Ricardo-M commited on
Commit
e12b6bf
·
verified ·
1 Parent(s): a88a0f6

Upload folder using huggingface_hub

Browse files
added_tokens.json CHANGED
@@ -1,12 +1,13 @@
1
  {
2
- "[IMG0]": 32000,
3
- "[IMG1]": 32001,
4
- "[IMG2]": 32002,
5
- "[IMG3]": 32003,
6
- "[IMG4]": 32004,
7
- "[IMG5]": 32005,
8
- "[IMG6]": 32006,
9
- "[IMG7]": 32007,
10
- "[IMG8]": 32008,
11
- "[IMG9]": 32009
 
12
  }
 
1
  {
2
+ "[IMG0]": 32001,
3
+ "[IMG1]": 32002,
4
+ "[IMG2]": 32003,
5
+ "[IMG3]": 32004,
6
+ "[IMG4]": 32005,
7
+ "[IMG5]": 32006,
8
+ "[IMG6]": 32007,
9
+ "[IMG7]": 32008,
10
+ "[IMG8]": 32009,
11
+ "[IMG9]": 32010,
12
+ "[SCORE]": 32000
13
  }
config.json CHANGED
@@ -5,7 +5,7 @@
5
  ],
6
  "attention_bias": false,
7
  "bos_token_id": 1,
8
- "ce_weight": 0.0,
9
  "emd_weight": 0.0,
10
  "eos_token_id": 2,
11
  "freeze_vision_model": false,
@@ -17,7 +17,6 @@
17
  "initializer_range": 0.02,
18
  "intermediate_size": 11008,
19
  "l1_weight": 0.0,
20
- "level": false,
21
  "max_position_embeddings": 2048,
22
  "max_score": 10,
23
  "min_score": 1,
@@ -39,14 +38,14 @@
39
  "num_hidden_layers": 32,
40
  "num_key_value_heads": 32,
41
  "num_tokens": 10,
42
- "output_first_id": 32000,
43
- "output_last_id": 32009,
44
  "pretraining_tp": 1,
45
  "rms_norm_eps": 1e-06,
46
  "rope_scaling": null,
47
  "rope_theta": 10000.0,
 
48
  "tie_word_embeddings": false,
49
- "token_weight": 15.0,
50
  "torch_dtype": "bfloat16",
51
  "transformers_version": "4.31.0",
52
  "tune_visual_abstractor": true,
@@ -206,5 +205,5 @@
206
  "use_flash_attn": false
207
  }
208
  },
209
- "vocab_size": 32010
210
  }
 
5
  ],
6
  "attention_bias": false,
7
  "bos_token_id": 1,
8
+ "ce_weight": 1.0,
9
  "emd_weight": 0.0,
10
  "eos_token_id": 2,
11
  "freeze_vision_model": false,
 
17
  "initializer_range": 0.02,
18
  "intermediate_size": 11008,
19
  "l1_weight": 0.0,
 
20
  "max_position_embeddings": 2048,
21
  "max_score": 10,
22
  "min_score": 1,
 
38
  "num_hidden_layers": 32,
39
  "num_key_value_heads": 32,
40
  "num_tokens": 10,
41
+ "output_first_id": 32001,
42
+ "output_last_id": 32010,
43
  "pretraining_tp": 1,
44
  "rms_norm_eps": 1e-06,
45
  "rope_scaling": null,
46
  "rope_theta": 10000.0,
47
+ "score_id": 32000,
48
  "tie_word_embeddings": false,
 
49
  "torch_dtype": "bfloat16",
50
  "transformers_version": "4.31.0",
51
  "tune_visual_abstractor": true,
 
205
  "use_flash_attn": false
206
  }
207
  },
208
+ "vocab_size": 32011
209
  }
pytorch_model-00001-of-00002.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fa6dd3cf731fcf0059db05e32868dca32109b7b91f4216cf6dc0515d35c87838
3
- size 9991673905
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b6f425277b735736e9f034b5b9389332441e22fcedb22b3e73abc89c0b4a860b
3
+ size 9991682097
pytorch_model-00002-of-00002.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:905727fa8a677db5ceab6391c4df593a00f980e1af8f2dddf3110e2c239f4267
3
- size 6417912890
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d43cd91bbc03fb08c19be9636228454b63b0351e58d8ff7c55d3f1c3556ae462
3
+ size 6417921082
pytorch_model.bin.index.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
  "metadata": {
3
- "total_size": 16409268226
4
  },
5
  "weight_map": {
6
  "learned_weight": "pytorch_model-00001-of-00002.bin",
 
1
  {
2
  "metadata": {
3
+ "total_size": 16409284610
4
  },
5
  "weight_map": {
6
  "learned_weight": "pytorch_model-00001-of-00002.bin",
trainer_state.json CHANGED
The diff for this file is too large to render. See raw diff
 
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ad17c8b05629df0466455149bfa645a787bb67afcb762311a0362f30e92c7b5d
3
- size 6011
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9bb7fc4c325c5f0d1d3f37f7b4903cc48160d7dfc97e6eabcc25d3d491750527
3
+ size 5947