Upload folder using huggingface_hub
Browse files- llm/config.json +33 -0
- llm/generation_config.json +10 -0
- llm/pytorch_model-00001-of-00007.bin +3 -0
- llm/pytorch_model-00002-of-00007.bin +3 -0
- llm/pytorch_model-00003-of-00007.bin +3 -0
- llm/pytorch_model-00004-of-00007.bin +3 -0
- llm/pytorch_model-00005-of-00007.bin +3 -0
- llm/pytorch_model-00006-of-00007.bin +3 -0
- llm/pytorch_model-00007-of-00007.bin +3 -0
- llm/pytorch_model.bin.index.json +298 -0
- llm/special_tokens_map.json +30 -0
- llm/tokenizer.json +0 -0
- llm/tokenizer.model +3 -0
- llm/tokenizer_config.json +42 -0
- llm_adapter/README.md +204 -0
- llm_adapter/adapter_config.json +31 -0
- llm_adapter/adapter_model.safetensors +3 -0
- projector/config.json +17 -0
- projector/configuration_projector.py +23 -0
- projector/model.safetensors +3 -0
- projector/modeling_projector.py +41 -0
- visual_encoder_adapter/README.md +204 -0
- visual_encoder_adapter/adapter_config.json +33 -0
- visual_encoder_adapter/adapter_model.safetensors +3 -0
- vit/config.json +22 -0
- vit/preprocessor_config.json +27 -0
- vit/pytorch_model-00001-of-00002.bin +3 -0
- vit/pytorch_model-00002-of-00002.bin +3 -0
- vit/pytorch_model.bin.index.json +526 -0
- xtuner_config.py +256 -0
llm/config.json
ADDED
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "lmsys/vicuna-7b-v1.5-16k",
|
3 |
+
"architectures": [
|
4 |
+
"LlamaForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_bias": false,
|
7 |
+
"attention_dropout": 0.0,
|
8 |
+
"bos_token_id": 1,
|
9 |
+
"eos_token_id": 2,
|
10 |
+
"hidden_act": "silu",
|
11 |
+
"hidden_size": 4096,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 11008,
|
14 |
+
"max_position_embeddings": 4096,
|
15 |
+
"max_sequence_length": 16384,
|
16 |
+
"model_type": "llama",
|
17 |
+
"num_attention_heads": 32,
|
18 |
+
"num_hidden_layers": 32,
|
19 |
+
"num_key_value_heads": 32,
|
20 |
+
"pad_token_id": 0,
|
21 |
+
"pretraining_tp": 1,
|
22 |
+
"rms_norm_eps": 1e-05,
|
23 |
+
"rope_scaling": {
|
24 |
+
"factor": 4.0,
|
25 |
+
"type": "linear"
|
26 |
+
},
|
27 |
+
"rope_theta": 10000.0,
|
28 |
+
"tie_word_embeddings": false,
|
29 |
+
"torch_dtype": "float16",
|
30 |
+
"transformers_version": "4.37.2",
|
31 |
+
"use_cache": true,
|
32 |
+
"vocab_size": 32000
|
33 |
+
}
|
llm/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": 16384,
|
6 |
+
"pad_token_id": 0,
|
7 |
+
"temperature": 0.9,
|
8 |
+
"top_p": 0.6,
|
9 |
+
"transformers_version": "4.37.2"
|
10 |
+
}
|
llm/pytorch_model-00001-of-00007.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a5f0930d41985d7ad41560deae0b420fde08ea1137eb5e8e7ae17ed8d959347d
|
3 |
+
size 1981888506
|
llm/pytorch_model-00002-of-00007.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a537aeaafb0642be98e293759ad6228d35e2a0dcd5256d4e545944e9cb7f14b9
|
3 |
+
size 1990294914
|
llm/pytorch_model-00003-of-00007.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3f369b5b02edb0620b9a8b089aeb6bfe8b65d417c135c0636e1ebe45a3dbbf67
|
3 |
+
size 1990294978
|
llm/pytorch_model-00004-of-00007.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:491c8f011be678033613b5a757d25478ae9356d3d0f489711d16ce13be0c0124
|
3 |
+
size 1990294978
|
llm/pytorch_model-00005-of-00007.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:be5d1457665213cbe6d5ba068150530f73043e15e002680bba5caff93fd618b3
|
3 |
+
size 1933654814
|
llm/pytorch_model-00006-of-00007.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3fbb83efac542fc219cebdfd00f1cb6a51e03928d87a7d140e7abd0ed57f711b
|
3 |
+
size 1933671874
|
llm/pytorch_model-00007-of-00007.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e015ce0ac5f9db55a5c21fc17a0b7502b8caa47d2f2d70f571335a5d04e3adaa
|
3 |
+
size 1656835708
|
llm/pytorch_model.bin.index.json
ADDED
@@ -0,0 +1,298 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"metadata": {
|
3 |
+
"total_size": 13476831232
|
4 |
+
},
|
5 |
+
"weight_map": {
|
6 |
+
"lm_head.weight": "pytorch_model-00007-of-00007.bin",
|
7 |
+
"model.embed_tokens.weight": "pytorch_model-00001-of-00007.bin",
|
8 |
+
"model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00007.bin",
|
9 |
+
"model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00007.bin",
|
10 |
+
"model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00007.bin",
|
11 |
+
"model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00007.bin",
|
12 |
+
"model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin",
|
13 |
+
"model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00007.bin",
|
14 |
+
"model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00007.bin",
|
15 |
+
"model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00007.bin",
|
16 |
+
"model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00007.bin",
|
17 |
+
"model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00007.bin",
|
18 |
+
"model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00007.bin",
|
19 |
+
"model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00007.bin",
|
20 |
+
"model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00007.bin",
|
21 |
+
"model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin",
|
22 |
+
"model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00007.bin",
|
23 |
+
"model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00007.bin",
|
24 |
+
"model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00007.bin",
|
25 |
+
"model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00007.bin",
|
26 |
+
"model.layers.10.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
|
27 |
+
"model.layers.10.mlp.down_proj.weight": "pytorch_model-00003-of-00007.bin",
|
28 |
+
"model.layers.10.mlp.gate_proj.weight": "pytorch_model-00003-of-00007.bin",
|
29 |
+
"model.layers.10.mlp.up_proj.weight": "pytorch_model-00003-of-00007.bin",
|
30 |
+
"model.layers.10.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
|
31 |
+
"model.layers.10.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin",
|
32 |
+
"model.layers.10.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin",
|
33 |
+
"model.layers.10.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin",
|
34 |
+
"model.layers.10.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin",
|
35 |
+
"model.layers.11.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
|
36 |
+
"model.layers.11.mlp.down_proj.weight": "pytorch_model-00003-of-00007.bin",
|
37 |
+
"model.layers.11.mlp.gate_proj.weight": "pytorch_model-00003-of-00007.bin",
|
38 |
+
"model.layers.11.mlp.up_proj.weight": "pytorch_model-00003-of-00007.bin",
|
39 |
+
"model.layers.11.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
|
40 |
+
"model.layers.11.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin",
|
41 |
+
"model.layers.11.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin",
|
42 |
+
"model.layers.11.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin",
|
43 |
+
"model.layers.11.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin",
|
44 |
+
"model.layers.12.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
|
45 |
+
"model.layers.12.mlp.down_proj.weight": "pytorch_model-00003-of-00007.bin",
|
46 |
+
"model.layers.12.mlp.gate_proj.weight": "pytorch_model-00003-of-00007.bin",
|
47 |
+
"model.layers.12.mlp.up_proj.weight": "pytorch_model-00003-of-00007.bin",
|
48 |
+
"model.layers.12.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
|
49 |
+
"model.layers.12.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin",
|
50 |
+
"model.layers.12.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin",
|
51 |
+
"model.layers.12.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin",
|
52 |
+
"model.layers.12.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin",
|
53 |
+
"model.layers.13.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
|
54 |
+
"model.layers.13.mlp.down_proj.weight": "pytorch_model-00003-of-00007.bin",
|
55 |
+
"model.layers.13.mlp.gate_proj.weight": "pytorch_model-00003-of-00007.bin",
|
56 |
+
"model.layers.13.mlp.up_proj.weight": "pytorch_model-00003-of-00007.bin",
|
57 |
+
"model.layers.13.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
|
58 |
+
"model.layers.13.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin",
|
59 |
+
"model.layers.13.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin",
|
60 |
+
"model.layers.13.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin",
|
61 |
+
"model.layers.13.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin",
|
62 |
+
"model.layers.14.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
|
63 |
+
"model.layers.14.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin",
|
64 |
+
"model.layers.14.mlp.gate_proj.weight": "pytorch_model-00004-of-00007.bin",
|
65 |
+
"model.layers.14.mlp.up_proj.weight": "pytorch_model-00004-of-00007.bin",
|
66 |
+
"model.layers.14.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
|
67 |
+
"model.layers.14.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin",
|
68 |
+
"model.layers.14.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin",
|
69 |
+
"model.layers.14.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin",
|
70 |
+
"model.layers.14.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin",
|
71 |
+
"model.layers.15.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
|
72 |
+
"model.layers.15.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin",
|
73 |
+
"model.layers.15.mlp.gate_proj.weight": "pytorch_model-00004-of-00007.bin",
|
74 |
+
"model.layers.15.mlp.up_proj.weight": "pytorch_model-00004-of-00007.bin",
|
75 |
+
"model.layers.15.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
|
76 |
+
"model.layers.15.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin",
|
77 |
+
"model.layers.15.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin",
|
78 |
+
"model.layers.15.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin",
|
79 |
+
"model.layers.15.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin",
|
80 |
+
"model.layers.16.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
|
81 |
+
"model.layers.16.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin",
|
82 |
+
"model.layers.16.mlp.gate_proj.weight": "pytorch_model-00004-of-00007.bin",
|
83 |
+
"model.layers.16.mlp.up_proj.weight": "pytorch_model-00004-of-00007.bin",
|
84 |
+
"model.layers.16.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
|
85 |
+
"model.layers.16.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin",
|
86 |
+
"model.layers.16.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin",
|
87 |
+
"model.layers.16.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin",
|
88 |
+
"model.layers.16.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin",
|
89 |
+
"model.layers.17.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
|
90 |
+
"model.layers.17.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin",
|
91 |
+
"model.layers.17.mlp.gate_proj.weight": "pytorch_model-00004-of-00007.bin",
|
92 |
+
"model.layers.17.mlp.up_proj.weight": "pytorch_model-00004-of-00007.bin",
|
93 |
+
"model.layers.17.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
|
94 |
+
"model.layers.17.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin",
|
95 |
+
"model.layers.17.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin",
|
96 |
+
"model.layers.17.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin",
|
97 |
+
"model.layers.17.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin",
|
98 |
+
"model.layers.18.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
|
99 |
+
"model.layers.18.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin",
|
100 |
+
"model.layers.18.mlp.gate_proj.weight": "pytorch_model-00004-of-00007.bin",
|
101 |
+
"model.layers.18.mlp.up_proj.weight": "pytorch_model-00004-of-00007.bin",
|
102 |
+
"model.layers.18.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
|
103 |
+
"model.layers.18.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin",
|
104 |
+
"model.layers.18.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin",
|
105 |
+
"model.layers.18.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin",
|
106 |
+
"model.layers.18.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin",
|
107 |
+
"model.layers.19.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
|
108 |
+
"model.layers.19.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin",
|
109 |
+
"model.layers.19.mlp.gate_proj.weight": "pytorch_model-00005-of-00007.bin",
|
110 |
+
"model.layers.19.mlp.up_proj.weight": "pytorch_model-00005-of-00007.bin",
|
111 |
+
"model.layers.19.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
|
112 |
+
"model.layers.19.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin",
|
113 |
+
"model.layers.19.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin",
|
114 |
+
"model.layers.19.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin",
|
115 |
+
"model.layers.19.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin",
|
116 |
+
"model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00007.bin",
|
117 |
+
"model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00007.bin",
|
118 |
+
"model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00007.bin",
|
119 |
+
"model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00007.bin",
|
120 |
+
"model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin",
|
121 |
+
"model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00007.bin",
|
122 |
+
"model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00007.bin",
|
123 |
+
"model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00007.bin",
|
124 |
+
"model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00007.bin",
|
125 |
+
"model.layers.20.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
|
126 |
+
"model.layers.20.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin",
|
127 |
+
"model.layers.20.mlp.gate_proj.weight": "pytorch_model-00005-of-00007.bin",
|
128 |
+
"model.layers.20.mlp.up_proj.weight": "pytorch_model-00005-of-00007.bin",
|
129 |
+
"model.layers.20.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
|
130 |
+
"model.layers.20.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin",
|
131 |
+
"model.layers.20.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin",
|
132 |
+
"model.layers.20.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin",
|
133 |
+
"model.layers.20.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin",
|
134 |
+
"model.layers.21.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
|
135 |
+
"model.layers.21.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin",
|
136 |
+
"model.layers.21.mlp.gate_proj.weight": "pytorch_model-00005-of-00007.bin",
|
137 |
+
"model.layers.21.mlp.up_proj.weight": "pytorch_model-00005-of-00007.bin",
|
138 |
+
"model.layers.21.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
|
139 |
+
"model.layers.21.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin",
|
140 |
+
"model.layers.21.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin",
|
141 |
+
"model.layers.21.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin",
|
142 |
+
"model.layers.21.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin",
|
143 |
+
"model.layers.22.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
|
144 |
+
"model.layers.22.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin",
|
145 |
+
"model.layers.22.mlp.gate_proj.weight": "pytorch_model-00005-of-00007.bin",
|
146 |
+
"model.layers.22.mlp.up_proj.weight": "pytorch_model-00005-of-00007.bin",
|
147 |
+
"model.layers.22.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
|
148 |
+
"model.layers.22.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin",
|
149 |
+
"model.layers.22.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin",
|
150 |
+
"model.layers.22.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin",
|
151 |
+
"model.layers.22.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin",
|
152 |
+
"model.layers.23.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
|
153 |
+
"model.layers.23.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin",
|
154 |
+
"model.layers.23.mlp.gate_proj.weight": "pytorch_model-00005-of-00007.bin",
|
155 |
+
"model.layers.23.mlp.up_proj.weight": "pytorch_model-00005-of-00007.bin",
|
156 |
+
"model.layers.23.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
|
157 |
+
"model.layers.23.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin",
|
158 |
+
"model.layers.23.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin",
|
159 |
+
"model.layers.23.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin",
|
160 |
+
"model.layers.23.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin",
|
161 |
+
"model.layers.24.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
|
162 |
+
"model.layers.24.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin",
|
163 |
+
"model.layers.24.mlp.gate_proj.weight": "pytorch_model-00006-of-00007.bin",
|
164 |
+
"model.layers.24.mlp.up_proj.weight": "pytorch_model-00006-of-00007.bin",
|
165 |
+
"model.layers.24.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
|
166 |
+
"model.layers.24.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin",
|
167 |
+
"model.layers.24.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin",
|
168 |
+
"model.layers.24.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin",
|
169 |
+
"model.layers.24.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin",
|
170 |
+
"model.layers.25.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
|
171 |
+
"model.layers.25.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin",
|
172 |
+
"model.layers.25.mlp.gate_proj.weight": "pytorch_model-00006-of-00007.bin",
|
173 |
+
"model.layers.25.mlp.up_proj.weight": "pytorch_model-00006-of-00007.bin",
|
174 |
+
"model.layers.25.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
|
175 |
+
"model.layers.25.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin",
|
176 |
+
"model.layers.25.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin",
|
177 |
+
"model.layers.25.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin",
|
178 |
+
"model.layers.25.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin",
|
179 |
+
"model.layers.26.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
|
180 |
+
"model.layers.26.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin",
|
181 |
+
"model.layers.26.mlp.gate_proj.weight": "pytorch_model-00006-of-00007.bin",
|
182 |
+
"model.layers.26.mlp.up_proj.weight": "pytorch_model-00006-of-00007.bin",
|
183 |
+
"model.layers.26.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
|
184 |
+
"model.layers.26.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin",
|
185 |
+
"model.layers.26.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin",
|
186 |
+
"model.layers.26.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin",
|
187 |
+
"model.layers.26.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin",
|
188 |
+
"model.layers.27.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
|
189 |
+
"model.layers.27.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin",
|
190 |
+
"model.layers.27.mlp.gate_proj.weight": "pytorch_model-00006-of-00007.bin",
|
191 |
+
"model.layers.27.mlp.up_proj.weight": "pytorch_model-00006-of-00007.bin",
|
192 |
+
"model.layers.27.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
|
193 |
+
"model.layers.27.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin",
|
194 |
+
"model.layers.27.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin",
|
195 |
+
"model.layers.27.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin",
|
196 |
+
"model.layers.27.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin",
|
197 |
+
"model.layers.28.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
|
198 |
+
"model.layers.28.mlp.down_proj.weight": "pytorch_model-00007-of-00007.bin",
|
199 |
+
"model.layers.28.mlp.gate_proj.weight": "pytorch_model-00006-of-00007.bin",
|
200 |
+
"model.layers.28.mlp.up_proj.weight": "pytorch_model-00007-of-00007.bin",
|
201 |
+
"model.layers.28.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin",
|
202 |
+
"model.layers.28.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin",
|
203 |
+
"model.layers.28.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin",
|
204 |
+
"model.layers.28.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin",
|
205 |
+
"model.layers.28.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin",
|
206 |
+
"model.layers.29.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
|
207 |
+
"model.layers.29.mlp.down_proj.weight": "pytorch_model-00007-of-00007.bin",
|
208 |
+
"model.layers.29.mlp.gate_proj.weight": "pytorch_model-00007-of-00007.bin",
|
209 |
+
"model.layers.29.mlp.up_proj.weight": "pytorch_model-00007-of-00007.bin",
|
210 |
+
"model.layers.29.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin",
|
211 |
+
"model.layers.29.self_attn.k_proj.weight": "pytorch_model-00007-of-00007.bin",
|
212 |
+
"model.layers.29.self_attn.o_proj.weight": "pytorch_model-00007-of-00007.bin",
|
213 |
+
"model.layers.29.self_attn.q_proj.weight": "pytorch_model-00007-of-00007.bin",
|
214 |
+
"model.layers.29.self_attn.v_proj.weight": "pytorch_model-00007-of-00007.bin",
|
215 |
+
"model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00007.bin",
|
216 |
+
"model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00007.bin",
|
217 |
+
"model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00007.bin",
|
218 |
+
"model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00007.bin",
|
219 |
+
"model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin",
|
220 |
+
"model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00007.bin",
|
221 |
+
"model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00007.bin",
|
222 |
+
"model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00007.bin",
|
223 |
+
"model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00007.bin",
|
224 |
+
"model.layers.30.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
|
225 |
+
"model.layers.30.mlp.down_proj.weight": "pytorch_model-00007-of-00007.bin",
|
226 |
+
"model.layers.30.mlp.gate_proj.weight": "pytorch_model-00007-of-00007.bin",
|
227 |
+
"model.layers.30.mlp.up_proj.weight": "pytorch_model-00007-of-00007.bin",
|
228 |
+
"model.layers.30.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin",
|
229 |
+
"model.layers.30.self_attn.k_proj.weight": "pytorch_model-00007-of-00007.bin",
|
230 |
+
"model.layers.30.self_attn.o_proj.weight": "pytorch_model-00007-of-00007.bin",
|
231 |
+
"model.layers.30.self_attn.q_proj.weight": "pytorch_model-00007-of-00007.bin",
|
232 |
+
"model.layers.30.self_attn.v_proj.weight": "pytorch_model-00007-of-00007.bin",
|
233 |
+
"model.layers.31.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
|
234 |
+
"model.layers.31.mlp.down_proj.weight": "pytorch_model-00007-of-00007.bin",
|
235 |
+
"model.layers.31.mlp.gate_proj.weight": "pytorch_model-00007-of-00007.bin",
|
236 |
+
"model.layers.31.mlp.up_proj.weight": "pytorch_model-00007-of-00007.bin",
|
237 |
+
"model.layers.31.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin",
|
238 |
+
"model.layers.31.self_attn.k_proj.weight": "pytorch_model-00007-of-00007.bin",
|
239 |
+
"model.layers.31.self_attn.o_proj.weight": "pytorch_model-00007-of-00007.bin",
|
240 |
+
"model.layers.31.self_attn.q_proj.weight": "pytorch_model-00007-of-00007.bin",
|
241 |
+
"model.layers.31.self_attn.v_proj.weight": "pytorch_model-00007-of-00007.bin",
|
242 |
+
"model.layers.4.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
|
243 |
+
"model.layers.4.mlp.down_proj.weight": "pytorch_model-00002-of-00007.bin",
|
244 |
+
"model.layers.4.mlp.gate_proj.weight": "pytorch_model-00002-of-00007.bin",
|
245 |
+
"model.layers.4.mlp.up_proj.weight": "pytorch_model-00002-of-00007.bin",
|
246 |
+
"model.layers.4.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
|
247 |
+
"model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00007.bin",
|
248 |
+
"model.layers.4.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin",
|
249 |
+
"model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00007.bin",
|
250 |
+
"model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00007.bin",
|
251 |
+
"model.layers.5.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
|
252 |
+
"model.layers.5.mlp.down_proj.weight": "pytorch_model-00002-of-00007.bin",
|
253 |
+
"model.layers.5.mlp.gate_proj.weight": "pytorch_model-00002-of-00007.bin",
|
254 |
+
"model.layers.5.mlp.up_proj.weight": "pytorch_model-00002-of-00007.bin",
|
255 |
+
"model.layers.5.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
|
256 |
+
"model.layers.5.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin",
|
257 |
+
"model.layers.5.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin",
|
258 |
+
"model.layers.5.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin",
|
259 |
+
"model.layers.5.self_attn.v_proj.weight": "pytorch_model-00002-of-00007.bin",
|
260 |
+
"model.layers.6.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
|
261 |
+
"model.layers.6.mlp.down_proj.weight": "pytorch_model-00002-of-00007.bin",
|
262 |
+
"model.layers.6.mlp.gate_proj.weight": "pytorch_model-00002-of-00007.bin",
|
263 |
+
"model.layers.6.mlp.up_proj.weight": "pytorch_model-00002-of-00007.bin",
|
264 |
+
"model.layers.6.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
|
265 |
+
"model.layers.6.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin",
|
266 |
+
"model.layers.6.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin",
|
267 |
+
"model.layers.6.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin",
|
268 |
+
"model.layers.6.self_attn.v_proj.weight": "pytorch_model-00002-of-00007.bin",
|
269 |
+
"model.layers.7.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
|
270 |
+
"model.layers.7.mlp.down_proj.weight": "pytorch_model-00002-of-00007.bin",
|
271 |
+
"model.layers.7.mlp.gate_proj.weight": "pytorch_model-00002-of-00007.bin",
|
272 |
+
"model.layers.7.mlp.up_proj.weight": "pytorch_model-00002-of-00007.bin",
|
273 |
+
"model.layers.7.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
|
274 |
+
"model.layers.7.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin",
|
275 |
+
"model.layers.7.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin",
|
276 |
+
"model.layers.7.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin",
|
277 |
+
"model.layers.7.self_attn.v_proj.weight": "pytorch_model-00002-of-00007.bin",
|
278 |
+
"model.layers.8.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
|
279 |
+
"model.layers.8.mlp.down_proj.weight": "pytorch_model-00002-of-00007.bin",
|
280 |
+
"model.layers.8.mlp.gate_proj.weight": "pytorch_model-00002-of-00007.bin",
|
281 |
+
"model.layers.8.mlp.up_proj.weight": "pytorch_model-00002-of-00007.bin",
|
282 |
+
"model.layers.8.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
|
283 |
+
"model.layers.8.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin",
|
284 |
+
"model.layers.8.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin",
|
285 |
+
"model.layers.8.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin",
|
286 |
+
"model.layers.8.self_attn.v_proj.weight": "pytorch_model-00002-of-00007.bin",
|
287 |
+
"model.layers.9.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
|
288 |
+
"model.layers.9.mlp.down_proj.weight": "pytorch_model-00003-of-00007.bin",
|
289 |
+
"model.layers.9.mlp.gate_proj.weight": "pytorch_model-00003-of-00007.bin",
|
290 |
+
"model.layers.9.mlp.up_proj.weight": "pytorch_model-00003-of-00007.bin",
|
291 |
+
"model.layers.9.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
|
292 |
+
"model.layers.9.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin",
|
293 |
+
"model.layers.9.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin",
|
294 |
+
"model.layers.9.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin",
|
295 |
+
"model.layers.9.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin",
|
296 |
+
"model.norm.weight": "pytorch_model-00007-of-00007.bin"
|
297 |
+
}
|
298 |
+
}
|
llm/special_tokens_map.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": {
|
17 |
+
"content": "<unk>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"unk_token": {
|
24 |
+
"content": "<unk>",
|
25 |
+
"lstrip": false,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
}
|
30 |
+
}
|
llm/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
llm/tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
3 |
+
size 499723
|
llm/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": 16384,
|
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 |
+
}
|
llm_adapter/README.md
ADDED
@@ -0,0 +1,204 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: peft
|
3 |
+
base_model: lmsys/vicuna-7b-v1.5-16k
|
4 |
+
---
|
5 |
+
|
6 |
+
# Model Card for Model ID
|
7 |
+
|
8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
9 |
+
|
10 |
+
|
11 |
+
|
12 |
+
## Model Details
|
13 |
+
|
14 |
+
### Model Description
|
15 |
+
|
16 |
+
<!-- Provide a longer summary of what this model is. -->
|
17 |
+
|
18 |
+
|
19 |
+
|
20 |
+
- **Developed by:** [More Information Needed]
|
21 |
+
- **Funded by [optional]:** [More Information Needed]
|
22 |
+
- **Shared by [optional]:** [More Information Needed]
|
23 |
+
- **Model type:** [More Information Needed]
|
24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
25 |
+
- **License:** [More Information Needed]
|
26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
27 |
+
|
28 |
+
### Model Sources [optional]
|
29 |
+
|
30 |
+
<!-- Provide the basic links for the model. -->
|
31 |
+
|
32 |
+
- **Repository:** [More Information Needed]
|
33 |
+
- **Paper [optional]:** [More Information Needed]
|
34 |
+
- **Demo [optional]:** [More Information Needed]
|
35 |
+
|
36 |
+
## Uses
|
37 |
+
|
38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
39 |
+
|
40 |
+
### Direct Use
|
41 |
+
|
42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
43 |
+
|
44 |
+
[More Information Needed]
|
45 |
+
|
46 |
+
### Downstream Use [optional]
|
47 |
+
|
48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
49 |
+
|
50 |
+
[More Information Needed]
|
51 |
+
|
52 |
+
### Out-of-Scope Use
|
53 |
+
|
54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
55 |
+
|
56 |
+
[More Information Needed]
|
57 |
+
|
58 |
+
## Bias, Risks, and Limitations
|
59 |
+
|
60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
61 |
+
|
62 |
+
[More Information Needed]
|
63 |
+
|
64 |
+
### Recommendations
|
65 |
+
|
66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
67 |
+
|
68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
69 |
+
|
70 |
+
## How to Get Started with the Model
|
71 |
+
|
72 |
+
Use the code below to get started with the model.
|
73 |
+
|
74 |
+
[More Information Needed]
|
75 |
+
|
76 |
+
## Training Details
|
77 |
+
|
78 |
+
### Training Data
|
79 |
+
|
80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
81 |
+
|
82 |
+
[More Information Needed]
|
83 |
+
|
84 |
+
### Training Procedure
|
85 |
+
|
86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
87 |
+
|
88 |
+
#### Preprocessing [optional]
|
89 |
+
|
90 |
+
[More Information Needed]
|
91 |
+
|
92 |
+
|
93 |
+
#### Training Hyperparameters
|
94 |
+
|
95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
96 |
+
|
97 |
+
#### Speeds, Sizes, Times [optional]
|
98 |
+
|
99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
100 |
+
|
101 |
+
[More Information Needed]
|
102 |
+
|
103 |
+
## Evaluation
|
104 |
+
|
105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
106 |
+
|
107 |
+
### Testing Data, Factors & Metrics
|
108 |
+
|
109 |
+
#### Testing Data
|
110 |
+
|
111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
112 |
+
|
113 |
+
[More Information Needed]
|
114 |
+
|
115 |
+
#### Factors
|
116 |
+
|
117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
118 |
+
|
119 |
+
[More Information Needed]
|
120 |
+
|
121 |
+
#### Metrics
|
122 |
+
|
123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
124 |
+
|
125 |
+
[More Information Needed]
|
126 |
+
|
127 |
+
### Results
|
128 |
+
|
129 |
+
[More Information Needed]
|
130 |
+
|
131 |
+
#### Summary
|
132 |
+
|
133 |
+
|
134 |
+
|
135 |
+
## Model Examination [optional]
|
136 |
+
|
137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
138 |
+
|
139 |
+
[More Information Needed]
|
140 |
+
|
141 |
+
## Environmental Impact
|
142 |
+
|
143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
144 |
+
|
145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
146 |
+
|
147 |
+
- **Hardware Type:** [More Information Needed]
|
148 |
+
- **Hours used:** [More Information Needed]
|
149 |
+
- **Cloud Provider:** [More Information Needed]
|
150 |
+
- **Compute Region:** [More Information Needed]
|
151 |
+
- **Carbon Emitted:** [More Information Needed]
|
152 |
+
|
153 |
+
## Technical Specifications [optional]
|
154 |
+
|
155 |
+
### Model Architecture and Objective
|
156 |
+
|
157 |
+
[More Information Needed]
|
158 |
+
|
159 |
+
### Compute Infrastructure
|
160 |
+
|
161 |
+
[More Information Needed]
|
162 |
+
|
163 |
+
#### Hardware
|
164 |
+
|
165 |
+
[More Information Needed]
|
166 |
+
|
167 |
+
#### Software
|
168 |
+
|
169 |
+
[More Information Needed]
|
170 |
+
|
171 |
+
## Citation [optional]
|
172 |
+
|
173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
174 |
+
|
175 |
+
**BibTeX:**
|
176 |
+
|
177 |
+
[More Information Needed]
|
178 |
+
|
179 |
+
**APA:**
|
180 |
+
|
181 |
+
[More Information Needed]
|
182 |
+
|
183 |
+
## Glossary [optional]
|
184 |
+
|
185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
186 |
+
|
187 |
+
[More Information Needed]
|
188 |
+
|
189 |
+
## More Information [optional]
|
190 |
+
|
191 |
+
[More Information Needed]
|
192 |
+
|
193 |
+
## Model Card Authors [optional]
|
194 |
+
|
195 |
+
[More Information Needed]
|
196 |
+
|
197 |
+
## Model Card Contact
|
198 |
+
|
199 |
+
[More Information Needed]
|
200 |
+
|
201 |
+
|
202 |
+
### Framework versions
|
203 |
+
|
204 |
+
- PEFT 0.7.1
|
llm_adapter/adapter_config.json
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "lmsys/vicuna-7b-v1.5-16k",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": false,
|
7 |
+
"inference_mode": true,
|
8 |
+
"init_lora_weights": true,
|
9 |
+
"layers_pattern": null,
|
10 |
+
"layers_to_transform": null,
|
11 |
+
"loftq_config": {},
|
12 |
+
"lora_alpha": 256,
|
13 |
+
"lora_dropout": 0.05,
|
14 |
+
"megatron_config": null,
|
15 |
+
"megatron_core": "megatron.core",
|
16 |
+
"modules_to_save": null,
|
17 |
+
"peft_type": "LORA",
|
18 |
+
"r": 512,
|
19 |
+
"rank_pattern": {},
|
20 |
+
"revision": null,
|
21 |
+
"target_modules": [
|
22 |
+
"k_proj",
|
23 |
+
"q_proj",
|
24 |
+
"up_proj",
|
25 |
+
"v_proj",
|
26 |
+
"down_proj",
|
27 |
+
"gate_proj",
|
28 |
+
"o_proj"
|
29 |
+
],
|
30 |
+
"task_type": "CAUSAL_LM"
|
31 |
+
}
|
llm_adapter/adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2d6c537e3423a9fe2e02094b3b3996a86c25aa59b033231b682ad2da630c4e1f
|
3 |
+
size 2558587064
|
projector/config.json
ADDED
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"ProjectorModel"
|
4 |
+
],
|
5 |
+
"auto_map": {
|
6 |
+
"AutoConfig": "configuration_projector.ProjectorConfig",
|
7 |
+
"AutoModel": "modeling_projector.ProjectorModel"
|
8 |
+
},
|
9 |
+
"bias": true,
|
10 |
+
"depth": 2,
|
11 |
+
"hidden_act": "gelu",
|
12 |
+
"llm_hidden_size": 4096,
|
13 |
+
"model_type": "projector",
|
14 |
+
"torch_dtype": "float32",
|
15 |
+
"transformers_version": "4.37.2",
|
16 |
+
"visual_hidden_size": 1280
|
17 |
+
}
|
projector/configuration_projector.py
ADDED
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
# Copyright (c) OpenMMLab. All rights reserved.
|
2 |
+
from transformers import PretrainedConfig
|
3 |
+
|
4 |
+
|
5 |
+
class ProjectorConfig(PretrainedConfig):
|
6 |
+
model_type = "projector"
|
7 |
+
_auto_class = "AutoConfig"
|
8 |
+
|
9 |
+
def __init__(
|
10 |
+
self,
|
11 |
+
visual_hidden_size=4096,
|
12 |
+
llm_hidden_size=4096,
|
13 |
+
depth=2,
|
14 |
+
hidden_act="gelu",
|
15 |
+
bias=True,
|
16 |
+
**kwargs,
|
17 |
+
):
|
18 |
+
self.visual_hidden_size = visual_hidden_size
|
19 |
+
self.llm_hidden_size = llm_hidden_size
|
20 |
+
self.depth = depth
|
21 |
+
self.hidden_act = hidden_act
|
22 |
+
self.bias = bias
|
23 |
+
super().__init__(**kwargs)
|
projector/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a2b805fdce8968993d54e23535ff93f113833a35d6c3b629e82ce7fcbf2943c5
|
3 |
+
size 88113520
|
projector/modeling_projector.py
ADDED
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
# Copyright (c) OpenMMLab. All rights reserved.
|
2 |
+
import torch
|
3 |
+
import torch.nn as nn
|
4 |
+
from transformers import PreTrainedModel
|
5 |
+
from transformers.activations import ACT2FN
|
6 |
+
|
7 |
+
from .configuration_projector import ProjectorConfig
|
8 |
+
|
9 |
+
|
10 |
+
class ProjectorModel(PreTrainedModel):
|
11 |
+
_auto_class = "AutoModel"
|
12 |
+
config_class = ProjectorConfig
|
13 |
+
base_model_prefix = "model"
|
14 |
+
supports_gradient_checkpointing = True
|
15 |
+
|
16 |
+
def __init__(self, config: ProjectorConfig) -> None:
|
17 |
+
super().__init__(config)
|
18 |
+
self.gradient_checkpointing = False
|
19 |
+
|
20 |
+
modules = [nn.Linear(config.visual_hidden_size, config.llm_hidden_size, bias=config.bias)]
|
21 |
+
for _ in range(1, config.depth):
|
22 |
+
modules.append(ACT2FN[config.hidden_act])
|
23 |
+
modules.append(nn.Linear(config.llm_hidden_size, config.llm_hidden_size, bias=config.bias))
|
24 |
+
self.model = nn.Sequential(*modules)
|
25 |
+
|
26 |
+
def enable_input_require_grads(self):
|
27 |
+
def make_inputs_require_grad(module, input, output):
|
28 |
+
output.requires_grad_(True)
|
29 |
+
|
30 |
+
self.model.register_forward_hook(make_inputs_require_grad)
|
31 |
+
|
32 |
+
def _set_gradient_checkpointing(self, module, value=False):
|
33 |
+
if isinstance(module, ProjectorModel):
|
34 |
+
module.gradient_checkpointing = value
|
35 |
+
|
36 |
+
def forward(self, x):
|
37 |
+
if self.gradient_checkpointing and self.training:
|
38 |
+
layer_outputs = torch.utils.checkpoint.checkpoint(self.model, x)
|
39 |
+
else:
|
40 |
+
layer_outputs = self.model(x)
|
41 |
+
return layer_outputs
|
visual_encoder_adapter/README.md
ADDED
@@ -0,0 +1,204 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: peft
|
3 |
+
base_model: apple/DFN5B-CLIP-ViT-H-14-378
|
4 |
+
---
|
5 |
+
|
6 |
+
# Model Card for Model ID
|
7 |
+
|
8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
9 |
+
|
10 |
+
|
11 |
+
|
12 |
+
## Model Details
|
13 |
+
|
14 |
+
### Model Description
|
15 |
+
|
16 |
+
<!-- Provide a longer summary of what this model is. -->
|
17 |
+
|
18 |
+
|
19 |
+
|
20 |
+
- **Developed by:** [More Information Needed]
|
21 |
+
- **Funded by [optional]:** [More Information Needed]
|
22 |
+
- **Shared by [optional]:** [More Information Needed]
|
23 |
+
- **Model type:** [More Information Needed]
|
24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
25 |
+
- **License:** [More Information Needed]
|
26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
27 |
+
|
28 |
+
### Model Sources [optional]
|
29 |
+
|
30 |
+
<!-- Provide the basic links for the model. -->
|
31 |
+
|
32 |
+
- **Repository:** [More Information Needed]
|
33 |
+
- **Paper [optional]:** [More Information Needed]
|
34 |
+
- **Demo [optional]:** [More Information Needed]
|
35 |
+
|
36 |
+
## Uses
|
37 |
+
|
38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
39 |
+
|
40 |
+
### Direct Use
|
41 |
+
|
42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
43 |
+
|
44 |
+
[More Information Needed]
|
45 |
+
|
46 |
+
### Downstream Use [optional]
|
47 |
+
|
48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
49 |
+
|
50 |
+
[More Information Needed]
|
51 |
+
|
52 |
+
### Out-of-Scope Use
|
53 |
+
|
54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
55 |
+
|
56 |
+
[More Information Needed]
|
57 |
+
|
58 |
+
## Bias, Risks, and Limitations
|
59 |
+
|
60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
61 |
+
|
62 |
+
[More Information Needed]
|
63 |
+
|
64 |
+
### Recommendations
|
65 |
+
|
66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
67 |
+
|
68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
69 |
+
|
70 |
+
## How to Get Started with the Model
|
71 |
+
|
72 |
+
Use the code below to get started with the model.
|
73 |
+
|
74 |
+
[More Information Needed]
|
75 |
+
|
76 |
+
## Training Details
|
77 |
+
|
78 |
+
### Training Data
|
79 |
+
|
80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
81 |
+
|
82 |
+
[More Information Needed]
|
83 |
+
|
84 |
+
### Training Procedure
|
85 |
+
|
86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
87 |
+
|
88 |
+
#### Preprocessing [optional]
|
89 |
+
|
90 |
+
[More Information Needed]
|
91 |
+
|
92 |
+
|
93 |
+
#### Training Hyperparameters
|
94 |
+
|
95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
96 |
+
|
97 |
+
#### Speeds, Sizes, Times [optional]
|
98 |
+
|
99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
100 |
+
|
101 |
+
[More Information Needed]
|
102 |
+
|
103 |
+
## Evaluation
|
104 |
+
|
105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
106 |
+
|
107 |
+
### Testing Data, Factors & Metrics
|
108 |
+
|
109 |
+
#### Testing Data
|
110 |
+
|
111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
112 |
+
|
113 |
+
[More Information Needed]
|
114 |
+
|
115 |
+
#### Factors
|
116 |
+
|
117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
118 |
+
|
119 |
+
[More Information Needed]
|
120 |
+
|
121 |
+
#### Metrics
|
122 |
+
|
123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
124 |
+
|
125 |
+
[More Information Needed]
|
126 |
+
|
127 |
+
### Results
|
128 |
+
|
129 |
+
[More Information Needed]
|
130 |
+
|
131 |
+
#### Summary
|
132 |
+
|
133 |
+
|
134 |
+
|
135 |
+
## Model Examination [optional]
|
136 |
+
|
137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
138 |
+
|
139 |
+
[More Information Needed]
|
140 |
+
|
141 |
+
## Environmental Impact
|
142 |
+
|
143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
144 |
+
|
145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
146 |
+
|
147 |
+
- **Hardware Type:** [More Information Needed]
|
148 |
+
- **Hours used:** [More Information Needed]
|
149 |
+
- **Cloud Provider:** [More Information Needed]
|
150 |
+
- **Compute Region:** [More Information Needed]
|
151 |
+
- **Carbon Emitted:** [More Information Needed]
|
152 |
+
|
153 |
+
## Technical Specifications [optional]
|
154 |
+
|
155 |
+
### Model Architecture and Objective
|
156 |
+
|
157 |
+
[More Information Needed]
|
158 |
+
|
159 |
+
### Compute Infrastructure
|
160 |
+
|
161 |
+
[More Information Needed]
|
162 |
+
|
163 |
+
#### Hardware
|
164 |
+
|
165 |
+
[More Information Needed]
|
166 |
+
|
167 |
+
#### Software
|
168 |
+
|
169 |
+
[More Information Needed]
|
170 |
+
|
171 |
+
## Citation [optional]
|
172 |
+
|
173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
174 |
+
|
175 |
+
**BibTeX:**
|
176 |
+
|
177 |
+
[More Information Needed]
|
178 |
+
|
179 |
+
**APA:**
|
180 |
+
|
181 |
+
[More Information Needed]
|
182 |
+
|
183 |
+
## Glossary [optional]
|
184 |
+
|
185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
186 |
+
|
187 |
+
[More Information Needed]
|
188 |
+
|
189 |
+
## More Information [optional]
|
190 |
+
|
191 |
+
[More Information Needed]
|
192 |
+
|
193 |
+
## Model Card Authors [optional]
|
194 |
+
|
195 |
+
[More Information Needed]
|
196 |
+
|
197 |
+
## Model Card Contact
|
198 |
+
|
199 |
+
[More Information Needed]
|
200 |
+
|
201 |
+
|
202 |
+
### Framework versions
|
203 |
+
|
204 |
+
- PEFT 0.7.1
|
visual_encoder_adapter/adapter_config.json
ADDED
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": {
|
4 |
+
"base_model_class": "PikaVidEncoder",
|
5 |
+
"parent_library": "xtuner.model.video_encoder"
|
6 |
+
},
|
7 |
+
"base_model_name_or_path": "apple/DFN5B-CLIP-ViT-H-14-378",
|
8 |
+
"bias": "none",
|
9 |
+
"fan_in_fan_out": false,
|
10 |
+
"inference_mode": true,
|
11 |
+
"init_lora_weights": true,
|
12 |
+
"layers_pattern": null,
|
13 |
+
"layers_to_transform": null,
|
14 |
+
"loftq_config": {},
|
15 |
+
"lora_alpha": 16,
|
16 |
+
"lora_dropout": 0.05,
|
17 |
+
"megatron_config": null,
|
18 |
+
"megatron_core": "megatron.core",
|
19 |
+
"modules_to_save": null,
|
20 |
+
"peft_type": "LORA",
|
21 |
+
"r": 64,
|
22 |
+
"rank_pattern": {},
|
23 |
+
"revision": null,
|
24 |
+
"target_modules": [
|
25 |
+
"k_proj",
|
26 |
+
"fc1",
|
27 |
+
"fc2",
|
28 |
+
"q_proj",
|
29 |
+
"v_proj",
|
30 |
+
"out_proj"
|
31 |
+
],
|
32 |
+
"task_type": null
|
33 |
+
}
|
visual_encoder_adapter/adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:07d6cc5058d81b85ce7c06affe42ba6c3f7724178cbdef6efb773c4e92003c51
|
3 |
+
size 188800496
|
vit/config.json
ADDED
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "apple/DFN5B-CLIP-ViT-H-14-378",
|
3 |
+
"architectures": [
|
4 |
+
"CLIPVisionModel"
|
5 |
+
],
|
6 |
+
"attention_dropout": 0.0,
|
7 |
+
"hidden_act": "quick_gelu",
|
8 |
+
"hidden_size": 1280,
|
9 |
+
"image_size": 378,
|
10 |
+
"initializer_factor": 1.0,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"intermediate_size": 5120,
|
13 |
+
"layer_norm_eps": 1e-05,
|
14 |
+
"model_type": "clip_vision_model",
|
15 |
+
"num_attention_heads": 16,
|
16 |
+
"num_channels": 3,
|
17 |
+
"num_hidden_layers": 32,
|
18 |
+
"patch_size": 14,
|
19 |
+
"projection_dim": 512,
|
20 |
+
"torch_dtype": "float32",
|
21 |
+
"transformers_version": "4.37.2"
|
22 |
+
}
|
vit/preprocessor_config.json
ADDED
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"crop_size": {
|
3 |
+
"height": 378,
|
4 |
+
"width": 378
|
5 |
+
},
|
6 |
+
"do_center_crop": true,
|
7 |
+
"do_convert_rgb": true,
|
8 |
+
"do_normalize": true,
|
9 |
+
"do_rescale": true,
|
10 |
+
"do_resize": true,
|
11 |
+
"image_mean": [
|
12 |
+
0.48145466,
|
13 |
+
0.4578275,
|
14 |
+
0.40821073
|
15 |
+
],
|
16 |
+
"image_processor_type": "CLIPImageProcessor",
|
17 |
+
"image_std": [
|
18 |
+
0.26862954,
|
19 |
+
0.26130258,
|
20 |
+
0.27577711
|
21 |
+
],
|
22 |
+
"resample": 3,
|
23 |
+
"rescale_factor": 0.00392156862745098,
|
24 |
+
"size": {
|
25 |
+
"shortest_edge": 378
|
26 |
+
}
|
27 |
+
}
|
vit/pytorch_model-00001-of-00002.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8b57623d22174038e0d60e66f4b0c64b834e88d7d3159f10ea2ae02213b67cb7
|
3 |
+
size 1994332295
|
vit/pytorch_model-00002-of-00002.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2d2af6f3129761250a4b0be44b53fbd4aef509cd897c6c8484c723cc69acd82f
|
3 |
+
size 531341514
|
vit/pytorch_model.bin.index.json
ADDED
@@ -0,0 +1,526 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"metadata": {
|
3 |
+
"total_size": 2525486080
|
4 |
+
},
|
5 |
+
"weight_map": {
|
6 |
+
"vision_model.embeddings.class_embedding": "pytorch_model-00001-of-00002.bin",
|
7 |
+
"vision_model.embeddings.patch_embedding.weight": "pytorch_model-00001-of-00002.bin",
|
8 |
+
"vision_model.embeddings.position_embedding.weight": "pytorch_model-00001-of-00002.bin",
|
9 |
+
"vision_model.encoder.layers.0.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
|
10 |
+
"vision_model.encoder.layers.0.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
|
11 |
+
"vision_model.encoder.layers.0.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
|
12 |
+
"vision_model.encoder.layers.0.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
|
13 |
+
"vision_model.encoder.layers.0.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
|
14 |
+
"vision_model.encoder.layers.0.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
15 |
+
"vision_model.encoder.layers.0.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
|
16 |
+
"vision_model.encoder.layers.0.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
17 |
+
"vision_model.encoder.layers.0.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
|
18 |
+
"vision_model.encoder.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
19 |
+
"vision_model.encoder.layers.0.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
|
20 |
+
"vision_model.encoder.layers.0.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
21 |
+
"vision_model.encoder.layers.0.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
|
22 |
+
"vision_model.encoder.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
23 |
+
"vision_model.encoder.layers.0.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
|
24 |
+
"vision_model.encoder.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
25 |
+
"vision_model.encoder.layers.1.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
|
26 |
+
"vision_model.encoder.layers.1.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
|
27 |
+
"vision_model.encoder.layers.1.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
|
28 |
+
"vision_model.encoder.layers.1.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
|
29 |
+
"vision_model.encoder.layers.1.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
|
30 |
+
"vision_model.encoder.layers.1.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
31 |
+
"vision_model.encoder.layers.1.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
|
32 |
+
"vision_model.encoder.layers.1.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
33 |
+
"vision_model.encoder.layers.1.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
|
34 |
+
"vision_model.encoder.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
35 |
+
"vision_model.encoder.layers.1.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
|
36 |
+
"vision_model.encoder.layers.1.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
37 |
+
"vision_model.encoder.layers.1.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
|
38 |
+
"vision_model.encoder.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
39 |
+
"vision_model.encoder.layers.1.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
|
40 |
+
"vision_model.encoder.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
41 |
+
"vision_model.encoder.layers.10.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
|
42 |
+
"vision_model.encoder.layers.10.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
|
43 |
+
"vision_model.encoder.layers.10.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
|
44 |
+
"vision_model.encoder.layers.10.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
|
45 |
+
"vision_model.encoder.layers.10.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
|
46 |
+
"vision_model.encoder.layers.10.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
47 |
+
"vision_model.encoder.layers.10.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
|
48 |
+
"vision_model.encoder.layers.10.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
49 |
+
"vision_model.encoder.layers.10.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
|
50 |
+
"vision_model.encoder.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
51 |
+
"vision_model.encoder.layers.10.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
|
52 |
+
"vision_model.encoder.layers.10.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
53 |
+
"vision_model.encoder.layers.10.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
|
54 |
+
"vision_model.encoder.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
55 |
+
"vision_model.encoder.layers.10.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
|
56 |
+
"vision_model.encoder.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
57 |
+
"vision_model.encoder.layers.11.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
|
58 |
+
"vision_model.encoder.layers.11.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
|
59 |
+
"vision_model.encoder.layers.11.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
|
60 |
+
"vision_model.encoder.layers.11.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
|
61 |
+
"vision_model.encoder.layers.11.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
|
62 |
+
"vision_model.encoder.layers.11.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
63 |
+
"vision_model.encoder.layers.11.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
|
64 |
+
"vision_model.encoder.layers.11.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
65 |
+
"vision_model.encoder.layers.11.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
|
66 |
+
"vision_model.encoder.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
67 |
+
"vision_model.encoder.layers.11.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
|
68 |
+
"vision_model.encoder.layers.11.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
69 |
+
"vision_model.encoder.layers.11.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
|
70 |
+
"vision_model.encoder.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
71 |
+
"vision_model.encoder.layers.11.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
|
72 |
+
"vision_model.encoder.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
73 |
+
"vision_model.encoder.layers.12.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
|
74 |
+
"vision_model.encoder.layers.12.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
|
75 |
+
"vision_model.encoder.layers.12.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
|
76 |
+
"vision_model.encoder.layers.12.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
|
77 |
+
"vision_model.encoder.layers.12.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
|
78 |
+
"vision_model.encoder.layers.12.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
79 |
+
"vision_model.encoder.layers.12.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
|
80 |
+
"vision_model.encoder.layers.12.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
81 |
+
"vision_model.encoder.layers.12.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
|
82 |
+
"vision_model.encoder.layers.12.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
83 |
+
"vision_model.encoder.layers.12.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
|
84 |
+
"vision_model.encoder.layers.12.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
85 |
+
"vision_model.encoder.layers.12.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
|
86 |
+
"vision_model.encoder.layers.12.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
87 |
+
"vision_model.encoder.layers.12.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
|
88 |
+
"vision_model.encoder.layers.12.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
89 |
+
"vision_model.encoder.layers.13.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
|
90 |
+
"vision_model.encoder.layers.13.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
|
91 |
+
"vision_model.encoder.layers.13.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
|
92 |
+
"vision_model.encoder.layers.13.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
|
93 |
+
"vision_model.encoder.layers.13.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
|
94 |
+
"vision_model.encoder.layers.13.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
95 |
+
"vision_model.encoder.layers.13.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
|
96 |
+
"vision_model.encoder.layers.13.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
97 |
+
"vision_model.encoder.layers.13.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
|
98 |
+
"vision_model.encoder.layers.13.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
99 |
+
"vision_model.encoder.layers.13.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
|
100 |
+
"vision_model.encoder.layers.13.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
101 |
+
"vision_model.encoder.layers.13.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
|
102 |
+
"vision_model.encoder.layers.13.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
103 |
+
"vision_model.encoder.layers.13.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
|
104 |
+
"vision_model.encoder.layers.13.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
105 |
+
"vision_model.encoder.layers.14.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
|
106 |
+
"vision_model.encoder.layers.14.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
|
107 |
+
"vision_model.encoder.layers.14.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
|
108 |
+
"vision_model.encoder.layers.14.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
|
109 |
+
"vision_model.encoder.layers.14.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
|
110 |
+
"vision_model.encoder.layers.14.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
111 |
+
"vision_model.encoder.layers.14.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
|
112 |
+
"vision_model.encoder.layers.14.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
113 |
+
"vision_model.encoder.layers.14.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
|
114 |
+
"vision_model.encoder.layers.14.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
115 |
+
"vision_model.encoder.layers.14.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
|
116 |
+
"vision_model.encoder.layers.14.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
117 |
+
"vision_model.encoder.layers.14.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
|
118 |
+
"vision_model.encoder.layers.14.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
119 |
+
"vision_model.encoder.layers.14.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
|
120 |
+
"vision_model.encoder.layers.14.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
121 |
+
"vision_model.encoder.layers.15.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
|
122 |
+
"vision_model.encoder.layers.15.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
|
123 |
+
"vision_model.encoder.layers.15.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
|
124 |
+
"vision_model.encoder.layers.15.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
|
125 |
+
"vision_model.encoder.layers.15.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
|
126 |
+
"vision_model.encoder.layers.15.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
127 |
+
"vision_model.encoder.layers.15.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
|
128 |
+
"vision_model.encoder.layers.15.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
129 |
+
"vision_model.encoder.layers.15.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
|
130 |
+
"vision_model.encoder.layers.15.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
131 |
+
"vision_model.encoder.layers.15.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
|
132 |
+
"vision_model.encoder.layers.15.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
133 |
+
"vision_model.encoder.layers.15.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
|
134 |
+
"vision_model.encoder.layers.15.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
135 |
+
"vision_model.encoder.layers.15.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
|
136 |
+
"vision_model.encoder.layers.15.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
137 |
+
"vision_model.encoder.layers.16.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
|
138 |
+
"vision_model.encoder.layers.16.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
|
139 |
+
"vision_model.encoder.layers.16.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
|
140 |
+
"vision_model.encoder.layers.16.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
|
141 |
+
"vision_model.encoder.layers.16.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
|
142 |
+
"vision_model.encoder.layers.16.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
143 |
+
"vision_model.encoder.layers.16.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
|
144 |
+
"vision_model.encoder.layers.16.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
145 |
+
"vision_model.encoder.layers.16.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
|
146 |
+
"vision_model.encoder.layers.16.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
147 |
+
"vision_model.encoder.layers.16.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
|
148 |
+
"vision_model.encoder.layers.16.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
149 |
+
"vision_model.encoder.layers.16.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
|
150 |
+
"vision_model.encoder.layers.16.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
151 |
+
"vision_model.encoder.layers.16.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
|
152 |
+
"vision_model.encoder.layers.16.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
153 |
+
"vision_model.encoder.layers.17.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
|
154 |
+
"vision_model.encoder.layers.17.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
|
155 |
+
"vision_model.encoder.layers.17.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
|
156 |
+
"vision_model.encoder.layers.17.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
|
157 |
+
"vision_model.encoder.layers.17.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
|
158 |
+
"vision_model.encoder.layers.17.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
159 |
+
"vision_model.encoder.layers.17.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
|
160 |
+
"vision_model.encoder.layers.17.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
161 |
+
"vision_model.encoder.layers.17.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
|
162 |
+
"vision_model.encoder.layers.17.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
163 |
+
"vision_model.encoder.layers.17.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
|
164 |
+
"vision_model.encoder.layers.17.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
165 |
+
"vision_model.encoder.layers.17.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
|
166 |
+
"vision_model.encoder.layers.17.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
167 |
+
"vision_model.encoder.layers.17.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
|
168 |
+
"vision_model.encoder.layers.17.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
169 |
+
"vision_model.encoder.layers.18.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
|
170 |
+
"vision_model.encoder.layers.18.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
|
171 |
+
"vision_model.encoder.layers.18.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
|
172 |
+
"vision_model.encoder.layers.18.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
|
173 |
+
"vision_model.encoder.layers.18.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
|
174 |
+
"vision_model.encoder.layers.18.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
175 |
+
"vision_model.encoder.layers.18.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
|
176 |
+
"vision_model.encoder.layers.18.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
177 |
+
"vision_model.encoder.layers.18.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
|
178 |
+
"vision_model.encoder.layers.18.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
179 |
+
"vision_model.encoder.layers.18.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
|
180 |
+
"vision_model.encoder.layers.18.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
181 |
+
"vision_model.encoder.layers.18.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
|
182 |
+
"vision_model.encoder.layers.18.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
183 |
+
"vision_model.encoder.layers.18.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
|
184 |
+
"vision_model.encoder.layers.18.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
185 |
+
"vision_model.encoder.layers.19.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
|
186 |
+
"vision_model.encoder.layers.19.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
|
187 |
+
"vision_model.encoder.layers.19.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
|
188 |
+
"vision_model.encoder.layers.19.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
|
189 |
+
"vision_model.encoder.layers.19.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
|
190 |
+
"vision_model.encoder.layers.19.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
191 |
+
"vision_model.encoder.layers.19.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
|
192 |
+
"vision_model.encoder.layers.19.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
193 |
+
"vision_model.encoder.layers.19.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
|
194 |
+
"vision_model.encoder.layers.19.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
195 |
+
"vision_model.encoder.layers.19.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
|
196 |
+
"vision_model.encoder.layers.19.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
197 |
+
"vision_model.encoder.layers.19.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
|
198 |
+
"vision_model.encoder.layers.19.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
199 |
+
"vision_model.encoder.layers.19.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
|
200 |
+
"vision_model.encoder.layers.19.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
201 |
+
"vision_model.encoder.layers.2.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
|
202 |
+
"vision_model.encoder.layers.2.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
|
203 |
+
"vision_model.encoder.layers.2.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
|
204 |
+
"vision_model.encoder.layers.2.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
|
205 |
+
"vision_model.encoder.layers.2.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
|
206 |
+
"vision_model.encoder.layers.2.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
207 |
+
"vision_model.encoder.layers.2.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
|
208 |
+
"vision_model.encoder.layers.2.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
209 |
+
"vision_model.encoder.layers.2.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
|
210 |
+
"vision_model.encoder.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
211 |
+
"vision_model.encoder.layers.2.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
|
212 |
+
"vision_model.encoder.layers.2.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
213 |
+
"vision_model.encoder.layers.2.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
|
214 |
+
"vision_model.encoder.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
215 |
+
"vision_model.encoder.layers.2.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
|
216 |
+
"vision_model.encoder.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
217 |
+
"vision_model.encoder.layers.20.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
|
218 |
+
"vision_model.encoder.layers.20.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
|
219 |
+
"vision_model.encoder.layers.20.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
|
220 |
+
"vision_model.encoder.layers.20.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
|
221 |
+
"vision_model.encoder.layers.20.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
|
222 |
+
"vision_model.encoder.layers.20.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
223 |
+
"vision_model.encoder.layers.20.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
|
224 |
+
"vision_model.encoder.layers.20.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
225 |
+
"vision_model.encoder.layers.20.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
|
226 |
+
"vision_model.encoder.layers.20.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
227 |
+
"vision_model.encoder.layers.20.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
|
228 |
+
"vision_model.encoder.layers.20.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
229 |
+
"vision_model.encoder.layers.20.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
|
230 |
+
"vision_model.encoder.layers.20.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
231 |
+
"vision_model.encoder.layers.20.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
|
232 |
+
"vision_model.encoder.layers.20.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
233 |
+
"vision_model.encoder.layers.21.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
|
234 |
+
"vision_model.encoder.layers.21.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
|
235 |
+
"vision_model.encoder.layers.21.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
|
236 |
+
"vision_model.encoder.layers.21.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
|
237 |
+
"vision_model.encoder.layers.21.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
|
238 |
+
"vision_model.encoder.layers.21.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
239 |
+
"vision_model.encoder.layers.21.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
|
240 |
+
"vision_model.encoder.layers.21.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
241 |
+
"vision_model.encoder.layers.21.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
|
242 |
+
"vision_model.encoder.layers.21.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
243 |
+
"vision_model.encoder.layers.21.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
|
244 |
+
"vision_model.encoder.layers.21.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
245 |
+
"vision_model.encoder.layers.21.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
|
246 |
+
"vision_model.encoder.layers.21.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
247 |
+
"vision_model.encoder.layers.21.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
|
248 |
+
"vision_model.encoder.layers.21.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
249 |
+
"vision_model.encoder.layers.22.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
|
250 |
+
"vision_model.encoder.layers.22.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
|
251 |
+
"vision_model.encoder.layers.22.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
|
252 |
+
"vision_model.encoder.layers.22.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
|
253 |
+
"vision_model.encoder.layers.22.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
|
254 |
+
"vision_model.encoder.layers.22.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
255 |
+
"vision_model.encoder.layers.22.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
|
256 |
+
"vision_model.encoder.layers.22.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
257 |
+
"vision_model.encoder.layers.22.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
|
258 |
+
"vision_model.encoder.layers.22.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
259 |
+
"vision_model.encoder.layers.22.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
|
260 |
+
"vision_model.encoder.layers.22.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
261 |
+
"vision_model.encoder.layers.22.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
|
262 |
+
"vision_model.encoder.layers.22.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
263 |
+
"vision_model.encoder.layers.22.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
|
264 |
+
"vision_model.encoder.layers.22.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
265 |
+
"vision_model.encoder.layers.23.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
|
266 |
+
"vision_model.encoder.layers.23.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
|
267 |
+
"vision_model.encoder.layers.23.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
|
268 |
+
"vision_model.encoder.layers.23.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
|
269 |
+
"vision_model.encoder.layers.23.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
|
270 |
+
"vision_model.encoder.layers.23.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
271 |
+
"vision_model.encoder.layers.23.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
|
272 |
+
"vision_model.encoder.layers.23.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
273 |
+
"vision_model.encoder.layers.23.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
|
274 |
+
"vision_model.encoder.layers.23.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
275 |
+
"vision_model.encoder.layers.23.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
|
276 |
+
"vision_model.encoder.layers.23.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
277 |
+
"vision_model.encoder.layers.23.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
|
278 |
+
"vision_model.encoder.layers.23.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
279 |
+
"vision_model.encoder.layers.23.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
|
280 |
+
"vision_model.encoder.layers.23.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
281 |
+
"vision_model.encoder.layers.24.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
|
282 |
+
"vision_model.encoder.layers.24.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
|
283 |
+
"vision_model.encoder.layers.24.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
|
284 |
+
"vision_model.encoder.layers.24.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
|
285 |
+
"vision_model.encoder.layers.24.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
|
286 |
+
"vision_model.encoder.layers.24.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
287 |
+
"vision_model.encoder.layers.24.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
|
288 |
+
"vision_model.encoder.layers.24.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
289 |
+
"vision_model.encoder.layers.24.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
|
290 |
+
"vision_model.encoder.layers.24.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
291 |
+
"vision_model.encoder.layers.24.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
|
292 |
+
"vision_model.encoder.layers.24.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
293 |
+
"vision_model.encoder.layers.24.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
|
294 |
+
"vision_model.encoder.layers.24.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
295 |
+
"vision_model.encoder.layers.24.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
|
296 |
+
"vision_model.encoder.layers.24.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
297 |
+
"vision_model.encoder.layers.25.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
|
298 |
+
"vision_model.encoder.layers.25.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
|
299 |
+
"vision_model.encoder.layers.25.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
|
300 |
+
"vision_model.encoder.layers.25.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
|
301 |
+
"vision_model.encoder.layers.25.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
|
302 |
+
"vision_model.encoder.layers.25.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
|
303 |
+
"vision_model.encoder.layers.25.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
|
304 |
+
"vision_model.encoder.layers.25.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
|
305 |
+
"vision_model.encoder.layers.25.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
|
306 |
+
"vision_model.encoder.layers.25.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
307 |
+
"vision_model.encoder.layers.25.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
|
308 |
+
"vision_model.encoder.layers.25.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
|
309 |
+
"vision_model.encoder.layers.25.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
|
310 |
+
"vision_model.encoder.layers.25.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
311 |
+
"vision_model.encoder.layers.25.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
|
312 |
+
"vision_model.encoder.layers.25.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
313 |
+
"vision_model.encoder.layers.26.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
|
314 |
+
"vision_model.encoder.layers.26.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
|
315 |
+
"vision_model.encoder.layers.26.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
|
316 |
+
"vision_model.encoder.layers.26.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
|
317 |
+
"vision_model.encoder.layers.26.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
|
318 |
+
"vision_model.encoder.layers.26.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
|
319 |
+
"vision_model.encoder.layers.26.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
|
320 |
+
"vision_model.encoder.layers.26.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
|
321 |
+
"vision_model.encoder.layers.26.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
|
322 |
+
"vision_model.encoder.layers.26.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
323 |
+
"vision_model.encoder.layers.26.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
|
324 |
+
"vision_model.encoder.layers.26.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
|
325 |
+
"vision_model.encoder.layers.26.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
|
326 |
+
"vision_model.encoder.layers.26.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
327 |
+
"vision_model.encoder.layers.26.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
|
328 |
+
"vision_model.encoder.layers.26.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
329 |
+
"vision_model.encoder.layers.27.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
|
330 |
+
"vision_model.encoder.layers.27.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
|
331 |
+
"vision_model.encoder.layers.27.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
|
332 |
+
"vision_model.encoder.layers.27.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
|
333 |
+
"vision_model.encoder.layers.27.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
|
334 |
+
"vision_model.encoder.layers.27.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
|
335 |
+
"vision_model.encoder.layers.27.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
|
336 |
+
"vision_model.encoder.layers.27.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
|
337 |
+
"vision_model.encoder.layers.27.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
|
338 |
+
"vision_model.encoder.layers.27.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
339 |
+
"vision_model.encoder.layers.27.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
|
340 |
+
"vision_model.encoder.layers.27.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
|
341 |
+
"vision_model.encoder.layers.27.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
|
342 |
+
"vision_model.encoder.layers.27.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
343 |
+
"vision_model.encoder.layers.27.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
|
344 |
+
"vision_model.encoder.layers.27.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
345 |
+
"vision_model.encoder.layers.28.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
|
346 |
+
"vision_model.encoder.layers.28.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
|
347 |
+
"vision_model.encoder.layers.28.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
|
348 |
+
"vision_model.encoder.layers.28.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
|
349 |
+
"vision_model.encoder.layers.28.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
|
350 |
+
"vision_model.encoder.layers.28.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
|
351 |
+
"vision_model.encoder.layers.28.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
|
352 |
+
"vision_model.encoder.layers.28.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
|
353 |
+
"vision_model.encoder.layers.28.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
|
354 |
+
"vision_model.encoder.layers.28.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
355 |
+
"vision_model.encoder.layers.28.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
|
356 |
+
"vision_model.encoder.layers.28.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
|
357 |
+
"vision_model.encoder.layers.28.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
|
358 |
+
"vision_model.encoder.layers.28.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
359 |
+
"vision_model.encoder.layers.28.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
|
360 |
+
"vision_model.encoder.layers.28.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
361 |
+
"vision_model.encoder.layers.29.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
|
362 |
+
"vision_model.encoder.layers.29.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
|
363 |
+
"vision_model.encoder.layers.29.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
|
364 |
+
"vision_model.encoder.layers.29.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
|
365 |
+
"vision_model.encoder.layers.29.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
|
366 |
+
"vision_model.encoder.layers.29.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
|
367 |
+
"vision_model.encoder.layers.29.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
|
368 |
+
"vision_model.encoder.layers.29.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
|
369 |
+
"vision_model.encoder.layers.29.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
|
370 |
+
"vision_model.encoder.layers.29.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
371 |
+
"vision_model.encoder.layers.29.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
|
372 |
+
"vision_model.encoder.layers.29.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
|
373 |
+
"vision_model.encoder.layers.29.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
|
374 |
+
"vision_model.encoder.layers.29.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
375 |
+
"vision_model.encoder.layers.29.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
|
376 |
+
"vision_model.encoder.layers.29.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
377 |
+
"vision_model.encoder.layers.3.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
|
378 |
+
"vision_model.encoder.layers.3.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
|
379 |
+
"vision_model.encoder.layers.3.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
|
380 |
+
"vision_model.encoder.layers.3.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
|
381 |
+
"vision_model.encoder.layers.3.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
|
382 |
+
"vision_model.encoder.layers.3.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
383 |
+
"vision_model.encoder.layers.3.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
|
384 |
+
"vision_model.encoder.layers.3.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
385 |
+
"vision_model.encoder.layers.3.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
|
386 |
+
"vision_model.encoder.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
387 |
+
"vision_model.encoder.layers.3.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
|
388 |
+
"vision_model.encoder.layers.3.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
389 |
+
"vision_model.encoder.layers.3.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
|
390 |
+
"vision_model.encoder.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
391 |
+
"vision_model.encoder.layers.3.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
|
392 |
+
"vision_model.encoder.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
393 |
+
"vision_model.encoder.layers.30.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
|
394 |
+
"vision_model.encoder.layers.30.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
|
395 |
+
"vision_model.encoder.layers.30.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
|
396 |
+
"vision_model.encoder.layers.30.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
|
397 |
+
"vision_model.encoder.layers.30.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
|
398 |
+
"vision_model.encoder.layers.30.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
|
399 |
+
"vision_model.encoder.layers.30.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
|
400 |
+
"vision_model.encoder.layers.30.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
|
401 |
+
"vision_model.encoder.layers.30.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
|
402 |
+
"vision_model.encoder.layers.30.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
403 |
+
"vision_model.encoder.layers.30.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
|
404 |
+
"vision_model.encoder.layers.30.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
|
405 |
+
"vision_model.encoder.layers.30.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
|
406 |
+
"vision_model.encoder.layers.30.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
407 |
+
"vision_model.encoder.layers.30.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
|
408 |
+
"vision_model.encoder.layers.30.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
409 |
+
"vision_model.encoder.layers.31.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
|
410 |
+
"vision_model.encoder.layers.31.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
|
411 |
+
"vision_model.encoder.layers.31.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
|
412 |
+
"vision_model.encoder.layers.31.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
|
413 |
+
"vision_model.encoder.layers.31.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
|
414 |
+
"vision_model.encoder.layers.31.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
|
415 |
+
"vision_model.encoder.layers.31.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
|
416 |
+
"vision_model.encoder.layers.31.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
|
417 |
+
"vision_model.encoder.layers.31.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
|
418 |
+
"vision_model.encoder.layers.31.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
419 |
+
"vision_model.encoder.layers.31.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
|
420 |
+
"vision_model.encoder.layers.31.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
|
421 |
+
"vision_model.encoder.layers.31.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
|
422 |
+
"vision_model.encoder.layers.31.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
423 |
+
"vision_model.encoder.layers.31.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
|
424 |
+
"vision_model.encoder.layers.31.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
425 |
+
"vision_model.encoder.layers.4.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
|
426 |
+
"vision_model.encoder.layers.4.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
|
427 |
+
"vision_model.encoder.layers.4.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
|
428 |
+
"vision_model.encoder.layers.4.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
|
429 |
+
"vision_model.encoder.layers.4.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
|
430 |
+
"vision_model.encoder.layers.4.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
431 |
+
"vision_model.encoder.layers.4.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
|
432 |
+
"vision_model.encoder.layers.4.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
433 |
+
"vision_model.encoder.layers.4.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
|
434 |
+
"vision_model.encoder.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
435 |
+
"vision_model.encoder.layers.4.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
|
436 |
+
"vision_model.encoder.layers.4.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
437 |
+
"vision_model.encoder.layers.4.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
|
438 |
+
"vision_model.encoder.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
439 |
+
"vision_model.encoder.layers.4.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
|
440 |
+
"vision_model.encoder.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
441 |
+
"vision_model.encoder.layers.5.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
|
442 |
+
"vision_model.encoder.layers.5.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
|
443 |
+
"vision_model.encoder.layers.5.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
|
444 |
+
"vision_model.encoder.layers.5.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
|
445 |
+
"vision_model.encoder.layers.5.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
|
446 |
+
"vision_model.encoder.layers.5.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
447 |
+
"vision_model.encoder.layers.5.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
|
448 |
+
"vision_model.encoder.layers.5.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
449 |
+
"vision_model.encoder.layers.5.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
|
450 |
+
"vision_model.encoder.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
451 |
+
"vision_model.encoder.layers.5.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
|
452 |
+
"vision_model.encoder.layers.5.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
453 |
+
"vision_model.encoder.layers.5.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
|
454 |
+
"vision_model.encoder.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
455 |
+
"vision_model.encoder.layers.5.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
|
456 |
+
"vision_model.encoder.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
457 |
+
"vision_model.encoder.layers.6.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
|
458 |
+
"vision_model.encoder.layers.6.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
|
459 |
+
"vision_model.encoder.layers.6.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
|
460 |
+
"vision_model.encoder.layers.6.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
|
461 |
+
"vision_model.encoder.layers.6.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
|
462 |
+
"vision_model.encoder.layers.6.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
463 |
+
"vision_model.encoder.layers.6.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
|
464 |
+
"vision_model.encoder.layers.6.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
465 |
+
"vision_model.encoder.layers.6.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
|
466 |
+
"vision_model.encoder.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
467 |
+
"vision_model.encoder.layers.6.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
|
468 |
+
"vision_model.encoder.layers.6.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
469 |
+
"vision_model.encoder.layers.6.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
|
470 |
+
"vision_model.encoder.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
471 |
+
"vision_model.encoder.layers.6.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
|
472 |
+
"vision_model.encoder.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
473 |
+
"vision_model.encoder.layers.7.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
|
474 |
+
"vision_model.encoder.layers.7.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
|
475 |
+
"vision_model.encoder.layers.7.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
|
476 |
+
"vision_model.encoder.layers.7.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
|
477 |
+
"vision_model.encoder.layers.7.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
|
478 |
+
"vision_model.encoder.layers.7.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
479 |
+
"vision_model.encoder.layers.7.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
|
480 |
+
"vision_model.encoder.layers.7.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
481 |
+
"vision_model.encoder.layers.7.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
|
482 |
+
"vision_model.encoder.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
483 |
+
"vision_model.encoder.layers.7.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
|
484 |
+
"vision_model.encoder.layers.7.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
485 |
+
"vision_model.encoder.layers.7.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
|
486 |
+
"vision_model.encoder.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
487 |
+
"vision_model.encoder.layers.7.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
|
488 |
+
"vision_model.encoder.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
489 |
+
"vision_model.encoder.layers.8.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
|
490 |
+
"vision_model.encoder.layers.8.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
|
491 |
+
"vision_model.encoder.layers.8.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
|
492 |
+
"vision_model.encoder.layers.8.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
|
493 |
+
"vision_model.encoder.layers.8.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
|
494 |
+
"vision_model.encoder.layers.8.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
495 |
+
"vision_model.encoder.layers.8.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
|
496 |
+
"vision_model.encoder.layers.8.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
497 |
+
"vision_model.encoder.layers.8.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
|
498 |
+
"vision_model.encoder.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
499 |
+
"vision_model.encoder.layers.8.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
|
500 |
+
"vision_model.encoder.layers.8.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
501 |
+
"vision_model.encoder.layers.8.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
|
502 |
+
"vision_model.encoder.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
503 |
+
"vision_model.encoder.layers.8.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
|
504 |
+
"vision_model.encoder.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
505 |
+
"vision_model.encoder.layers.9.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
|
506 |
+
"vision_model.encoder.layers.9.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
|
507 |
+
"vision_model.encoder.layers.9.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
|
508 |
+
"vision_model.encoder.layers.9.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
|
509 |
+
"vision_model.encoder.layers.9.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
|
510 |
+
"vision_model.encoder.layers.9.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
511 |
+
"vision_model.encoder.layers.9.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
|
512 |
+
"vision_model.encoder.layers.9.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
513 |
+
"vision_model.encoder.layers.9.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
|
514 |
+
"vision_model.encoder.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
515 |
+
"vision_model.encoder.layers.9.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
|
516 |
+
"vision_model.encoder.layers.9.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
517 |
+
"vision_model.encoder.layers.9.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
|
518 |
+
"vision_model.encoder.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
519 |
+
"vision_model.encoder.layers.9.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
|
520 |
+
"vision_model.encoder.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
521 |
+
"vision_model.post_layernorm.bias": "pytorch_model-00002-of-00002.bin",
|
522 |
+
"vision_model.post_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
523 |
+
"vision_model.pre_layrnorm.bias": "pytorch_model-00001-of-00002.bin",
|
524 |
+
"vision_model.pre_layrnorm.weight": "pytorch_model-00001-of-00002.bin"
|
525 |
+
}
|
526 |
+
}
|
xtuner_config.py
ADDED
@@ -0,0 +1,256 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import torch
|
2 |
+
from mmengine.dataset import DefaultSampler
|
3 |
+
from mmengine.hooks import (CheckpointHook, DistSamplerSeedHook, IterTimerHook,
|
4 |
+
LoggerHook, ParamSchedulerHook)
|
5 |
+
|
6 |
+
from transformers import (AutoModelForCausalLM, AutoTokenizer,
|
7 |
+
BitsAndBytesConfig,
|
8 |
+
CLIPImageProcessor, CLIPVisionModel)
|
9 |
+
from mmengine.optim import AmpOptimWrapper, CosineAnnealingLR, LinearLR
|
10 |
+
from peft import LoraConfig
|
11 |
+
from math import sqrt
|
12 |
+
from torch.optim import AdamW
|
13 |
+
from xtuner.dataset import VideoDataset, PikaDataset, ConcatDataset, ShareGPTVideoDataset
|
14 |
+
from xtuner.dataset.collate_fns import default_collate_fn
|
15 |
+
from xtuner.dataset.map_fns import llava_video_map_fn, llava_map_fn, pika_map_fn, template_map_fn_factory
|
16 |
+
from xtuner.dataset.samplers import LengthGroupedSampler
|
17 |
+
from xtuner.engine import DatasetInfoHook, EvaluateChatHook
|
18 |
+
from xtuner.model import PikaModel, PikaVidEncoder
|
19 |
+
from xtuner.utils import PROMPT_TEMPLATE
|
20 |
+
|
21 |
+
|
22 |
+
#######################################################################
|
23 |
+
# PART 1 Settings #
|
24 |
+
#######################################################################
|
25 |
+
# Model
|
26 |
+
llm_name_or_path = 'lmsys/vicuna-7b-v1.5-16k'
|
27 |
+
visual_encoder_name_or_path = 'apple/DFN5B-CLIP-ViT-H-14-378'
|
28 |
+
# Specify the s3 pretrained pth
|
29 |
+
# pretrained_pth = './work_dirs/7b_16k_s4_cont/iter_2000.pth'
|
30 |
+
pretrained_pth = 'work_dirs/7b_16k_s5/iter_800.pth'
|
31 |
+
prompt_template = PROMPT_TEMPLATE.vicuna
|
32 |
+
|
33 |
+
size = 378
|
34 |
+
# None for sampling all the video frames
|
35 |
+
n_sample_frames = 32
|
36 |
+
visual_token_merge_ratio = 0.1
|
37 |
+
accumulative_counts = 32
|
38 |
+
lr = 1e-4
|
39 |
+
batch_size = 1 # per_device can only be set to 1 to support image and video mix training
|
40 |
+
|
41 |
+
max_length = 4096
|
42 |
+
dataloader_num_workers = 0
|
43 |
+
max_epochs = 1
|
44 |
+
optim_type = AdamW
|
45 |
+
betas = (0.9, 0.999)
|
46 |
+
weight_decay = 0.1
|
47 |
+
max_norm = 1 # grad clip
|
48 |
+
warmup_ratio = 0.03
|
49 |
+
|
50 |
+
# Save
|
51 |
+
save_steps = 200
|
52 |
+
save_total_limit = 2 # Maximum checkpoints to keep (-1 means unlimited)
|
53 |
+
|
54 |
+
#######################################################################
|
55 |
+
# PART 2 Model & Tokenizer & Image Processor #
|
56 |
+
#######################################################################
|
57 |
+
tokenizer = dict(
|
58 |
+
type=AutoTokenizer.from_pretrained,
|
59 |
+
pretrained_model_name_or_path=llm_name_or_path,
|
60 |
+
trust_remote_code=True,
|
61 |
+
padding_side='right')
|
62 |
+
|
63 |
+
image_processor = dict(
|
64 |
+
type=CLIPImageProcessor.from_pretrained,
|
65 |
+
pretrained_model_name_or_path='laion/CLIP-ViT-bigG-14-laion2B-39B-b160k',
|
66 |
+
trust_remote_code=True,
|
67 |
+
size=size,
|
68 |
+
crop_size=size)
|
69 |
+
|
70 |
+
model = dict(
|
71 |
+
type=PikaModel,
|
72 |
+
freeze_llm=True,
|
73 |
+
freeze_visual_encoder=True,
|
74 |
+
pretrained_pth=pretrained_pth,
|
75 |
+
llm=dict(
|
76 |
+
type=AutoModelForCausalLM.from_pretrained,
|
77 |
+
pretrained_model_name_or_path=llm_name_or_path,
|
78 |
+
trust_remote_code=True,
|
79 |
+
torch_dtype=torch.float16,
|
80 |
+
quantization_config=dict(
|
81 |
+
type=BitsAndBytesConfig,
|
82 |
+
load_in_4bit=True,
|
83 |
+
load_in_8bit=False,
|
84 |
+
llm_int8_threshold=6.0,
|
85 |
+
llm_int8_has_fp16_weight=False,
|
86 |
+
bnb_4bit_compute_dtype=torch.float16,
|
87 |
+
bnb_4bit_use_double_quant=True,
|
88 |
+
bnb_4bit_quant_type='nf4')),
|
89 |
+
llm_lora=dict(
|
90 |
+
type=LoraConfig,
|
91 |
+
r=512,
|
92 |
+
lora_alpha=256,
|
93 |
+
lora_dropout=0.05,
|
94 |
+
bias='none',
|
95 |
+
task_type='CAUSAL_LM'),
|
96 |
+
visual_encoder=dict(
|
97 |
+
# type=CLIPVisionModel.from_pretrained,
|
98 |
+
type=PikaVidEncoder.from_pretrained,
|
99 |
+
pretrained_model_name_or_path=visual_encoder_name_or_path,
|
100 |
+
visual_token_merge_ratio=visual_token_merge_ratio),
|
101 |
+
visual_encoder_lora=dict(
|
102 |
+
type=LoraConfig, r=64, lora_alpha=16, lora_dropout=0.05, bias='none'),
|
103 |
+
)
|
104 |
+
|
105 |
+
|
106 |
+
#######################################################################
|
107 |
+
# PART 3 Dataset & Dataloader #
|
108 |
+
#######################################################################
|
109 |
+
allava_image_caption_dataset = dict(
|
110 |
+
type=PikaDataset,
|
111 |
+
data_path='./data/image_finetune/ALLaVA-Caption-LAION-4V',
|
112 |
+
image_folder='./data/image_data',
|
113 |
+
tokenizer=tokenizer,
|
114 |
+
image_processor=image_processor,
|
115 |
+
dataset_map_fn=llava_map_fn,
|
116 |
+
template_map_fn=dict(
|
117 |
+
type=template_map_fn_factory, template=prompt_template),
|
118 |
+
max_length=max_length,
|
119 |
+
pad_image_to_square=False,
|
120 |
+
keep_aspect_ratio=True,)
|
121 |
+
|
122 |
+
sharegpt4v_video_caption_dataset = dict(
|
123 |
+
type=ShareGPTVideoDataset,
|
124 |
+
data_path='./data/video_finetune/sharegptvideo_caption_full_frame',
|
125 |
+
image_folder='./data/video_data/sharegptvideo_900k',
|
126 |
+
tokenizer=tokenizer,
|
127 |
+
image_processor=image_processor,
|
128 |
+
dataset_map_fn=llava_video_map_fn,
|
129 |
+
template_map_fn=dict(
|
130 |
+
type=template_map_fn_factory, template=prompt_template),
|
131 |
+
max_length=max_length,
|
132 |
+
pad_image_to_square=False,
|
133 |
+
frame_number=n_sample_frames,
|
134 |
+
keep_aspect_ratio=True,)
|
135 |
+
|
136 |
+
# mix video and image
|
137 |
+
train_dataset = dict(
|
138 |
+
type=ConcatDataset,
|
139 |
+
datasets=[
|
140 |
+
allava_image_caption_dataset,
|
141 |
+
sharegpt4v_video_caption_dataset,
|
142 |
+
])
|
143 |
+
|
144 |
+
train_dataloader = dict(
|
145 |
+
batch_size=batch_size,
|
146 |
+
num_workers=dataloader_num_workers,
|
147 |
+
dataset=train_dataset,
|
148 |
+
# sampler=dict(
|
149 |
+
# type=LengthGroupedSampler,
|
150 |
+
# length_property='modality_length',
|
151 |
+
# per_device_batch_size=batch_size * accumulative_counts),
|
152 |
+
sampler=dict(type=DefaultSampler, shuffle=True),
|
153 |
+
collate_fn=dict(type=default_collate_fn))
|
154 |
+
|
155 |
+
#######################################################################
|
156 |
+
# PART 4 Scheduler & Optimizer #
|
157 |
+
#######################################################################
|
158 |
+
# optimizer
|
159 |
+
optim_wrapper = dict(
|
160 |
+
type=AmpOptimWrapper,
|
161 |
+
optimizer=dict(
|
162 |
+
type=optim_type, lr=lr, betas=betas, weight_decay=weight_decay),
|
163 |
+
clip_grad=dict(max_norm=max_norm, error_if_nonfinite=False),
|
164 |
+
accumulative_counts=accumulative_counts,
|
165 |
+
loss_scale='dynamic',
|
166 |
+
dtype='float16')
|
167 |
+
|
168 |
+
# learning policy
|
169 |
+
# More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501
|
170 |
+
param_scheduler = [
|
171 |
+
dict(
|
172 |
+
type=LinearLR,
|
173 |
+
start_factor=1e-5,
|
174 |
+
by_epoch=True,
|
175 |
+
begin=0,
|
176 |
+
end=warmup_ratio * max_epochs,
|
177 |
+
convert_to_iter_based=True),
|
178 |
+
dict(
|
179 |
+
type=CosineAnnealingLR,
|
180 |
+
eta_min=0.0,
|
181 |
+
by_epoch=True,
|
182 |
+
begin=warmup_ratio * max_epochs,
|
183 |
+
T_max=max_epochs,
|
184 |
+
convert_to_iter_based=True)
|
185 |
+
]
|
186 |
+
|
187 |
+
# train, val, test setting
|
188 |
+
train_cfg = dict(by_epoch=True, max_epochs=max_epochs, val_interval=1)
|
189 |
+
|
190 |
+
#######################################################################
|
191 |
+
# PART 5 Runtime #
|
192 |
+
#######################################################################
|
193 |
+
# Evaluate the generation performance during the training
|
194 |
+
evaluation_freq = 500
|
195 |
+
SYSTEM = ''
|
196 |
+
evaluation_images = 'https://llava-vl.github.io/static/images/view.jpg'
|
197 |
+
evaluation_inputs = ['请描述一下这张照片', 'Please describe this picture']
|
198 |
+
|
199 |
+
|
200 |
+
# Log the dialogue periodically during the training process, optional
|
201 |
+
custom_hooks = [
|
202 |
+
dict(type=DatasetInfoHook, tokenizer=tokenizer),
|
203 |
+
dict(
|
204 |
+
type=EvaluateChatHook,
|
205 |
+
tokenizer=tokenizer,
|
206 |
+
image_processor=image_processor,
|
207 |
+
every_n_iters=evaluation_freq,
|
208 |
+
evaluation_inputs=evaluation_inputs,
|
209 |
+
evaluation_images=evaluation_images,
|
210 |
+
system=SYSTEM,
|
211 |
+
prompt_template=prompt_template)
|
212 |
+
]
|
213 |
+
|
214 |
+
# configure default hooks
|
215 |
+
default_hooks = dict(
|
216 |
+
# record the time of every iteration.
|
217 |
+
timer=dict(type=IterTimerHook),
|
218 |
+
# print log every 100 iterations.
|
219 |
+
logger=dict(type=LoggerHook, interval=10),
|
220 |
+
# enable the parameter scheduler.
|
221 |
+
param_scheduler=dict(type=ParamSchedulerHook),
|
222 |
+
# save checkpoint per epoch.
|
223 |
+
# checkpoint=dict(type=CheckpointHook, interval=1),
|
224 |
+
checkpoint=dict(
|
225 |
+
type=CheckpointHook,
|
226 |
+
by_epoch=False,
|
227 |
+
interval=save_steps,
|
228 |
+
max_keep_ckpts=save_total_limit),
|
229 |
+
# set sampler seed in distributed evrionment.
|
230 |
+
sampler_seed=dict(type=DistSamplerSeedHook),
|
231 |
+
)
|
232 |
+
|
233 |
+
# configure environment
|
234 |
+
env_cfg = dict(
|
235 |
+
# whether to enable cudnn benchmark
|
236 |
+
cudnn_benchmark=False,
|
237 |
+
# set multi process parameters
|
238 |
+
mp_cfg=dict(mp_start_method='fork', opencv_num_threads=0),
|
239 |
+
# set distributed parameters
|
240 |
+
dist_cfg=dict(backend='nccl'),
|
241 |
+
)
|
242 |
+
|
243 |
+
# set visualizer
|
244 |
+
visualizer = None
|
245 |
+
|
246 |
+
# set log level
|
247 |
+
log_level = 'INFO'
|
248 |
+
|
249 |
+
# load from which checkpoint
|
250 |
+
load_from = None
|
251 |
+
|
252 |
+
# whether to resume training from the loaded checkpoint
|
253 |
+
resume = False
|
254 |
+
|
255 |
+
# Defaults to use random seed and disable `deterministic`
|
256 |
+
randomness = dict(seed=None, deterministic=False)
|