sfsdfsafsddsfsdafsa commited on
Commit
fefe07a
1 Parent(s): 97adf3c

Upload 11 files

Browse files
llama-vid-7b-full-224-long-video-MovieLLM/config.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "./work_dirs/llama-vid/llama-vid-7b-full-224-video-fps-1",
3
+ "architectures": [
4
+ "LlavaLlamaAttForCausalLM"
5
+ ],
6
+ "bert_type": "qformer_pretrain_freeze_all",
7
+ "bos_token_id": 1,
8
+ "compress_type": "mean",
9
+ "eos_token_id": 2,
10
+ "freeze_mm_mlp_adapter": false,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 4096,
13
+ "image_aspect_ratio": "pad",
14
+ "image_grid_pinpoints": null,
15
+ "image_processor": "./llamavid/processor/clip-patch14-224",
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 11008,
18
+ "max_position_embeddings": 4096,
19
+ "max_token": 65536,
20
+ "mm_hidden_size": 1408,
21
+ "mm_projector_type": "mlp2x_gelu",
22
+ "mm_use_im_patch_token": false,
23
+ "mm_use_im_start_end": false,
24
+ "mm_vision_select_feature": "patch",
25
+ "mm_vision_select_layer": -2,
26
+ "mm_vision_tower": "./model_zoo/LAVIS/eva_vit_g.pth",
27
+ "model_type": "llava",
28
+ "num_attention_heads": 32,
29
+ "num_hidden_layers": 32,
30
+ "num_key_value_heads": 32,
31
+ "num_query": 32,
32
+ "pad_token_id": 0,
33
+ "pretraining_tp": 1,
34
+ "rms_norm_eps": 1e-05,
35
+ "rope_scaling": {
36
+ "factor": 16.0,
37
+ "type": "linear"
38
+ },
39
+ "tie_word_embeddings": false,
40
+ "torch_dtype": "float16",
41
+ "transformers_version": "4.31.0",
42
+ "tune_mm_mlp_adapter": false,
43
+ "use_cache": true,
44
+ "use_mm_proj": true,
45
+ "vocab_size": 32000
46
+ }
llama-vid-7b-full-224-long-video-MovieLLM/generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 1,
3
+ "eos_token_id": 2,
4
+ "max_length": 4096,
5
+ "pad_token_id": 0,
6
+ "temperature": 0.9,
7
+ "top_p": 0.6,
8
+ "transformers_version": "4.31.0"
9
+ }
llama-vid-7b-full-224-long-video-MovieLLM/pytorch_model-00001-of-00004.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:744ea3d4803c3bffb96103640179c70960300fc2b9ed47b01dde2e8acfc65615
3
+ size 9878088153
llama-vid-7b-full-224-long-video-MovieLLM/pytorch_model-00002-of-00004.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49a91ffee93f536bffcb88d28a22bdfea33133edca967c463de7c600be97c3f2
3
+ size 9894801014
llama-vid-7b-full-224-long-video-MovieLLM/pytorch_model-00003-of-00004.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:42475da0701b962c99c41ffd28c32a16997c2339f783608312f090533be40897
3
+ size 9994488626
llama-vid-7b-full-224-long-video-MovieLLM/pytorch_model-00004-of-00004.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:19465048c91d3064681bd513c73b84047b2991bd0a8e42b1ac8d447548e56528
3
+ size 1998604747
llama-vid-7b-full-224-long-video-MovieLLM/pytorch_model.bin.index.json ADDED
The diff for this file is too large to render. See raw diff
 
llama-vid-7b-full-224-long-video-MovieLLM/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
+ }
llama-vid-7b-full-224-long-video-MovieLLM/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
llama-vid-7b-full-224-long-video-MovieLLM/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": 65536,
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
+ }
llama-vid-7b-full-224-long-video-MovieLLM/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d35144148c0862d26640c975ea0ffbb7c275b7d6da02a5985676bad5cfc09d87
3
+ size 5691