Upload folder using huggingface_hub
Browse files- config.json +53 -0
- generation_config.json +9 -0
- pytorch_model-00001-of-00002.bin +3 -0
- pytorch_model-00002-of-00002.bin +3 -0
- pytorch_model.bin.index.json +0 -0
- special_tokens_map.json +24 -0
- tokenizer.model +3 -0
- tokenizer_config.json +35 -0
- trainer_state.json +0 -0
- training_args.bin +3 -0
config.json
ADDED
@@ -0,0 +1,53 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"X": [
|
3 |
+
"Audio_asr",
|
4 |
+
"Audio_caption",
|
5 |
+
"Video",
|
6 |
+
"Image"
|
7 |
+
],
|
8 |
+
"_name_or_path": "/mnt/bn/tns-algo-video-public-my2/wangpeng.an/model/vicuna-7b-v1.5-16k",
|
9 |
+
"architectures": [
|
10 |
+
"LlavaLlamaForCausalLM"
|
11 |
+
],
|
12 |
+
"bos_token_id": 1,
|
13 |
+
"eos_token_id": 2,
|
14 |
+
"freeze_mm_mlp_adapter": false,
|
15 |
+
"hidden_act": "silu",
|
16 |
+
"hidden_size": 4096,
|
17 |
+
"image_aspect_ratio": "pad",
|
18 |
+
"image_grid_pinpoints": null,
|
19 |
+
"initializer_range": 0.02,
|
20 |
+
"intermediate_size": 11008,
|
21 |
+
"is_fusion": false,
|
22 |
+
"max_position_embeddings": 4096,
|
23 |
+
"max_sequence_length": 16384,
|
24 |
+
"mm_audio_caption_tower": "/mnt/bn/tns-algo-video-public-my2/wangpeng.an/model/pretrained_model/LanguageBind_Audio",
|
25 |
+
"mm_audio_tower": "/mnt/bn/tns-algo-video-public-my2/wangpeng.an/model/LanguageBind_Audio_Asr",
|
26 |
+
"mm_hidden_size": 1024,
|
27 |
+
"mm_image_tower": "/mnt/bn/tns-algo-video-public-my2/wangpeng.an/model/pretrained_model/LanguageBind_Image",
|
28 |
+
"mm_projector_type": "mlp2x_gelu",
|
29 |
+
"mm_use_x_patch_token": false,
|
30 |
+
"mm_use_x_start_end": false,
|
31 |
+
"mm_video_tower": "/mnt/bn/tns-algo-video-public-my2/wangpeng.an/model/pretrained_model/LanguageBind_Video_merge",
|
32 |
+
"mm_vision_select_feature": "patch",
|
33 |
+
"mm_vision_select_layer": -2,
|
34 |
+
"model_type": "llava",
|
35 |
+
"num_attention_heads": 32,
|
36 |
+
"num_hidden_layers": 32,
|
37 |
+
"num_key_value_heads": 32,
|
38 |
+
"pad_token_id": 0,
|
39 |
+
"pretraining_tp": 1,
|
40 |
+
"rms_norm_eps": 1e-05,
|
41 |
+
"rope_scaling": {
|
42 |
+
"factor": 4.0,
|
43 |
+
"type": "linear"
|
44 |
+
},
|
45 |
+
"tie_word_embeddings": false,
|
46 |
+
"tokenizer_model_max_length": 3072,
|
47 |
+
"torch_dtype": "bfloat16",
|
48 |
+
"transformers_version": "4.31.0",
|
49 |
+
"tune_mm_mlp_adapter": false,
|
50 |
+
"use_cache": true,
|
51 |
+
"use_mm_proj": true,
|
52 |
+
"vocab_size": 32000
|
53 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token_id": 1,
|
3 |
+
"eos_token_id": 2,
|
4 |
+
"max_length": 16384,
|
5 |
+
"pad_token_id": 0,
|
6 |
+
"temperature": 0.9,
|
7 |
+
"top_p": 0.6,
|
8 |
+
"transformers_version": "4.31.0"
|
9 |
+
}
|
pytorch_model-00001-of-00002.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ae3f5d6e1ed72782ab4a101153abf755ae104b46ac36439a28bd3cbaea517c5d
|
3 |
+
size 9976631973
|
pytorch_model-00002-of-00002.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:632998956bcb8be35d3945effcf3a18d96376704356d19517b6a5cc967781a6e
|
3 |
+
size 6184360270
|
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 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": "<unk>",
|
17 |
+
"unk_token": {
|
18 |
+
"content": "<unk>",
|
19 |
+
"lstrip": false,
|
20 |
+
"normalized": false,
|
21 |
+
"rstrip": false,
|
22 |
+
"single_word": false
|
23 |
+
}
|
24 |
+
}
|
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 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"bos_token": {
|
5 |
+
"__type": "AddedToken",
|
6 |
+
"content": "<s>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false
|
11 |
+
},
|
12 |
+
"clean_up_tokenization_spaces": false,
|
13 |
+
"eos_token": {
|
14 |
+
"__type": "AddedToken",
|
15 |
+
"content": "</s>",
|
16 |
+
"lstrip": false,
|
17 |
+
"normalized": false,
|
18 |
+
"rstrip": false,
|
19 |
+
"single_word": false
|
20 |
+
},
|
21 |
+
"legacy": false,
|
22 |
+
"model_max_length": 2048,
|
23 |
+
"pad_token": null,
|
24 |
+
"padding_side": "right",
|
25 |
+
"sp_model_kwargs": {},
|
26 |
+
"tokenizer_class": "LlamaTokenizer",
|
27 |
+
"unk_token": {
|
28 |
+
"__type": "AddedToken",
|
29 |
+
"content": "<unk>",
|
30 |
+
"lstrip": false,
|
31 |
+
"normalized": false,
|
32 |
+
"rstrip": false,
|
33 |
+
"single_word": false
|
34 |
+
}
|
35 |
+
}
|
trainer_state.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9a9eca08716753172bb2fe5872337203b51af78d727cd9fb2f1fdca65c2caf87
|
3 |
+
size 5944
|