Upload config.json with huggingface_hub
Browse files- config.json +27 -26
config.json
CHANGED
@@ -1,27 +1,28 @@
|
|
1 |
{
|
2 |
-
|
3 |
-
|
4 |
-
|
5 |
-
|
6 |
-
|
7 |
-
|
8 |
-
|
9 |
-
|
10 |
-
|
11 |
-
|
12 |
-
|
13 |
-
|
14 |
-
|
15 |
-
|
16 |
-
|
17 |
-
|
18 |
-
|
19 |
-
|
20 |
-
|
21 |
-
|
22 |
-
|
23 |
-
|
24 |
-
|
25 |
-
|
26 |
-
|
27 |
-
|
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "../weights/vlm-qwen-big-uform",
|
3 |
+
"architectures": [
|
4 |
+
"VLMForCausalLM"
|
5 |
+
],
|
6 |
+
"auto_map": {
|
7 |
+
"AutoConfig": "configuration_uform_gen.VLMConfig",
|
8 |
+
"AutoModel": "modeling_uform_gen.VLMForCausalLM",
|
9 |
+
"AutoProcessor": "processing_uform_gen.VLMProcessor"
|
10 |
+
},
|
11 |
+
"image_encoder_hidden_size": 1280,
|
12 |
+
"image_encoder_name_or_path": "unum-cloud/uform-vl-english-big",
|
13 |
+
"image_encoder_num_heads": 16,
|
14 |
+
"image_encoder_num_layers": 32,
|
15 |
+
"image_encoder_patch_size": 14,
|
16 |
+
"image_encoder_pooling": "cls",
|
17 |
+
"image_pooler_intermediate_size": 3200,
|
18 |
+
"image_pooler_num_attn_heads": 16,
|
19 |
+
"image_size": 336,
|
20 |
+
"image_token_id": 151646,
|
21 |
+
"initializer_range": 0.02,
|
22 |
+
"model_type": "vlm",
|
23 |
+
"num_image_latents": 256,
|
24 |
+
"text_decoder_name_or_path": "Qwen/Qwen1.5-0.5B-Chat",
|
25 |
+
"torch_dtype": "float32",
|
26 |
+
"transformers_version": "4.37.2",
|
27 |
+
"use_cache": true
|
28 |
+
}
|