Upload 8 files
Browse files- config.json +68 -0
- generation_config.json +7 -0
- model.safetensors +3 -0
- preprocessor_config.json +51 -0
- special_tokens_map.json +30 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +57 -0
config.json
ADDED
@@ -0,0 +1,68 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "/home/ea/work/my_optimum_intel/optimum-intel/tiny-random-llava-next/config.json",
|
3 |
+
"architectures": [
|
4 |
+
"LlavaNextForConditionalGeneration"
|
5 |
+
],
|
6 |
+
"ignore_index": -100,
|
7 |
+
"image_grid_pinpoints": [
|
8 |
+
[
|
9 |
+
30,
|
10 |
+
60
|
11 |
+
],
|
12 |
+
[
|
13 |
+
60,
|
14 |
+
30
|
15 |
+
],
|
16 |
+
[
|
17 |
+
60,
|
18 |
+
60
|
19 |
+
],
|
20 |
+
[
|
21 |
+
90,
|
22 |
+
30
|
23 |
+
],
|
24 |
+
[
|
25 |
+
30,
|
26 |
+
90
|
27 |
+
]
|
28 |
+
],
|
29 |
+
"image_token_index": 32000,
|
30 |
+
"model_type": "llava_next",
|
31 |
+
"projector_hidden_act": "gelu",
|
32 |
+
"text_config": {
|
33 |
+
"_name_or_path": "HuggingFaceM4/tiny-random-LlamaForCausalLM",
|
34 |
+
"architectures": [
|
35 |
+
"LlamaForCausalLM"
|
36 |
+
],
|
37 |
+
"bos_token_id": 0,
|
38 |
+
"eos_token_id": 1,
|
39 |
+
"hidden_size": 16,
|
40 |
+
"intermediate_size": 64,
|
41 |
+
"model_type": "llama",
|
42 |
+
"num_attention_heads": 4,
|
43 |
+
"num_hidden_layers": 2,
|
44 |
+
"num_key_value_heads": 4,
|
45 |
+
"pad_token_id": 3201,
|
46 |
+
"torch_dtype": "float32",
|
47 |
+
"vocab_size": 32002
|
48 |
+
},
|
49 |
+
"tie_word_embeddings": false,
|
50 |
+
"torch_dtype": "float32",
|
51 |
+
"transformers_version": "4.44.2",
|
52 |
+
"use_image_newline_parameter": true,
|
53 |
+
"vision_config": {
|
54 |
+
"attention_dropout": 0.1,
|
55 |
+
"dropout": 0.1,
|
56 |
+
"hidden_size": 32,
|
57 |
+
"image_size": 30,
|
58 |
+
"intermediate_size": 37,
|
59 |
+
"model_type": "clip_vision_model",
|
60 |
+
"num_attention_heads": 4,
|
61 |
+
"num_hidden_layers": 2,
|
62 |
+
"patch_size": 2,
|
63 |
+
"projection_dim": 32
|
64 |
+
},
|
65 |
+
"vision_feature_layer": -2,
|
66 |
+
"vision_feature_select_strategy": "default",
|
67 |
+
"vocab_size": 32002
|
68 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 0,
|
4 |
+
"eos_token_id": 1,
|
5 |
+
"pad_token_id": 1,
|
6 |
+
"transformers_version": "4.44.2"
|
7 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:66020b265c84677d19fc68afc67669f9ff1efce2e8cd8baeea21f520510d2477
|
3 |
+
size 4225912
|
preprocessor_config.json
ADDED
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"aspect_ratio_setting": "anyres",
|
3 |
+
"crop_size": {
|
4 |
+
"height": 30,
|
5 |
+
"width": 30
|
6 |
+
},
|
7 |
+
"image_grid_pinpoints": [
|
8 |
+
[
|
9 |
+
30,
|
10 |
+
60
|
11 |
+
],
|
12 |
+
[
|
13 |
+
60,
|
14 |
+
30
|
15 |
+
],
|
16 |
+
[
|
17 |
+
60,
|
18 |
+
60
|
19 |
+
],
|
20 |
+
[
|
21 |
+
90,
|
22 |
+
30
|
23 |
+
],
|
24 |
+
[
|
25 |
+
30,
|
26 |
+
90
|
27 |
+
]
|
28 |
+
],
|
29 |
+
"do_center_crop": true,
|
30 |
+
"do_convert_rgb": true,
|
31 |
+
"do_normalize": true,
|
32 |
+
"do_rescale": true,
|
33 |
+
"do_resize": true,
|
34 |
+
"image_mean": [
|
35 |
+
0.48145466,
|
36 |
+
0.4578275,
|
37 |
+
0.40821073
|
38 |
+
],
|
39 |
+
"image_processor_type": "LlavaNextImageProcessor",
|
40 |
+
"image_std": [
|
41 |
+
0.26862954,
|
42 |
+
0.26130258,
|
43 |
+
0.27577711
|
44 |
+
],
|
45 |
+
"processor_class": "LlavaNextProcessor",
|
46 |
+
"resample": 3,
|
47 |
+
"rescale_factor": 0.00392156862745098,
|
48 |
+
"size": {
|
49 |
+
"shortest_edge": 30
|
50 |
+
}
|
51 |
+
}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "</s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "<unk>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"unk_token": {
|
24 |
+
"content": "<unk>",
|
25 |
+
"lstrip": false,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
}
|
30 |
+
}
|
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 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"add_prefix_space": null,
|
5 |
+
"added_tokens_decoder": {
|
6 |
+
"0": {
|
7 |
+
"content": "<unk>",
|
8 |
+
"lstrip": false,
|
9 |
+
"normalized": false,
|
10 |
+
"rstrip": false,
|
11 |
+
"single_word": false,
|
12 |
+
"special": true
|
13 |
+
},
|
14 |
+
"1": {
|
15 |
+
"content": "<s>",
|
16 |
+
"lstrip": false,
|
17 |
+
"normalized": false,
|
18 |
+
"rstrip": false,
|
19 |
+
"single_word": false,
|
20 |
+
"special": true
|
21 |
+
},
|
22 |
+
"2": {
|
23 |
+
"content": "</s>",
|
24 |
+
"lstrip": false,
|
25 |
+
"normalized": false,
|
26 |
+
"rstrip": false,
|
27 |
+
"single_word": false,
|
28 |
+
"special": true
|
29 |
+
},
|
30 |
+
"32000": {
|
31 |
+
"content": "<image>",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": false,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false,
|
36 |
+
"special": true
|
37 |
+
},
|
38 |
+
"32001": {
|
39 |
+
"content": "<pad>",
|
40 |
+
"lstrip": false,
|
41 |
+
"normalized": false,
|
42 |
+
"rstrip": false,
|
43 |
+
"single_word": false,
|
44 |
+
"special": true
|
45 |
+
}
|
46 |
+
},
|
47 |
+
"bos_token": "<s>",
|
48 |
+
"clean_up_tokenization_spaces": false,
|
49 |
+
"eos_token": "</s>",
|
50 |
+
"legacy": true,
|
51 |
+
"model_max_length": 2048,
|
52 |
+
"pad_token": "<unk>",
|
53 |
+
"processor_class": "LlavaProcessor",
|
54 |
+
"tokenizer_class": "LlamaTokenizer",
|
55 |
+
"unk_token": "<unk>",
|
56 |
+
"use_default_system_prompt": true
|
57 |
+
}
|