Commit
•
c783aaf
1
Parent(s):
9e3bdce
Upload Pix2StructForConditionalGeneration
Browse files- config.json +31 -0
- generation_config.json +8 -0
- model.safetensors +3 -0
config.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "google/pix2struct-docvqa-base",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"Pix2StructForConditionalGeneration"
|
| 5 |
+
],
|
| 6 |
+
"decoder_start_token_id": 0,
|
| 7 |
+
"eos_token_id": 1,
|
| 8 |
+
"initializer_factor": 1.0,
|
| 9 |
+
"initializer_range": 0.02,
|
| 10 |
+
"is_encoder_decoder": true,
|
| 11 |
+
"is_vqa": false,
|
| 12 |
+
"model_type": "pix2struct",
|
| 13 |
+
"pad_token_id": 0,
|
| 14 |
+
"text_config": {
|
| 15 |
+
"encoder_hidden_size": 768,
|
| 16 |
+
"initializer_range": 0.02,
|
| 17 |
+
"model_type": "pix2struct_text_model",
|
| 18 |
+
"vocab_size": 50349
|
| 19 |
+
},
|
| 20 |
+
"tie_word_embeddings": false,
|
| 21 |
+
"torch_dtype": "float32",
|
| 22 |
+
"transformers_version": "4.37.0.dev0",
|
| 23 |
+
"vision_config": {
|
| 24 |
+
"initializer_range": 0.02,
|
| 25 |
+
"layer_norm_bias": false,
|
| 26 |
+
"model_type": "pix2struct_vision_model",
|
| 27 |
+
"num_channels": 3,
|
| 28 |
+
"patch_size": 16,
|
| 29 |
+
"projection_dim": 768
|
| 30 |
+
}
|
| 31 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"decoder_start_token_id": 0,
|
| 4 |
+
"eos_token_id": 1,
|
| 5 |
+
"pad_token_id": 0,
|
| 6 |
+
"transformers_version": "4.37.0.dev0",
|
| 7 |
+
"use_cache": false
|
| 8 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:197b4e856a155c76832922a20e5d64f4e7fc5b883817508632b3979bf897427c
|
| 3 |
+
size 1129823096
|