28.0
+- TRL: 0.29.0
 - Transformers: 4.57.1
 - Pytorch: 2.8.0+cu126
 - Datasets: 4.4.2

added_tokens.json

@@ -1,3 +1,5 @@
 {
-  "<image_soft_token>": 262144
+  "<image_soft_token>": 262144,
+  "<|im_end|>": 262146,
+  "<|im_start|>": 262145
 }

chat_template.jinja

@@ -17,8 +17,5 @@
 {%- if add_generation_prompt -%}
     
     {{ "<|im_start|>assistant
-" + "<think>
-
-</think>
-"  }}
+" }}
 {%- endif -%}

config.json

@@ -50,5 +50,5 @@
   "transformers_version": "4.57.1",
   "use_bidirectional_attention": false,
   "use_cache": true,
-  "vocab_size": 262144
+  "vocab_size": 262147
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb866034f112a448803d04d3b7d002c550a70365577704ec1108d4da329c663d
-size 1072419256
+oid sha256:124ecaca0cdb1aea023e85cc3a9cfe41b078c691d09490fccc23464f5dcf7efc
+size 1072426936

runs/Mar01_01-31-54_ab2580001b44/events.out.tfevents.1772329576.ab2580001b44.66.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3af23f5ee7dc27cd1267c2a70ee1f883f2ad4818b947257b3fa04949722fae1
+size 254604

special_tokens_map.json

@@ -1,4 +1,20 @@
 {
+  "additional_special_tokens": [
+    {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
   "boi_token": "<start_of_image>",
   "bos_token": {
     "content": "<bos>",

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4667f2089529e8e7657cfb6d1c19910ae71ff5f28aa7ab2ff2763330affad795
-size 33384568
+oid sha256:3c5591c1449f71a5ae4c2ed1cb1cbdadf42e4cc9537c9850184d520a42cb18dc
+size 33384944

tokenizer_config.json

@@ -51321,8 +51321,28 @@
       "rstrip": false,
       "single_word": false,
       "special": true
+    },
+    "262145": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "262146": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
     }
   },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
   "boi_token": "<start_of_image>",
   "bos_token": "<bos>",
   "clean_up_tokenization_spaces": false,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7b0494a970849945d2006eff4c85aa1f0ee1433bb201ecbefea81899e2ba093
+oid sha256:6e0211cd5e84a3a5f1ce5cac882c3e72eca010cd652a0d843121fbc0f08b45d5
 size 6225