Update tiny models for Aimv2Model
Browse files- config.json +50 -0
- model.safetensors +3 -0
- preprocessor_config.json +28 -0
- tokenizer.json +0 -0
- tokenizer_config.json +15 -0
config.json
ADDED
|
@@ -0,0 +1,50 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Aimv2Model"
|
| 4 |
+
],
|
| 5 |
+
"dtype": "float32",
|
| 6 |
+
"initializer_factor": 1.0,
|
| 7 |
+
"logit_scale_init_value": 2.6592,
|
| 8 |
+
"max_logit_scale": 100.0,
|
| 9 |
+
"model_type": "aimv2",
|
| 10 |
+
"projection_dim": 64,
|
| 11 |
+
"text_config": {
|
| 12 |
+
"attention_dropout": 0.1,
|
| 13 |
+
"dropout": 0.1,
|
| 14 |
+
"eos_token_id": 49407,
|
| 15 |
+
"hidden_act": "silu",
|
| 16 |
+
"hidden_size": 32,
|
| 17 |
+
"initializer_range": 0.02,
|
| 18 |
+
"intermediate_size": 37,
|
| 19 |
+
"max_position_embeddings": 200,
|
| 20 |
+
"mlp_bias": false,
|
| 21 |
+
"model_type": "aimv2_text_model",
|
| 22 |
+
"num_attention_heads": 4,
|
| 23 |
+
"num_hidden_layers": 2,
|
| 24 |
+
"projection_dim": 32,
|
| 25 |
+
"qkv_bias": false,
|
| 26 |
+
"rms_norm_eps": 1e-05,
|
| 27 |
+
"vocab_size": 49408
|
| 28 |
+
},
|
| 29 |
+
"transformers_version": "5.16.0.dev0",
|
| 30 |
+
"vision_config": {
|
| 31 |
+
"attention_dropout": 0.1,
|
| 32 |
+
"dropout": 0.1,
|
| 33 |
+
"hidden_act": "silu",
|
| 34 |
+
"hidden_size": 32,
|
| 35 |
+
"image_size": 30,
|
| 36 |
+
"initializer_range": 0.02,
|
| 37 |
+
"intermediate_size": 37,
|
| 38 |
+
"is_native": false,
|
| 39 |
+
"mlp_bias": false,
|
| 40 |
+
"model_type": "aimv2_vision_model",
|
| 41 |
+
"num_attention_heads": 4,
|
| 42 |
+
"num_channels": 3,
|
| 43 |
+
"num_hidden_layers": 2,
|
| 44 |
+
"patch_size": 2,
|
| 45 |
+
"projection_dim": 32,
|
| 46 |
+
"qkv_bias": false,
|
| 47 |
+
"rms_norm_eps": 1e-05,
|
| 48 |
+
"use_head": true
|
| 49 |
+
}
|
| 50 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c95d2a89359e89daa46fdc4dbdb12c567f08f616e7e6f2289aa5627392da0f5b
|
| 3 |
+
size 6538828
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"crop_size": {
|
| 3 |
+
"longest_edge": 30,
|
| 4 |
+
"shortest_edge": 30
|
| 5 |
+
},
|
| 6 |
+
"do_center_crop": true,
|
| 7 |
+
"do_convert_rgb": true,
|
| 8 |
+
"do_normalize": true,
|
| 9 |
+
"do_rescale": true,
|
| 10 |
+
"do_resize": true,
|
| 11 |
+
"image_mean": [
|
| 12 |
+
0.48145466,
|
| 13 |
+
0.4578275,
|
| 14 |
+
0.40821073
|
| 15 |
+
],
|
| 16 |
+
"image_processor_type": "CLIPImageProcessor",
|
| 17 |
+
"image_std": [
|
| 18 |
+
0.26862954,
|
| 19 |
+
0.26130258,
|
| 20 |
+
0.27577711
|
| 21 |
+
],
|
| 22 |
+
"resample": 3,
|
| 23 |
+
"rescale_factor": 0.00392156862745098,
|
| 24 |
+
"size": {
|
| 25 |
+
"longest_edge": 30,
|
| 26 |
+
"shortest_edge": 30
|
| 27 |
+
}
|
| 28 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"backend": "tokenizers",
|
| 3 |
+
"bos_token": "<start_of_text>",
|
| 4 |
+
"clean_up_tokenization_spaces": false,
|
| 5 |
+
"eos_token": "<end_of_text>",
|
| 6 |
+
"errors": "replace",
|
| 7 |
+
"is_local": true,
|
| 8 |
+
"local_files_only": false,
|
| 9 |
+
"model_max_length": 77,
|
| 10 |
+
"pad_token": "<end_of_text>",
|
| 11 |
+
"processor_class": "CLIPProcessor",
|
| 12 |
+
"tokenizer_class": "CLIPTokenizer",
|
| 13 |
+
"unk_token": "<end_of_text>",
|
| 14 |
+
"use_fast": true
|
| 15 |
+
}
|