Hugging Face's logo

sr5434
/
rm_hh_rlhf

Text Classification
Transformers
TensorBoard
Safetensors
gemma3_text
Generated from Trainer
trl
reward-trainer
text-embeddings-inference
Model card Files
xet
 Metrics Community
sr5434 commited on
Commit
08e307a
·
verified ·
1 Parent(s): 8ec541a

End of training

Browse files
Files changed (9) hide show
  1. README.md +1 -1
  2. added_tokens.json +3 -1
  3. chat_template.jinja +1 -4
  4. model.safetensors +1 -1
  5. runs/Mar01_22-29-39_83ffa021e35a/events.out.tfevents.1772404271.83ffa021e35a.64.0 +3 -0
  6. special_tokens_map.json +4 -0
  7. tokenizer.json +2 -2
  8. tokenizer_config.json +20 -0
  9. training_args.bin +1 -1
README.md CHANGED
@@ -4,8 +4,8 @@ library_name: transformers
4
  model_name: rm_hh_rlhf
5
  tags:
6
  - generated_from_trainer
7
- - reward-trainer
8
  - trl
 
9
  licence: license
10
  ---
11
 
 
4
  model_name: rm_hh_rlhf
5
  tags:
6
  - generated_from_trainer
 
7
  - trl
8
+ - reward-trainer
9
  licence: license
10
  ---
11
 
added_tokens.json CHANGED
@@ -1,3 +1,5 @@
1
  {
2
- "<image_soft_token>": 262144
 
 
3
  }
 
1
  {
2
+ "<image_soft_token>": 262144,
3
+ "<|im_end|>": 262146,
4
+ "<|im_start|>": 262145
5
  }
chat_template.jinja CHANGED
@@ -17,8 +17,5 @@
17
  {%- if add_generation_prompt -%}
18
 
19
  {{ "<|im_start|>assistant
20
- " + "<think>
21
-
22
- </think>
23
- " }}
24
  {%- endif -%}
 
17
  {%- if add_generation_prompt -%}
18
 
19
  {{ "<|im_start|>assistant
20
+ " }}
 
 
 
21
  {%- endif -%}
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:64388433a90441a8ad7fac8ddb0580075d9e01b1870e8a3ef61ae97c5ae27116
3
  size 1072429584
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d224f81b5d779777a65909c992c909a997c2bc7dd72e64678262dbc6c276deb
3
  size 1072429584
runs/Mar01_22-29-39_83ffa021e35a/events.out.tfevents.1772404271.83ffa021e35a.64.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:625b009c089853edcccd0e571cc6bbeaef08fc8e681c2e4eef513c27cf82ecb9
3
+ size 43238
special_tokens_map.json CHANGED
@@ -1,4 +1,8 @@
1
  {
 
 
 
 
2
  "boi_token": "<start_of_image>",
3
  "bos_token": {
4
  "content": "<bos>",
 
1
  {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>"
5
+ ],
6
  "boi_token": "<start_of_image>",
7
  "bos_token": {
8
  "content": "<bos>",
tokenizer.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4667f2089529e8e7657cfb6d1c19910ae71ff5f28aa7ab2ff2763330affad795
3
- size 33384568
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c5591c1449f71a5ae4c2ed1cb1cbdadf42e4cc9537c9850184d520a42cb18dc
3
+ size 33384944
tokenizer_config.json CHANGED
@@ -51321,8 +51321,28 @@
51321
  "rstrip": false,
51322
  "single_word": false,
51323
  "special": true
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
51324
  }
51325
  },
 
 
 
 
51326
  "boi_token": "<start_of_image>",
51327
  "bos_token": "<bos>",
51328
  "clean_up_tokenization_spaces": false,
 
51321
  "rstrip": false,
51322
  "single_word": false,
51323
  "special": true
51324
+ },
51325
+ "262145": {
51326
+ "content": "<|im_start|>",
51327
+ "lstrip": false,
51328
+ "normalized": false,
51329
+ "rstrip": false,
51330
+ "single_word": false,
51331
+ "special": true
51332
+ },
51333
+ "262146": {
51334
+ "content": "<|im_end|>",
51335
+ "lstrip": false,
51336
+ "normalized": false,
51337
+ "rstrip": false,
51338
+ "single_word": false,
51339
+ "special": true
51340
  }
51341
  },
51342
+ "additional_special_tokens": [
51343
+ "<|im_start|>",
51344
+ "<|im_end|>"
51345
+ ],
51346
  "boi_token": "<start_of_image>",
51347
  "bos_token": "<bos>",
51348
  "clean_up_tokenization_spaces": false,
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ca59eb1c06f1689cc0023b60fa26ad801750128409443858acc2f28d661fd513
3
  size 6033
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9da82dc4390fecb7c32c8f63f74219b723888c643ac4f2197a4217a8502c94de
3
  size 6033