Commit
·
2c2f2e2
1
Parent(s):
6b6f84b
Upload tiny models for IdeficsForVisionText2Text
Browse files- added_tokens.json +4 -0
- config.json +65 -0
- generation_config.json +7 -0
- preprocessor_config.json +9 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +40 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +36 -0
added_tokens.json
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<fake_token_around_image>": 32000,
|
| 3 |
+
"<image>": 32001
|
| 4 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,65 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_vocab_size": 0,
|
| 3 |
+
"alpha_initializer": "zeros",
|
| 4 |
+
"alpha_type": "float",
|
| 5 |
+
"alphas_initializer_range": 0.0,
|
| 6 |
+
"architectures": [
|
| 7 |
+
"IdeficsForVisionText2Text"
|
| 8 |
+
],
|
| 9 |
+
"attention_probs_dropout_prob": 0.1,
|
| 10 |
+
"bos_token_id": 1,
|
| 11 |
+
"cross_layer_interval": 1,
|
| 12 |
+
"dropout": 0.0,
|
| 13 |
+
"eos_token_id": 2,
|
| 14 |
+
"freeze_lm_head": false,
|
| 15 |
+
"freeze_text_layers": true,
|
| 16 |
+
"freeze_text_module_exceptions": [],
|
| 17 |
+
"freeze_vision_layers": true,
|
| 18 |
+
"freeze_vision_module_exceptions": [],
|
| 19 |
+
"hidden_act": "gelu",
|
| 20 |
+
"hidden_dropout_prob": 0.1,
|
| 21 |
+
"hidden_size": 32,
|
| 22 |
+
"id2label": {
|
| 23 |
+
"0": "LABEL_0",
|
| 24 |
+
"1": "LABEL_1",
|
| 25 |
+
"2": "LABEL_2"
|
| 26 |
+
},
|
| 27 |
+
"image_size": 30,
|
| 28 |
+
"initializer_range": 0.02,
|
| 29 |
+
"intermediate_size": 37,
|
| 30 |
+
"label2id": {
|
| 31 |
+
"LABEL_0": 0,
|
| 32 |
+
"LABEL_1": 1,
|
| 33 |
+
"LABEL_2": 2
|
| 34 |
+
},
|
| 35 |
+
"max_position_embeddings": 512,
|
| 36 |
+
"modality_type_vocab_size": 2,
|
| 37 |
+
"model_type": "idefics",
|
| 38 |
+
"num_attention_heads": 4,
|
| 39 |
+
"num_channels": 3,
|
| 40 |
+
"num_hidden_layers": 5,
|
| 41 |
+
"num_images": -1,
|
| 42 |
+
"pad_token_id": 0,
|
| 43 |
+
"patch_size": 2,
|
| 44 |
+
"perceiver_config": {
|
| 45 |
+
"model_type": "idefics"
|
| 46 |
+
},
|
| 47 |
+
"qk_layer_norms": false,
|
| 48 |
+
"rms_norm_eps": 1e-06,
|
| 49 |
+
"tie_word_embeddings": false,
|
| 50 |
+
"torch_dtype": "float32",
|
| 51 |
+
"transformers_version": "4.33.0.dev0",
|
| 52 |
+
"type_vocab_size": 16,
|
| 53 |
+
"use_cache": true,
|
| 54 |
+
"use_resampler": false,
|
| 55 |
+
"vision_config": {
|
| 56 |
+
"embed_dim": 32,
|
| 57 |
+
"image_size": 30,
|
| 58 |
+
"intermediate_size": 37,
|
| 59 |
+
"model_type": "idefics",
|
| 60 |
+
"num_attention_heads": 4,
|
| 61 |
+
"num_hidden_layers": 5,
|
| 62 |
+
"patch_size": 2
|
| 63 |
+
},
|
| 64 |
+
"vocab_size": 32002
|
| 65 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 1,
|
| 4 |
+
"eos_token_id": 2,
|
| 5 |
+
"pad_token_id": 0,
|
| 6 |
+
"transformers_version": "4.33.0.dev0"
|
| 7 |
+
}
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"crop_size": 30,
|
| 3 |
+
"image_mean": null,
|
| 4 |
+
"image_num_channels": 3,
|
| 5 |
+
"image_processor_type": "IdeficsImageProcessor",
|
| 6 |
+
"image_size": 224,
|
| 7 |
+
"image_std": null,
|
| 8 |
+
"size": 30
|
| 9 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4e8bb9f3cdaec2abfed2e67afd64a18193209c920752b9d9a4a1a09cd34d2ea5
|
| 3 |
+
size 8733485
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
{
|
| 4 |
+
"content": "<fake_token_around_image>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": true,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false
|
| 9 |
+
},
|
| 10 |
+
{
|
| 11 |
+
"content": "<image>",
|
| 12 |
+
"lstrip": false,
|
| 13 |
+
"normalized": true,
|
| 14 |
+
"rstrip": false,
|
| 15 |
+
"single_word": false
|
| 16 |
+
}
|
| 17 |
+
],
|
| 18 |
+
"bos_token": {
|
| 19 |
+
"content": "<s>",
|
| 20 |
+
"lstrip": false,
|
| 21 |
+
"normalized": true,
|
| 22 |
+
"rstrip": false,
|
| 23 |
+
"single_word": false
|
| 24 |
+
},
|
| 25 |
+
"eos_token": {
|
| 26 |
+
"content": "</s>",
|
| 27 |
+
"lstrip": false,
|
| 28 |
+
"normalized": true,
|
| 29 |
+
"rstrip": false,
|
| 30 |
+
"single_word": false
|
| 31 |
+
},
|
| 32 |
+
"pad_token": "<unk>",
|
| 33 |
+
"unk_token": {
|
| 34 |
+
"content": "<unk>",
|
| 35 |
+
"lstrip": false,
|
| 36 |
+
"normalized": true,
|
| 37 |
+
"rstrip": false,
|
| 38 |
+
"single_word": false
|
| 39 |
+
}
|
| 40 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
| 3 |
+
size 499723
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"bos_token": {
|
| 5 |
+
"__type": "AddedToken",
|
| 6 |
+
"content": "<s>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": true,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false
|
| 11 |
+
},
|
| 12 |
+
"clean_up_tokenization_spaces": false,
|
| 13 |
+
"eos_token": {
|
| 14 |
+
"__type": "AddedToken",
|
| 15 |
+
"content": "</s>",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": true,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false
|
| 20 |
+
},
|
| 21 |
+
"legacy": true,
|
| 22 |
+
"model_max_length": 512,
|
| 23 |
+
"pad_token": null,
|
| 24 |
+
"sp_model_kwargs": {},
|
| 25 |
+
"spaces_between_special_tokens": false,
|
| 26 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 27 |
+
"unk_token": {
|
| 28 |
+
"__type": "AddedToken",
|
| 29 |
+
"content": "<unk>",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": true,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false
|
| 34 |
+
},
|
| 35 |
+
"use_default_system_prompt": true
|
| 36 |
+
}
|