First model version
Browse files- config.json +56 -0
- model-00001-of-00003.safetensors +3 -0
- model-00002-of-00003.safetensors +3 -0
- model-00003-of-00003.safetensors +3 -0
- model.safetensors.index.json +0 -0
- special_tokens_map.json +24 -0
- tokenizer.model +3 -0
- tokenizer_config.json +42 -0
- trainer_state.json +0 -0
- training_args.bin +3 -0
config.json
ADDED
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "model_zoo/LLM/vicuna/7B-V1.5",
|
3 |
+
"architectures": [
|
4 |
+
"LlavaLlamaUniForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_bias": false,
|
7 |
+
"attention_dropout": 0.0,
|
8 |
+
"aux_img_fold": false,
|
9 |
+
"aux_with_fpn": false,
|
10 |
+
"bos_token_id": 1,
|
11 |
+
"eos_token_id": 2,
|
12 |
+
"freeze_mm_mlp_adapter": false,
|
13 |
+
"hidden_act": "silu",
|
14 |
+
"hidden_size": 4096,
|
15 |
+
"image_aspect_ratio": "pad",
|
16 |
+
"image_global": true,
|
17 |
+
"image_grid": 2,
|
18 |
+
"image_grid_pinpoints": null,
|
19 |
+
"image_size_aux": 1536,
|
20 |
+
"initializer_range": 0.02,
|
21 |
+
"intermediate_size": 11008,
|
22 |
+
"max_position_embeddings": 4096,
|
23 |
+
"mm_hidden_size": 1024,
|
24 |
+
"mm_hidden_size_aux": 2880,
|
25 |
+
"mm_projector_lr": null,
|
26 |
+
"mm_projector_type": "mlp2x_gelu",
|
27 |
+
"mm_use_im_patch_token": false,
|
28 |
+
"mm_use_im_start_end": false,
|
29 |
+
"mm_vision_select_feature": "patch",
|
30 |
+
"mm_vision_select_layer": -2,
|
31 |
+
"mm_vision_tower": "model_zoo/OpenAI/clip-vit-large-patch14-336",
|
32 |
+
"mm_vision_tower_aux": "model_zoo/OpenAI/openclip-convnext-large-d-320-laion2B-s29B-b131K-ft-soup",
|
33 |
+
"model_type": "llava_uni",
|
34 |
+
"num_attention_heads": 32,
|
35 |
+
"num_hidden_layers": 32,
|
36 |
+
"num_key_value_heads": 32,
|
37 |
+
"optimize_vision_tower": false,
|
38 |
+
"optimize_vision_tower_aux": false,
|
39 |
+
"pad_token_id": 0,
|
40 |
+
"pretraining_tp": 1,
|
41 |
+
"rms_norm_eps": 1e-05,
|
42 |
+
"rope_scaling": null,
|
43 |
+
"rope_theta": 10000.0,
|
44 |
+
"tie_word_embeddings": false,
|
45 |
+
"tokenizer_model_max_length": 4096,
|
46 |
+
"tokenizer_padding_side": "right",
|
47 |
+
"torch_dtype": "bfloat16",
|
48 |
+
"transformers_version": "4.36.2",
|
49 |
+
"tune_mm_mlp_adapter": false,
|
50 |
+
"unified_resampler": "simple_sum",
|
51 |
+
"use_cache": true,
|
52 |
+
"use_mm_proj": true,
|
53 |
+
"use_same_im_pos": false,
|
54 |
+
"video_grid": -1,
|
55 |
+
"vocab_size": 32000
|
56 |
+
}
|
model-00001-of-00003.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bd94dac1f11eab1c11195ce63634a6d5d2efb62e94159d652fe34b94e9084c0d
|
3 |
+
size 4938985352
|
model-00002-of-00003.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3486096de9dbf4c322b314ca563a42c2ba6406f9d344547b631a13b5cc5ffc30
|
3 |
+
size 4947390880
|
model-00003-of-00003.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d08f1b8925b88d323ce1af88ead512f71eb6325d10534b769aee7f308230cb1d
|
3 |
+
size 4645953464
|
model.safetensors.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 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
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": "<s>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
},
|
21 |
+
"2": {
|
22 |
+
"content": "</s>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": false,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false,
|
27 |
+
"special": true
|
28 |
+
}
|
29 |
+
},
|
30 |
+
"bos_token": "<s>",
|
31 |
+
"clean_up_tokenization_spaces": false,
|
32 |
+
"eos_token": "</s>",
|
33 |
+
"legacy": false,
|
34 |
+
"model_max_length": 4096,
|
35 |
+
"pad_token": "<unk>",
|
36 |
+
"padding_side": "right",
|
37 |
+
"sp_model_kwargs": {},
|
38 |
+
"spaces_between_special_tokens": false,
|
39 |
+
"tokenizer_class": "LlamaTokenizer",
|
40 |
+
"unk_token": "<unk>",
|
41 |
+
"use_default_system_prompt": false
|
42 |
+
}
|
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:a85eed1e3d559aeaca02b6808bae526281b2b9081421e7ad8c903f5f3e987ab8
|
3 |
+
size 5883
|