Ubuntu
commited on
Commit
•
38c7682
1
Parent(s):
c93ec9f
add small files
Browse files- added_tokens.json +8 -0
- config.json +42 -0
- generation_config.json +10 -0
- pytorch_model.bin.index.json +0 -0
- special_tokens_map.json +14 -0
- tokenizer_config.json +76 -0
added_tokens.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<unk>": 0,
|
3 |
+
"<|endoftext|>": 2,
|
4 |
+
"<|im_end|>": 7,
|
5 |
+
"<|im_sep|>": 8,
|
6 |
+
"<|im_start|>": 6,
|
7 |
+
"<|startoftext|>": 1
|
8 |
+
}
|
config.json
ADDED
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "./yi-vl-34b",
|
3 |
+
"architectures": [
|
4 |
+
"LlavaLlamaForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_bias": false,
|
7 |
+
"bos_token_id": 1,
|
8 |
+
"eos_token_id": 2,
|
9 |
+
"freeze_mm_mlp_adapter": false,
|
10 |
+
"hidden_act": "silu",
|
11 |
+
"hidden_size": 7168,
|
12 |
+
"image_aspect_ratio": "pad",
|
13 |
+
"image_grid_pinpoints": null,
|
14 |
+
"initializer_range": 0.02,
|
15 |
+
"intermediate_size": 20480,
|
16 |
+
"max_position_embeddings": 4096,
|
17 |
+
"mm_hidden_size": 1280,
|
18 |
+
"mm_projector_type": "mlp2x_gelu_Norm",
|
19 |
+
"mm_use_im_patch_token": false,
|
20 |
+
"mm_use_im_start_end": false,
|
21 |
+
"mm_vision_select_feature": "patch",
|
22 |
+
"mm_vision_select_layer": -2,
|
23 |
+
"mm_vision_tower": "./vit/clip-vit-H-14-laion2B-s32B-b79K-yi-vl-34B-448",
|
24 |
+
"model_type": "llava",
|
25 |
+
"moe_layer": null,
|
26 |
+
"moe_mode": "easy",
|
27 |
+
"num_attention_heads": 56,
|
28 |
+
"num_hidden_layers": 60,
|
29 |
+
"num_key_value_heads": 8,
|
30 |
+
"pretraining_tp": 1,
|
31 |
+
"rms_norm_eps": 1e-05,
|
32 |
+
"rope_scaling": null,
|
33 |
+
"rope_theta": 5000000.0,
|
34 |
+
"tie_word_embeddings": false,
|
35 |
+
"torch_dtype": "bfloat16",
|
36 |
+
"transformers_version": "4.34.0",
|
37 |
+
"tune_mm_mlp_adapter": false,
|
38 |
+
"tune_vision_tower": true,
|
39 |
+
"use_cache": false,
|
40 |
+
"use_mm_proj": true,
|
41 |
+
"vocab_size": 64000
|
42 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token_id": 1,
|
3 |
+
"do_sample": true,
|
4 |
+
"eos_token_id": 2,
|
5 |
+
"max_length": 4096,
|
6 |
+
"pad_token_id": 0,
|
7 |
+
"temperature": 0.6,
|
8 |
+
"top_p": 0.8,
|
9 |
+
"transformers_version": "4.34.0"
|
10 |
+
}
|
pytorch_model.bin.index.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
special_tokens_map.json
ADDED
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<unk>",
|
4 |
+
"<|startoftext|>",
|
5 |
+
"<|endoftext|>",
|
6 |
+
"<|im_start|>",
|
7 |
+
"<|im_end|>",
|
8 |
+
"<|im_sep|>"
|
9 |
+
],
|
10 |
+
"bos_token": "<|startoftext|>",
|
11 |
+
"eos_token": "<|endoftext|>",
|
12 |
+
"pad_token": "<unk>",
|
13 |
+
"unk_token": "<unk>"
|
14 |
+
}
|
tokenizer_config.json
ADDED
@@ -0,0 +1,76 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": false,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"0": {
|
6 |
+
"content": "<unk>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"1": {
|
14 |
+
"content": "<|startoftext|>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
},
|
21 |
+
"2": {
|
22 |
+
"content": "<|endoftext|>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": false,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false,
|
27 |
+
"special": true
|
28 |
+
},
|
29 |
+
"6": {
|
30 |
+
"content": "<|im_start|>",
|
31 |
+
"lstrip": false,
|
32 |
+
"normalized": false,
|
33 |
+
"rstrip": false,
|
34 |
+
"single_word": false,
|
35 |
+
"special": true
|
36 |
+
},
|
37 |
+
"7": {
|
38 |
+
"content": "<|im_end|>",
|
39 |
+
"lstrip": false,
|
40 |
+
"normalized": false,
|
41 |
+
"rstrip": false,
|
42 |
+
"single_word": false,
|
43 |
+
"special": true
|
44 |
+
},
|
45 |
+
"8": {
|
46 |
+
"content": "<|im_sep|>",
|
47 |
+
"lstrip": false,
|
48 |
+
"normalized": false,
|
49 |
+
"rstrip": false,
|
50 |
+
"single_word": false,
|
51 |
+
"special": true
|
52 |
+
}
|
53 |
+
},
|
54 |
+
"additional_special_tokens": [
|
55 |
+
"<unk>",
|
56 |
+
"<|startoftext|>",
|
57 |
+
"<|endoftext|>",
|
58 |
+
"<|im_start|>",
|
59 |
+
"<|im_end|>",
|
60 |
+
"<|im_sep|>"
|
61 |
+
],
|
62 |
+
"bos_token": "<|startoftext|>",
|
63 |
+
"chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
64 |
+
"clean_up_tokenization_spaces": false,
|
65 |
+
"eos_token": "<|endoftext|>",
|
66 |
+
"legacy": true,
|
67 |
+
"model_max_length": 4096,
|
68 |
+
"pad_token": "<unk>",
|
69 |
+
"padding_side": "right",
|
70 |
+
"sp_model_kwargs": {},
|
71 |
+
"spaces_between_special_tokens": false,
|
72 |
+
"tokenizer_class": "LlamaTokenizer",
|
73 |
+
"tokenizer_file": null,
|
74 |
+
"unk_token": "<unk>",
|
75 |
+
"use_default_system_prompt": true
|
76 |
+
}
|