Upload folder using huggingface_hub
Browse files- checkpoints/oculus_reasoning_v2/vqa_model/config.json +58 -0
- checkpoints/oculus_reasoning_v2/vqa_model/generation_config.json +4 -0
- checkpoints/oculus_reasoning_v2/vqa_model/model.safetensors +3 -0
- checkpoints/oculus_reasoning_v2/vqa_model/processor_config.json +29 -0
- checkpoints/oculus_reasoning_v2/vqa_model/tokenizer.json +0 -0
- checkpoints/oculus_reasoning_v2/vqa_model/tokenizer_config.json +22 -0
checkpoints/oculus_reasoning_v2/vqa_model/config.json
ADDED
|
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"BlipForQuestionAnswering"
|
| 4 |
+
],
|
| 5 |
+
"dtype": "float32",
|
| 6 |
+
"image_text_hidden_size": 256,
|
| 7 |
+
"initializer_factor": 1.0,
|
| 8 |
+
"initializer_range": 0.02,
|
| 9 |
+
"label_smoothing": 0.0,
|
| 10 |
+
"logit_scale_init_value": 2.6592,
|
| 11 |
+
"model_type": "blip",
|
| 12 |
+
"projection_dim": 512,
|
| 13 |
+
"text_config": {
|
| 14 |
+
"attention_probs_dropout_prob": 0.0,
|
| 15 |
+
"encoder_hidden_size": 768,
|
| 16 |
+
"hidden_act": "gelu",
|
| 17 |
+
"hidden_dropout_prob": 0.0,
|
| 18 |
+
"hidden_size": 768,
|
| 19 |
+
"initializer_factor": 1.0,
|
| 20 |
+
"initializer_range": 0.02,
|
| 21 |
+
"intermediate_size": 3072,
|
| 22 |
+
"label_smoothing": 0.0,
|
| 23 |
+
"layer_norm_eps": 1e-12,
|
| 24 |
+
"max_position_embeddings": 512,
|
| 25 |
+
"model_type": "blip_text_model",
|
| 26 |
+
"num_attention_heads": 12,
|
| 27 |
+
"num_hidden_layers": 12,
|
| 28 |
+
"projection_dim": 768,
|
| 29 |
+
"pruned_heads": {},
|
| 30 |
+
"tf_legacy_loss": false,
|
| 31 |
+
"torchscript": false,
|
| 32 |
+
"use_bfloat16": false,
|
| 33 |
+
"use_cache": true,
|
| 34 |
+
"vocab_size": 30524
|
| 35 |
+
},
|
| 36 |
+
"transformers_version": "5.0.0rc1",
|
| 37 |
+
"vision_config": {
|
| 38 |
+
"attention_dropout": 0.0,
|
| 39 |
+
"dropout": 0.0,
|
| 40 |
+
"hidden_act": "gelu",
|
| 41 |
+
"hidden_size": 768,
|
| 42 |
+
"image_size": 384,
|
| 43 |
+
"initializer_factor": 1.0,
|
| 44 |
+
"initializer_range": 0.02,
|
| 45 |
+
"intermediate_size": 3072,
|
| 46 |
+
"layer_norm_eps": 1e-05,
|
| 47 |
+
"model_type": "blip_vision_model",
|
| 48 |
+
"num_attention_heads": 12,
|
| 49 |
+
"num_channels": 3,
|
| 50 |
+
"num_hidden_layers": 12,
|
| 51 |
+
"patch_size": 16,
|
| 52 |
+
"projection_dim": 512,
|
| 53 |
+
"pruned_heads": {},
|
| 54 |
+
"tf_legacy_loss": false,
|
| 55 |
+
"torchscript": false,
|
| 56 |
+
"use_bfloat16": false
|
| 57 |
+
}
|
| 58 |
+
}
|
checkpoints/oculus_reasoning_v2/vqa_model/generation_config.json
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"transformers_version": "5.0.0rc1"
|
| 4 |
+
}
|
checkpoints/oculus_reasoning_v2/vqa_model/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e694b40dc9205491c9aa3b7a49ca93d79d780767a3ed578a0f6d8e8436b7ee56
|
| 3 |
+
size 1538792112
|
checkpoints/oculus_reasoning_v2/vqa_model/processor_config.json
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"image_processor": {
|
| 3 |
+
"do_convert_rgb": true,
|
| 4 |
+
"do_normalize": true,
|
| 5 |
+
"do_pad": true,
|
| 6 |
+
"do_rescale": true,
|
| 7 |
+
"do_resize": true,
|
| 8 |
+
"image_mean": [
|
| 9 |
+
0.48145466,
|
| 10 |
+
0.4578275,
|
| 11 |
+
0.40821073
|
| 12 |
+
],
|
| 13 |
+
"image_processor_type": "BlipImageProcessor",
|
| 14 |
+
"image_std": [
|
| 15 |
+
0.26862954,
|
| 16 |
+
0.26130258,
|
| 17 |
+
0.27577711
|
| 18 |
+
],
|
| 19 |
+
"processor_class": "BlipProcessor",
|
| 20 |
+
"resample": 3,
|
| 21 |
+
"rescale_factor": 0.00392156862745098,
|
| 22 |
+
"size": {
|
| 23 |
+
"height": 384,
|
| 24 |
+
"width": 384
|
| 25 |
+
},
|
| 26 |
+
"size_divisor": 32
|
| 27 |
+
},
|
| 28 |
+
"processor_class": "BlipProcessor"
|
| 29 |
+
}
|
checkpoints/oculus_reasoning_v2/vqa_model/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoints/oculus_reasoning_v2/vqa_model/tokenizer_config.json
ADDED
|
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": null,
|
| 3 |
+
"backend": "tokenizers",
|
| 4 |
+
"cls_token": "[CLS]",
|
| 5 |
+
"do_basic_tokenize": true,
|
| 6 |
+
"do_lower_case": true,
|
| 7 |
+
"is_local": false,
|
| 8 |
+
"mask_token": "[MASK]",
|
| 9 |
+
"model_input_names": [
|
| 10 |
+
"input_ids",
|
| 11 |
+
"attention_mask"
|
| 12 |
+
],
|
| 13 |
+
"model_max_length": 512,
|
| 14 |
+
"never_split": null,
|
| 15 |
+
"pad_token": "[PAD]",
|
| 16 |
+
"processor_class": "BlipProcessor",
|
| 17 |
+
"sep_token": "[SEP]",
|
| 18 |
+
"strip_accents": null,
|
| 19 |
+
"tokenize_chinese_chars": true,
|
| 20 |
+
"tokenizer_class": "BertTokenizer",
|
| 21 |
+
"unk_token": "[UNK]"
|
| 22 |
+
}
|