Ubuntu
commited on
Commit
•
d51e87e
1
Parent(s):
a55a3d2
Add large model files
Browse files- ckpts/config.json +39 -0
- ckpts/dino_mm_projector.bin +3 -0
- ckpts/mm_projector.bin +3 -0
- ckpts/trainer_state.json +0 -0
- llava_mae/config.json +39 -0
- llava_mae/generation_config.json +10 -0
- llava_mae/pytorch_model-00001-of-00003.bin +3 -0
- llava_mae/pytorch_model-00002-of-00003.bin +3 -0
- llava_mae/pytorch_model-00003-of-00003.bin +3 -0
- llava_mae/pytorch_model.bin.index.json +0 -0
- llava_mae/special_tokens_map.json +24 -0
- llava_mae/tokenizer.model +3 -0
- llava_mae/tokenizer_config.json +35 -0
- llava_mae/trainer_state.json +0 -0
- llava_mae/training_args.bin +3 -0
ckpts/config.json
ADDED
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "/home/ubuntu/.cache/huggingface/hub/models--lmsys--vicuna-13b-v1.5/snapshots/3deb0106f72a3a433f0c6ea0cb978bdf14bcd3a6",
|
3 |
+
"architectures": [
|
4 |
+
"LlamaForCausalLM"
|
5 |
+
],
|
6 |
+
"bos_token_id": 1,
|
7 |
+
"eos_token_id": 2,
|
8 |
+
"freeze_mm_mlp_adapter": false,
|
9 |
+
"hidden_act": "silu",
|
10 |
+
"hidden_size": 5120,
|
11 |
+
"image_aspect_ratio": "square",
|
12 |
+
"image_grid_pinpoints": null,
|
13 |
+
"initializer_range": 0.02,
|
14 |
+
"intermediate_size": 13824,
|
15 |
+
"max_length": 4096,
|
16 |
+
"max_position_embeddings": 4096,
|
17 |
+
"mm_hidden_size": 1024,
|
18 |
+
"mm_projector_type": "mlp2x_gelu",
|
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": "openai/clip-vit-large-patch14",
|
24 |
+
"model_type": "llava",
|
25 |
+
"num_attention_heads": 40,
|
26 |
+
"num_hidden_layers": 40,
|
27 |
+
"num_key_value_heads": 40,
|
28 |
+
"pad_token_id": 0,
|
29 |
+
"pretraining_tp": 1,
|
30 |
+
"rms_norm_eps": 1e-05,
|
31 |
+
"rope_scaling": null,
|
32 |
+
"tie_word_embeddings": false,
|
33 |
+
"torch_dtype": "float16",
|
34 |
+
"transformers_version": "4.31.0",
|
35 |
+
"tune_mm_mlp_adapter": true,
|
36 |
+
"use_cache": true,
|
37 |
+
"use_mm_proj": true,
|
38 |
+
"vocab_size": 32000
|
39 |
+
}
|
ckpts/dino_mm_projector.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:97b54fc9e779d4db2a04e84cd2931510445ace27dc57e24d2866a1d3303a82f8
|
3 |
+
size 62936731
|
ckpts/mm_projector.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:eeba6ff3894e9a73e3465040e59a8cbde56344684d58fd40ad573e876f8363f8
|
3 |
+
size 125872897
|
ckpts/trainer_state.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
llava_mae/config.json
ADDED
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "/home/ubuntu/.cache/huggingface/hub/models--lmsys--vicuna-13b-v1.5/snapshots/3deb0106f72a3a433f0c6ea0cb978bdf14bcd3a6",
|
3 |
+
"architectures": [
|
4 |
+
"LlavaLlamaForCausalLM"
|
5 |
+
],
|
6 |
+
"bos_token_id": 1,
|
7 |
+
"eos_token_id": 2,
|
8 |
+
"freeze_mm_mlp_adapter": false,
|
9 |
+
"hidden_act": "silu",
|
10 |
+
"hidden_size": 5120,
|
11 |
+
"image_aspect_ratio": "pad",
|
12 |
+
"image_grid_pinpoints": null,
|
13 |
+
"initializer_range": 0.02,
|
14 |
+
"intermediate_size": 13824,
|
15 |
+
"max_length": 4096,
|
16 |
+
"max_position_embeddings": 4096,
|
17 |
+
"mm_hidden_size": 1024,
|
18 |
+
"mm_projector_type": "mlp2x_gelu",
|
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": "openai/clip-vit-large-patch14",
|
24 |
+
"model_type": "llava",
|
25 |
+
"num_attention_heads": 40,
|
26 |
+
"num_hidden_layers": 40,
|
27 |
+
"num_key_value_heads": 40,
|
28 |
+
"pad_token_id": 0,
|
29 |
+
"pretraining_tp": 1,
|
30 |
+
"rms_norm_eps": 1e-05,
|
31 |
+
"rope_scaling": null,
|
32 |
+
"tie_word_embeddings": false,
|
33 |
+
"torch_dtype": "bfloat16",
|
34 |
+
"transformers_version": "4.31.0",
|
35 |
+
"tune_mm_mlp_adapter": false,
|
36 |
+
"use_cache": true,
|
37 |
+
"use_mm_proj": true,
|
38 |
+
"vocab_size": 32000
|
39 |
+
}
|
llava_mae/generation_config.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 1,
|
4 |
+
"eos_token_id": 2,
|
5 |
+
"max_length": 4096,
|
6 |
+
"pad_token_id": 0,
|
7 |
+
"temperature": 0.9,
|
8 |
+
"top_p": 0.6,
|
9 |
+
"transformers_version": "4.31.0"
|
10 |
+
}
|
llava_mae/pytorch_model-00001-of-00003.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3d4ba6e45b23d809f8762b05e67dfb13cad0f2b8faca478c1100b067239e594c
|
3 |
+
size 9948726510
|
llava_mae/pytorch_model-00002-of-00003.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5de51fc264bcd0ce348f7ef8d5fe9cf325fa1d3bd9a7de023ad236403fb0c6a8
|
3 |
+
size 9904162976
|
llava_mae/pytorch_model-00003-of-00003.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0a58a9512cb0b6cb0afae671df4fa697db6e6ae62db968e4859cafb6ed029b14
|
3 |
+
size 8124626347
|
llava_mae/pytorch_model.bin.index.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
llava_mae/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 |
+
}
|
llava_mae/tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
3 |
+
size 499723
|
llava_mae/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 |
+
}
|
llava_mae/trainer_state.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
llava_mae/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ee0aea0549cf97f43e14a2d6d047dbfc2ac926f61d1d318a77abbeb112f08d4b
|
3 |
+
size 5947
|