Delete checkpoints/SEAGULL-7B
Browse files- checkpoints/SEAGULL-7B/.DS_Store +0 -0
- checkpoints/SEAGULL-7B/README.md +0 -3
- checkpoints/SEAGULL-7B/added_tokens.json +0 -4
- checkpoints/SEAGULL-7B/config.json +0 -36
- checkpoints/SEAGULL-7B/generation_config.json +0 -9
- checkpoints/SEAGULL-7B/pytorch_model.bin.index.json +0 -749
- checkpoints/SEAGULL-7B/special_tokens_map.json +0 -24
- checkpoints/SEAGULL-7B/tokenizer.model +0 -3
- checkpoints/SEAGULL-7B/tokenizer_config.json +0 -35
checkpoints/SEAGULL-7B/.DS_Store
DELETED
Binary file (6.15 kB)
|
|
checkpoints/SEAGULL-7B/README.md
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
---
|
2 |
-
license: mit
|
3 |
-
---
|
|
|
|
|
|
|
|
checkpoints/SEAGULL-7B/added_tokens.json
DELETED
@@ -1,4 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"<global>": 32000,
|
3 |
-
"<local>": 32001
|
4 |
-
}
|
|
|
|
|
|
|
|
|
|
checkpoints/SEAGULL-7B/config.json
DELETED
@@ -1,36 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"_name_or_path": "SEAGULL-7B",
|
3 |
-
"architectures": [
|
4 |
-
"OspreyLlamaForCausalLM"
|
5 |
-
],
|
6 |
-
"bos_token_id": 1,
|
7 |
-
"eos_token_id": 2,
|
8 |
-
"freeze_mm_mlp_adapter": false,
|
9 |
-
"hidden_act": "silu",
|
10 |
-
"hidden_size": 4096,
|
11 |
-
"image_aspect_ratio": "pad",
|
12 |
-
"image_grid_pinpoints": null,
|
13 |
-
"initializer_range": 0.02,
|
14 |
-
"intermediate_size": 11008,
|
15 |
-
"max_position_embeddings": 4096,
|
16 |
-
"mm_projector_lr": null,
|
17 |
-
"mm_projector_type": "mlp2x_gelu",
|
18 |
-
"mm_use_im_patch_token": false,
|
19 |
-
"mm_use_im_start_end": false,
|
20 |
-
"mm_vision_tower": "./checkpoints/open_clip_pytorch_model.bin",
|
21 |
-
"model_type": "osprey",
|
22 |
-
"num_attention_heads": 32,
|
23 |
-
"num_hidden_layers": 32,
|
24 |
-
"num_key_value_heads": 32,
|
25 |
-
"pad_token_id": 0,
|
26 |
-
"pretraining_tp": 1,
|
27 |
-
"rms_norm_eps": 1e-05,
|
28 |
-
"rope_scaling": null,
|
29 |
-
"tie_word_embeddings": false,
|
30 |
-
"torch_dtype": "float16",
|
31 |
-
"transformers_version": "4.31.0",
|
32 |
-
"tune_mm_mlp_adapter": false,
|
33 |
-
"use_cache": true,
|
34 |
-
"use_mm_proj": true,
|
35 |
-
"vocab_size": 32002
|
36 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoints/SEAGULL-7B/generation_config.json
DELETED
@@ -1,9 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"bos_token_id": 1,
|
3 |
-
"eos_token_id": 2,
|
4 |
-
"max_length": 4096,
|
5 |
-
"pad_token_id": 0,
|
6 |
-
"temperature": 0.9,
|
7 |
-
"top_p": 0.6,
|
8 |
-
"transformers_version": "4.31.0"
|
9 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoints/SEAGULL-7B/pytorch_model.bin.index.json
DELETED
@@ -1,749 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"metadata": {
|
3 |
-
"total_size": 14122027444
|
4 |
-
},
|
5 |
-
"weight_map": {
|
6 |
-
"lm_head.weight": "pytorch_model-00002-of-00002.bin",
|
7 |
-
"mask_extractor.cross_att_res.cross_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
|
8 |
-
"mask_extractor.cross_att_res.cross_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
9 |
-
"mask_extractor.cross_att_res.cross_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
|
10 |
-
"mask_extractor.cross_att_res.cross_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
|
11 |
-
"mask_extractor.cross_att_res.cross_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
|
12 |
-
"mask_extractor.cross_att_res.cross_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
13 |
-
"mask_extractor.cross_att_res.cross_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
|
14 |
-
"mask_extractor.cross_att_res.cross_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
15 |
-
"mask_extractor.cross_att_res.mlp.lin1.bias": "pytorch_model-00002-of-00002.bin",
|
16 |
-
"mask_extractor.cross_att_res.mlp.lin1.weight": "pytorch_model-00002-of-00002.bin",
|
17 |
-
"mask_extractor.cross_att_res.mlp.lin2.bias": "pytorch_model-00002-of-00002.bin",
|
18 |
-
"mask_extractor.cross_att_res.mlp.lin2.weight": "pytorch_model-00002-of-00002.bin",
|
19 |
-
"mask_extractor.cross_att_res.norm1.bias": "pytorch_model-00002-of-00002.bin",
|
20 |
-
"mask_extractor.cross_att_res.norm1.weight": "pytorch_model-00002-of-00002.bin",
|
21 |
-
"mask_extractor.cross_att_res.norm2.bias": "pytorch_model-00002-of-00002.bin",
|
22 |
-
"mask_extractor.cross_att_res.norm2.weight": "pytorch_model-00002-of-00002.bin",
|
23 |
-
"mask_extractor.cross_att_res.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
|
24 |
-
"mask_extractor.cross_att_res.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
25 |
-
"mask_extractor.cross_att_res.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
|
26 |
-
"mask_extractor.cross_att_res.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
|
27 |
-
"mask_extractor.cross_att_res.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
|
28 |
-
"mask_extractor.cross_att_res.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
29 |
-
"mask_extractor.cross_att_res.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
|
30 |
-
"mask_extractor.cross_att_res.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
31 |
-
"mask_extractor.cross_feat_linear.bias": "pytorch_model-00002-of-00002.bin",
|
32 |
-
"mask_extractor.cross_feat_linear.weight": "pytorch_model-00002-of-00002.bin",
|
33 |
-
"mask_extractor.feat_linear.bias": "pytorch_model-00002-of-00002.bin",
|
34 |
-
"mask_extractor.feat_linear.weight": "pytorch_model-00002-of-00002.bin",
|
35 |
-
"mask_extractor.final_mlp.bias": "pytorch_model-00002-of-00002.bin",
|
36 |
-
"mask_extractor.final_mlp.weight": "pytorch_model-00002-of-00002.bin",
|
37 |
-
"mask_extractor.g_res2.bias": "pytorch_model-00002-of-00002.bin",
|
38 |
-
"mask_extractor.g_res2.weight": "pytorch_model-00002-of-00002.bin",
|
39 |
-
"mask_extractor.g_res3.bias": "pytorch_model-00002-of-00002.bin",
|
40 |
-
"mask_extractor.g_res3.weight": "pytorch_model-00002-of-00002.bin",
|
41 |
-
"mask_extractor.g_res4.bias": "pytorch_model-00002-of-00002.bin",
|
42 |
-
"mask_extractor.g_res4.weight": "pytorch_model-00002-of-00002.bin",
|
43 |
-
"mask_extractor.g_res5.bias": "pytorch_model-00002-of-00002.bin",
|
44 |
-
"mask_extractor.g_res5.weight": "pytorch_model-00002-of-00002.bin",
|
45 |
-
"mask_extractor.global_vit.0.bias": "pytorch_model-00002-of-00002.bin",
|
46 |
-
"mask_extractor.global_vit.0.weight": "pytorch_model-00002-of-00002.bin",
|
47 |
-
"mask_extractor.global_vit.3.bias": "pytorch_model-00002-of-00002.bin",
|
48 |
-
"mask_extractor.global_vit.3.weight": "pytorch_model-00002-of-00002.bin",
|
49 |
-
"mask_extractor.mask_linear.layers.0.bias": "pytorch_model-00002-of-00002.bin",
|
50 |
-
"mask_extractor.mask_linear.layers.0.weight": "pytorch_model-00002-of-00002.bin",
|
51 |
-
"mask_extractor.mask_linear.layers.1.bias": "pytorch_model-00002-of-00002.bin",
|
52 |
-
"mask_extractor.mask_linear.layers.1.weight": "pytorch_model-00002-of-00002.bin",
|
53 |
-
"mask_extractor.mask_linear.layers.2.bias": "pytorch_model-00002-of-00002.bin",
|
54 |
-
"mask_extractor.mask_linear.layers.2.weight": "pytorch_model-00002-of-00002.bin",
|
55 |
-
"mask_extractor.mlp.layers.0.bias": "pytorch_model-00002-of-00002.bin",
|
56 |
-
"mask_extractor.mlp.layers.0.weight": "pytorch_model-00002-of-00002.bin",
|
57 |
-
"mask_extractor.mlp.layers.1.bias": "pytorch_model-00002-of-00002.bin",
|
58 |
-
"mask_extractor.mlp.layers.1.weight": "pytorch_model-00002-of-00002.bin",
|
59 |
-
"mask_extractor.mlp.layers.2.bias": "pytorch_model-00002-of-00002.bin",
|
60 |
-
"mask_extractor.mlp.layers.2.weight": "pytorch_model-00002-of-00002.bin",
|
61 |
-
"mask_extractor.res2.bias": "pytorch_model-00002-of-00002.bin",
|
62 |
-
"mask_extractor.res2.weight": "pytorch_model-00002-of-00002.bin",
|
63 |
-
"mask_extractor.res3.bias": "pytorch_model-00002-of-00002.bin",
|
64 |
-
"mask_extractor.res3.weight": "pytorch_model-00002-of-00002.bin",
|
65 |
-
"mask_extractor.res4.bias": "pytorch_model-00002-of-00002.bin",
|
66 |
-
"mask_extractor.res4.weight": "pytorch_model-00002-of-00002.bin",
|
67 |
-
"mask_extractor.res5.bias": "pytorch_model-00002-of-00002.bin",
|
68 |
-
"mask_extractor.res5.weight": "pytorch_model-00002-of-00002.bin",
|
69 |
-
"mask_extractor.sa.k_proj.bias": "pytorch_model-00002-of-00002.bin",
|
70 |
-
"mask_extractor.sa.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
71 |
-
"mask_extractor.sa.out_proj.bias": "pytorch_model-00002-of-00002.bin",
|
72 |
-
"mask_extractor.sa.out_proj.weight": "pytorch_model-00002-of-00002.bin",
|
73 |
-
"mask_extractor.sa.q_proj.bias": "pytorch_model-00002-of-00002.bin",
|
74 |
-
"mask_extractor.sa.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
75 |
-
"mask_extractor.sa.v_proj.bias": "pytorch_model-00002-of-00002.bin",
|
76 |
-
"mask_extractor.sa.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
77 |
-
"model.embed_tokens.weight": "pytorch_model-00001-of-00002.bin",
|
78 |
-
"model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
79 |
-
"model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
80 |
-
"model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
81 |
-
"model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
82 |
-
"model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
83 |
-
"model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
84 |
-
"model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
85 |
-
"model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
86 |
-
"model.layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
|
87 |
-
"model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
88 |
-
"model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
89 |
-
"model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
90 |
-
"model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
91 |
-
"model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
92 |
-
"model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
93 |
-
"model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
94 |
-
"model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
95 |
-
"model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
96 |
-
"model.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
|
97 |
-
"model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
98 |
-
"model.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
99 |
-
"model.layers.10.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
100 |
-
"model.layers.10.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
101 |
-
"model.layers.10.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
102 |
-
"model.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
103 |
-
"model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
104 |
-
"model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
105 |
-
"model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
106 |
-
"model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
|
107 |
-
"model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
108 |
-
"model.layers.11.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
109 |
-
"model.layers.11.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
110 |
-
"model.layers.11.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
111 |
-
"model.layers.11.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
112 |
-
"model.layers.11.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
113 |
-
"model.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
114 |
-
"model.layers.11.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
115 |
-
"model.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
116 |
-
"model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
|
117 |
-
"model.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
118 |
-
"model.layers.12.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
119 |
-
"model.layers.12.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
120 |
-
"model.layers.12.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
121 |
-
"model.layers.12.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
122 |
-
"model.layers.12.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
123 |
-
"model.layers.12.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
124 |
-
"model.layers.12.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
125 |
-
"model.layers.12.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
126 |
-
"model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
|
127 |
-
"model.layers.12.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
128 |
-
"model.layers.13.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
129 |
-
"model.layers.13.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
130 |
-
"model.layers.13.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
131 |
-
"model.layers.13.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
132 |
-
"model.layers.13.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
133 |
-
"model.layers.13.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
134 |
-
"model.layers.13.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
135 |
-
"model.layers.13.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
136 |
-
"model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
|
137 |
-
"model.layers.13.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
138 |
-
"model.layers.14.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
139 |
-
"model.layers.14.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
140 |
-
"model.layers.14.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
141 |
-
"model.layers.14.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
142 |
-
"model.layers.14.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
143 |
-
"model.layers.14.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
144 |
-
"model.layers.14.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
145 |
-
"model.layers.14.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
146 |
-
"model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
|
147 |
-
"model.layers.14.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
148 |
-
"model.layers.15.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
149 |
-
"model.layers.15.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
150 |
-
"model.layers.15.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
151 |
-
"model.layers.15.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
152 |
-
"model.layers.15.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
153 |
-
"model.layers.15.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
154 |
-
"model.layers.15.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
155 |
-
"model.layers.15.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
156 |
-
"model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
|
157 |
-
"model.layers.15.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
158 |
-
"model.layers.16.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
159 |
-
"model.layers.16.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
160 |
-
"model.layers.16.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
161 |
-
"model.layers.16.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
162 |
-
"model.layers.16.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
163 |
-
"model.layers.16.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
164 |
-
"model.layers.16.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
165 |
-
"model.layers.16.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
166 |
-
"model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
|
167 |
-
"model.layers.16.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
168 |
-
"model.layers.17.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
169 |
-
"model.layers.17.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
170 |
-
"model.layers.17.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
171 |
-
"model.layers.17.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
172 |
-
"model.layers.17.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
173 |
-
"model.layers.17.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
174 |
-
"model.layers.17.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
175 |
-
"model.layers.17.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
176 |
-
"model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
|
177 |
-
"model.layers.17.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
178 |
-
"model.layers.18.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
179 |
-
"model.layers.18.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
180 |
-
"model.layers.18.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
181 |
-
"model.layers.18.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
182 |
-
"model.layers.18.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
183 |
-
"model.layers.18.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
184 |
-
"model.layers.18.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
185 |
-
"model.layers.18.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
186 |
-
"model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
|
187 |
-
"model.layers.18.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
188 |
-
"model.layers.19.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
189 |
-
"model.layers.19.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
190 |
-
"model.layers.19.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
191 |
-
"model.layers.19.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
192 |
-
"model.layers.19.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
193 |
-
"model.layers.19.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
194 |
-
"model.layers.19.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
195 |
-
"model.layers.19.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
196 |
-
"model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
|
197 |
-
"model.layers.19.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
198 |
-
"model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
199 |
-
"model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
200 |
-
"model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
201 |
-
"model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
202 |
-
"model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
203 |
-
"model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
204 |
-
"model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
205 |
-
"model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
206 |
-
"model.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
|
207 |
-
"model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
208 |
-
"model.layers.20.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
209 |
-
"model.layers.20.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
210 |
-
"model.layers.20.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
211 |
-
"model.layers.20.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
212 |
-
"model.layers.20.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
213 |
-
"model.layers.20.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
214 |
-
"model.layers.20.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
215 |
-
"model.layers.20.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
216 |
-
"model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
|
217 |
-
"model.layers.20.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
218 |
-
"model.layers.21.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
219 |
-
"model.layers.21.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
220 |
-
"model.layers.21.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
221 |
-
"model.layers.21.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
222 |
-
"model.layers.21.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
223 |
-
"model.layers.21.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
224 |
-
"model.layers.21.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
225 |
-
"model.layers.21.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
226 |
-
"model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
|
227 |
-
"model.layers.21.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
228 |
-
"model.layers.22.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
229 |
-
"model.layers.22.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
230 |
-
"model.layers.22.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
231 |
-
"model.layers.22.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
232 |
-
"model.layers.22.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
233 |
-
"model.layers.22.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
234 |
-
"model.layers.22.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
235 |
-
"model.layers.22.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
236 |
-
"model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
|
237 |
-
"model.layers.22.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
238 |
-
"model.layers.23.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
239 |
-
"model.layers.23.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
240 |
-
"model.layers.23.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
241 |
-
"model.layers.23.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
242 |
-
"model.layers.23.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
243 |
-
"model.layers.23.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
244 |
-
"model.layers.23.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
245 |
-
"model.layers.23.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
246 |
-
"model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
|
247 |
-
"model.layers.23.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
248 |
-
"model.layers.24.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
249 |
-
"model.layers.24.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
250 |
-
"model.layers.24.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
251 |
-
"model.layers.24.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
252 |
-
"model.layers.24.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
253 |
-
"model.layers.24.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
254 |
-
"model.layers.24.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
255 |
-
"model.layers.24.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
256 |
-
"model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
|
257 |
-
"model.layers.24.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
258 |
-
"model.layers.25.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
259 |
-
"model.layers.25.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
260 |
-
"model.layers.25.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
261 |
-
"model.layers.25.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
262 |
-
"model.layers.25.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
263 |
-
"model.layers.25.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
264 |
-
"model.layers.25.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
265 |
-
"model.layers.25.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
266 |
-
"model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
|
267 |
-
"model.layers.25.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
268 |
-
"model.layers.26.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
269 |
-
"model.layers.26.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
270 |
-
"model.layers.26.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
271 |
-
"model.layers.26.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
272 |
-
"model.layers.26.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
273 |
-
"model.layers.26.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
274 |
-
"model.layers.26.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
275 |
-
"model.layers.26.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
276 |
-
"model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
|
277 |
-
"model.layers.26.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
278 |
-
"model.layers.27.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
279 |
-
"model.layers.27.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
280 |
-
"model.layers.27.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
281 |
-
"model.layers.27.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
282 |
-
"model.layers.27.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
283 |
-
"model.layers.27.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
284 |
-
"model.layers.27.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
285 |
-
"model.layers.27.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
286 |
-
"model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
|
287 |
-
"model.layers.27.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
288 |
-
"model.layers.28.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
289 |
-
"model.layers.28.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
290 |
-
"model.layers.28.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
291 |
-
"model.layers.28.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
292 |
-
"model.layers.28.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
293 |
-
"model.layers.28.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
294 |
-
"model.layers.28.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
295 |
-
"model.layers.28.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
296 |
-
"model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
|
297 |
-
"model.layers.28.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
298 |
-
"model.layers.29.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
299 |
-
"model.layers.29.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
300 |
-
"model.layers.29.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
301 |
-
"model.layers.29.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
302 |
-
"model.layers.29.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
303 |
-
"model.layers.29.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
304 |
-
"model.layers.29.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
305 |
-
"model.layers.29.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
306 |
-
"model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
|
307 |
-
"model.layers.29.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
308 |
-
"model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
309 |
-
"model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
310 |
-
"model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
311 |
-
"model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
312 |
-
"model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
313 |
-
"model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
314 |
-
"model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
315 |
-
"model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
316 |
-
"model.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
|
317 |
-
"model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
318 |
-
"model.layers.30.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
319 |
-
"model.layers.30.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
320 |
-
"model.layers.30.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
321 |
-
"model.layers.30.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
322 |
-
"model.layers.30.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
323 |
-
"model.layers.30.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
324 |
-
"model.layers.30.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
325 |
-
"model.layers.30.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
326 |
-
"model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
|
327 |
-
"model.layers.30.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
328 |
-
"model.layers.31.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
329 |
-
"model.layers.31.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
330 |
-
"model.layers.31.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
331 |
-
"model.layers.31.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
332 |
-
"model.layers.31.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
333 |
-
"model.layers.31.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
334 |
-
"model.layers.31.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
335 |
-
"model.layers.31.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
336 |
-
"model.layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
|
337 |
-
"model.layers.31.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
338 |
-
"model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
339 |
-
"model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
340 |
-
"model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
341 |
-
"model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
342 |
-
"model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
343 |
-
"model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
344 |
-
"model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
345 |
-
"model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
346 |
-
"model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
|
347 |
-
"model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
348 |
-
"model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
349 |
-
"model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
350 |
-
"model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
351 |
-
"model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
352 |
-
"model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
353 |
-
"model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
354 |
-
"model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
355 |
-
"model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
356 |
-
"model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
|
357 |
-
"model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
358 |
-
"model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
359 |
-
"model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
360 |
-
"model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
361 |
-
"model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
362 |
-
"model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
363 |
-
"model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
364 |
-
"model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
365 |
-
"model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
366 |
-
"model.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
|
367 |
-
"model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
368 |
-
"model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
369 |
-
"model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
370 |
-
"model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
371 |
-
"model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
372 |
-
"model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
373 |
-
"model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
374 |
-
"model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
375 |
-
"model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
376 |
-
"model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
|
377 |
-
"model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
378 |
-
"model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
379 |
-
"model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
380 |
-
"model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
381 |
-
"model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
382 |
-
"model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
383 |
-
"model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
384 |
-
"model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
385 |
-
"model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
386 |
-
"model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
|
387 |
-
"model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
388 |
-
"model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
389 |
-
"model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
390 |
-
"model.layers.9.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
391 |
-
"model.layers.9.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
392 |
-
"model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
393 |
-
"model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
394 |
-
"model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
395 |
-
"model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
396 |
-
"model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
|
397 |
-
"model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
398 |
-
"model.mm_projector.0.bias": "pytorch_model-00002-of-00002.bin",
|
399 |
-
"model.mm_projector.0.weight": "pytorch_model-00002-of-00002.bin",
|
400 |
-
"model.mm_projector.2.bias": "pytorch_model-00002-of-00002.bin",
|
401 |
-
"model.mm_projector.2.weight": "pytorch_model-00002-of-00002.bin",
|
402 |
-
"model.norm.weight": "pytorch_model-00002-of-00002.bin",
|
403 |
-
"model.vision_tower.vision_tower.visual.head.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
|
404 |
-
"model.vision_tower.vision_tower.visual.head.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
|
405 |
-
"model.vision_tower.vision_tower.visual.head.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
|
406 |
-
"model.vision_tower.vision_tower.visual.trunk.head.norm.bias": "pytorch_model-00002-of-00002.bin",
|
407 |
-
"model.vision_tower.vision_tower.visual.trunk.head.norm.weight": "pytorch_model-00002-of-00002.bin",
|
408 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.0.blocks.0.conv_dw.bias": "pytorch_model-00002-of-00002.bin",
|
409 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.0.blocks.0.conv_dw.weight": "pytorch_model-00002-of-00002.bin",
|
410 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.0.blocks.0.gamma": "pytorch_model-00002-of-00002.bin",
|
411 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.0.blocks.0.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
|
412 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.0.blocks.0.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
|
413 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.0.blocks.0.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
|
414 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.0.blocks.0.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
|
415 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.0.blocks.0.norm.bias": "pytorch_model-00002-of-00002.bin",
|
416 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.0.blocks.0.norm.weight": "pytorch_model-00002-of-00002.bin",
|
417 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.0.blocks.1.conv_dw.bias": "pytorch_model-00002-of-00002.bin",
|
418 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.0.blocks.1.conv_dw.weight": "pytorch_model-00002-of-00002.bin",
|
419 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.0.blocks.1.gamma": "pytorch_model-00002-of-00002.bin",
|
420 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.0.blocks.1.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
|
421 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.0.blocks.1.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
|
422 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.0.blocks.1.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
|
423 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.0.blocks.1.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
|
424 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.0.blocks.1.norm.bias": "pytorch_model-00002-of-00002.bin",
|
425 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.0.blocks.1.norm.weight": "pytorch_model-00002-of-00002.bin",
|
426 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.0.blocks.2.conv_dw.bias": "pytorch_model-00002-of-00002.bin",
|
427 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.0.blocks.2.conv_dw.weight": "pytorch_model-00002-of-00002.bin",
|
428 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.0.blocks.2.gamma": "pytorch_model-00002-of-00002.bin",
|
429 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.0.blocks.2.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
|
430 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.0.blocks.2.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
|
431 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.0.blocks.2.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
|
432 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.0.blocks.2.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
|
433 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.0.blocks.2.norm.bias": "pytorch_model-00002-of-00002.bin",
|
434 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.0.blocks.2.norm.weight": "pytorch_model-00002-of-00002.bin",
|
435 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.1.blocks.0.conv_dw.bias": "pytorch_model-00002-of-00002.bin",
|
436 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.1.blocks.0.conv_dw.weight": "pytorch_model-00002-of-00002.bin",
|
437 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.1.blocks.0.gamma": "pytorch_model-00002-of-00002.bin",
|
438 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.1.blocks.0.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
|
439 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.1.blocks.0.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
|
440 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.1.blocks.0.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
|
441 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.1.blocks.0.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
|
442 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.1.blocks.0.norm.bias": "pytorch_model-00002-of-00002.bin",
|
443 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.1.blocks.0.norm.weight": "pytorch_model-00002-of-00002.bin",
|
444 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.1.blocks.1.conv_dw.bias": "pytorch_model-00002-of-00002.bin",
|
445 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.1.blocks.1.conv_dw.weight": "pytorch_model-00002-of-00002.bin",
|
446 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.1.blocks.1.gamma": "pytorch_model-00002-of-00002.bin",
|
447 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.1.blocks.1.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
|
448 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.1.blocks.1.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
|
449 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.1.blocks.1.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
|
450 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.1.blocks.1.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
|
451 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.1.blocks.1.norm.bias": "pytorch_model-00002-of-00002.bin",
|
452 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.1.blocks.1.norm.weight": "pytorch_model-00002-of-00002.bin",
|
453 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.1.blocks.2.conv_dw.bias": "pytorch_model-00002-of-00002.bin",
|
454 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.1.blocks.2.conv_dw.weight": "pytorch_model-00002-of-00002.bin",
|
455 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.1.blocks.2.gamma": "pytorch_model-00002-of-00002.bin",
|
456 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.1.blocks.2.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
|
457 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.1.blocks.2.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
|
458 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.1.blocks.2.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
|
459 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.1.blocks.2.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
|
460 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.1.blocks.2.norm.bias": "pytorch_model-00002-of-00002.bin",
|
461 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.1.blocks.2.norm.weight": "pytorch_model-00002-of-00002.bin",
|
462 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.1.downsample.0.bias": "pytorch_model-00002-of-00002.bin",
|
463 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.1.downsample.0.weight": "pytorch_model-00002-of-00002.bin",
|
464 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.1.downsample.1.bias": "pytorch_model-00002-of-00002.bin",
|
465 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.1.downsample.1.weight": "pytorch_model-00002-of-00002.bin",
|
466 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.0.conv_dw.bias": "pytorch_model-00002-of-00002.bin",
|
467 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.0.conv_dw.weight": "pytorch_model-00002-of-00002.bin",
|
468 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.0.gamma": "pytorch_model-00002-of-00002.bin",
|
469 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.0.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
|
470 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.0.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
|
471 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.0.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
|
472 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.0.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
|
473 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.0.norm.bias": "pytorch_model-00002-of-00002.bin",
|
474 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.0.norm.weight": "pytorch_model-00002-of-00002.bin",
|
475 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.1.conv_dw.bias": "pytorch_model-00002-of-00002.bin",
|
476 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.1.conv_dw.weight": "pytorch_model-00002-of-00002.bin",
|
477 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.1.gamma": "pytorch_model-00002-of-00002.bin",
|
478 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.1.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
|
479 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.1.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
|
480 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.1.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
|
481 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.1.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
|
482 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.1.norm.bias": "pytorch_model-00002-of-00002.bin",
|
483 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.1.norm.weight": "pytorch_model-00002-of-00002.bin",
|
484 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.10.conv_dw.bias": "pytorch_model-00002-of-00002.bin",
|
485 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.10.conv_dw.weight": "pytorch_model-00002-of-00002.bin",
|
486 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.10.gamma": "pytorch_model-00002-of-00002.bin",
|
487 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.10.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
|
488 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.10.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
|
489 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.10.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
|
490 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.10.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
|
491 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.10.norm.bias": "pytorch_model-00002-of-00002.bin",
|
492 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.10.norm.weight": "pytorch_model-00002-of-00002.bin",
|
493 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.11.conv_dw.bias": "pytorch_model-00002-of-00002.bin",
|
494 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.11.conv_dw.weight": "pytorch_model-00002-of-00002.bin",
|
495 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.11.gamma": "pytorch_model-00002-of-00002.bin",
|
496 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.11.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
|
497 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.11.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
|
498 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.11.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
|
499 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.11.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
|
500 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.11.norm.bias": "pytorch_model-00002-of-00002.bin",
|
501 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.11.norm.weight": "pytorch_model-00002-of-00002.bin",
|
502 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.12.conv_dw.bias": "pytorch_model-00002-of-00002.bin",
|
503 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.12.conv_dw.weight": "pytorch_model-00002-of-00002.bin",
|
504 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.12.gamma": "pytorch_model-00002-of-00002.bin",
|
505 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.12.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
|
506 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.12.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
|
507 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.12.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
|
508 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.12.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
|
509 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.12.norm.bias": "pytorch_model-00002-of-00002.bin",
|
510 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.12.norm.weight": "pytorch_model-00002-of-00002.bin",
|
511 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.13.conv_dw.bias": "pytorch_model-00002-of-00002.bin",
|
512 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.13.conv_dw.weight": "pytorch_model-00002-of-00002.bin",
|
513 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.13.gamma": "pytorch_model-00002-of-00002.bin",
|
514 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.13.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
|
515 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.13.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
|
516 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.13.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
|
517 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.13.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
|
518 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.13.norm.bias": "pytorch_model-00002-of-00002.bin",
|
519 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.13.norm.weight": "pytorch_model-00002-of-00002.bin",
|
520 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.14.conv_dw.bias": "pytorch_model-00002-of-00002.bin",
|
521 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.14.conv_dw.weight": "pytorch_model-00002-of-00002.bin",
|
522 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.14.gamma": "pytorch_model-00002-of-00002.bin",
|
523 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.14.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
|
524 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.14.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
|
525 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.14.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
|
526 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.14.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
|
527 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.14.norm.bias": "pytorch_model-00002-of-00002.bin",
|
528 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.14.norm.weight": "pytorch_model-00002-of-00002.bin",
|
529 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.15.conv_dw.bias": "pytorch_model-00002-of-00002.bin",
|
530 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.15.conv_dw.weight": "pytorch_model-00002-of-00002.bin",
|
531 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.15.gamma": "pytorch_model-00002-of-00002.bin",
|
532 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.15.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
|
533 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.15.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
|
534 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.15.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
|
535 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.15.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
|
536 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.15.norm.bias": "pytorch_model-00002-of-00002.bin",
|
537 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.15.norm.weight": "pytorch_model-00002-of-00002.bin",
|
538 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.16.conv_dw.bias": "pytorch_model-00002-of-00002.bin",
|
539 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.16.conv_dw.weight": "pytorch_model-00002-of-00002.bin",
|
540 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.16.gamma": "pytorch_model-00002-of-00002.bin",
|
541 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.16.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
|
542 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.16.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
|
543 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.16.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
|
544 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.16.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
|
545 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.16.norm.bias": "pytorch_model-00002-of-00002.bin",
|
546 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.16.norm.weight": "pytorch_model-00002-of-00002.bin",
|
547 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.17.conv_dw.bias": "pytorch_model-00002-of-00002.bin",
|
548 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.17.conv_dw.weight": "pytorch_model-00002-of-00002.bin",
|
549 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.17.gamma": "pytorch_model-00002-of-00002.bin",
|
550 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.17.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
|
551 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.17.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
|
552 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.17.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
|
553 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.17.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
|
554 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.17.norm.bias": "pytorch_model-00002-of-00002.bin",
|
555 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.17.norm.weight": "pytorch_model-00002-of-00002.bin",
|
556 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.18.conv_dw.bias": "pytorch_model-00002-of-00002.bin",
|
557 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.18.conv_dw.weight": "pytorch_model-00002-of-00002.bin",
|
558 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.18.gamma": "pytorch_model-00002-of-00002.bin",
|
559 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.18.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
|
560 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.18.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
|
561 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.18.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
|
562 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.18.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
|
563 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.18.norm.bias": "pytorch_model-00002-of-00002.bin",
|
564 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.18.norm.weight": "pytorch_model-00002-of-00002.bin",
|
565 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.19.conv_dw.bias": "pytorch_model-00002-of-00002.bin",
|
566 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.19.conv_dw.weight": "pytorch_model-00002-of-00002.bin",
|
567 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.19.gamma": "pytorch_model-00002-of-00002.bin",
|
568 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.19.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
|
569 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.19.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
|
570 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.19.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
|
571 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.19.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
|
572 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.19.norm.bias": "pytorch_model-00002-of-00002.bin",
|
573 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.19.norm.weight": "pytorch_model-00002-of-00002.bin",
|
574 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.2.conv_dw.bias": "pytorch_model-00002-of-00002.bin",
|
575 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.2.conv_dw.weight": "pytorch_model-00002-of-00002.bin",
|
576 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.2.gamma": "pytorch_model-00002-of-00002.bin",
|
577 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.2.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
|
578 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.2.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
|
579 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.2.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
|
580 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.2.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
|
581 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.2.norm.bias": "pytorch_model-00002-of-00002.bin",
|
582 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.2.norm.weight": "pytorch_model-00002-of-00002.bin",
|
583 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.20.conv_dw.bias": "pytorch_model-00002-of-00002.bin",
|
584 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.20.conv_dw.weight": "pytorch_model-00002-of-00002.bin",
|
585 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.20.gamma": "pytorch_model-00002-of-00002.bin",
|
586 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.20.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
|
587 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.20.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
|
588 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.20.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
|
589 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.20.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
|
590 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.20.norm.bias": "pytorch_model-00002-of-00002.bin",
|
591 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.20.norm.weight": "pytorch_model-00002-of-00002.bin",
|
592 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.21.conv_dw.bias": "pytorch_model-00002-of-00002.bin",
|
593 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.21.conv_dw.weight": "pytorch_model-00002-of-00002.bin",
|
594 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.21.gamma": "pytorch_model-00002-of-00002.bin",
|
595 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.21.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
|
596 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.21.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
|
597 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.21.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
|
598 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.21.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
|
599 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.21.norm.bias": "pytorch_model-00002-of-00002.bin",
|
600 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.21.norm.weight": "pytorch_model-00002-of-00002.bin",
|
601 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.22.conv_dw.bias": "pytorch_model-00002-of-00002.bin",
|
602 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.22.conv_dw.weight": "pytorch_model-00002-of-00002.bin",
|
603 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.22.gamma": "pytorch_model-00002-of-00002.bin",
|
604 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.22.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
|
605 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.22.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
|
606 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.22.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
|
607 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.22.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
|
608 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.22.norm.bias": "pytorch_model-00002-of-00002.bin",
|
609 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.22.norm.weight": "pytorch_model-00002-of-00002.bin",
|
610 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.23.conv_dw.bias": "pytorch_model-00002-of-00002.bin",
|
611 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.23.conv_dw.weight": "pytorch_model-00002-of-00002.bin",
|
612 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.23.gamma": "pytorch_model-00002-of-00002.bin",
|
613 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.23.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
|
614 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.23.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
|
615 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.23.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
|
616 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.23.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
|
617 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.23.norm.bias": "pytorch_model-00002-of-00002.bin",
|
618 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.23.norm.weight": "pytorch_model-00002-of-00002.bin",
|
619 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.24.conv_dw.bias": "pytorch_model-00002-of-00002.bin",
|
620 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.24.conv_dw.weight": "pytorch_model-00002-of-00002.bin",
|
621 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.24.gamma": "pytorch_model-00002-of-00002.bin",
|
622 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.24.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
|
623 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.24.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
|
624 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.24.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
|
625 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.24.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
|
626 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.24.norm.bias": "pytorch_model-00002-of-00002.bin",
|
627 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.24.norm.weight": "pytorch_model-00002-of-00002.bin",
|
628 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.25.conv_dw.bias": "pytorch_model-00002-of-00002.bin",
|
629 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.25.conv_dw.weight": "pytorch_model-00002-of-00002.bin",
|
630 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.25.gamma": "pytorch_model-00002-of-00002.bin",
|
631 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.25.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
|
632 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.25.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
|
633 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.25.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
|
634 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.25.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
|
635 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.25.norm.bias": "pytorch_model-00002-of-00002.bin",
|
636 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.25.norm.weight": "pytorch_model-00002-of-00002.bin",
|
637 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.26.conv_dw.bias": "pytorch_model-00002-of-00002.bin",
|
638 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.26.conv_dw.weight": "pytorch_model-00002-of-00002.bin",
|
639 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.26.gamma": "pytorch_model-00002-of-00002.bin",
|
640 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.26.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
|
641 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.26.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
|
642 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.26.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
|
643 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.26.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
|
644 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.26.norm.bias": "pytorch_model-00002-of-00002.bin",
|
645 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.26.norm.weight": "pytorch_model-00002-of-00002.bin",
|
646 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.3.conv_dw.bias": "pytorch_model-00002-of-00002.bin",
|
647 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.3.conv_dw.weight": "pytorch_model-00002-of-00002.bin",
|
648 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.3.gamma": "pytorch_model-00002-of-00002.bin",
|
649 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.3.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
|
650 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.3.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
|
651 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.3.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
|
652 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.3.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
|
653 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.3.norm.bias": "pytorch_model-00002-of-00002.bin",
|
654 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.3.norm.weight": "pytorch_model-00002-of-00002.bin",
|
655 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.4.conv_dw.bias": "pytorch_model-00002-of-00002.bin",
|
656 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.4.conv_dw.weight": "pytorch_model-00002-of-00002.bin",
|
657 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.4.gamma": "pytorch_model-00002-of-00002.bin",
|
658 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.4.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
|
659 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.4.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
|
660 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.4.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
|
661 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.4.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
|
662 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.4.norm.bias": "pytorch_model-00002-of-00002.bin",
|
663 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.4.norm.weight": "pytorch_model-00002-of-00002.bin",
|
664 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.5.conv_dw.bias": "pytorch_model-00002-of-00002.bin",
|
665 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.5.conv_dw.weight": "pytorch_model-00002-of-00002.bin",
|
666 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.5.gamma": "pytorch_model-00002-of-00002.bin",
|
667 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.5.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
|
668 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.5.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
|
669 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.5.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
|
670 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.5.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
|
671 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.5.norm.bias": "pytorch_model-00002-of-00002.bin",
|
672 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.5.norm.weight": "pytorch_model-00002-of-00002.bin",
|
673 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.6.conv_dw.bias": "pytorch_model-00002-of-00002.bin",
|
674 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.6.conv_dw.weight": "pytorch_model-00002-of-00002.bin",
|
675 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.6.gamma": "pytorch_model-00002-of-00002.bin",
|
676 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.6.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
|
677 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.6.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
|
678 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.6.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
|
679 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.6.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
|
680 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.6.norm.bias": "pytorch_model-00002-of-00002.bin",
|
681 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.6.norm.weight": "pytorch_model-00002-of-00002.bin",
|
682 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.7.conv_dw.bias": "pytorch_model-00002-of-00002.bin",
|
683 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.7.conv_dw.weight": "pytorch_model-00002-of-00002.bin",
|
684 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.7.gamma": "pytorch_model-00002-of-00002.bin",
|
685 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.7.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
|
686 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.7.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
|
687 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.7.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
|
688 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.7.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
|
689 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.7.norm.bias": "pytorch_model-00002-of-00002.bin",
|
690 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.7.norm.weight": "pytorch_model-00002-of-00002.bin",
|
691 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.8.conv_dw.bias": "pytorch_model-00002-of-00002.bin",
|
692 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.8.conv_dw.weight": "pytorch_model-00002-of-00002.bin",
|
693 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.8.gamma": "pytorch_model-00002-of-00002.bin",
|
694 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.8.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
|
695 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.8.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
|
696 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.8.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
|
697 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.8.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
|
698 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.8.norm.bias": "pytorch_model-00002-of-00002.bin",
|
699 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.8.norm.weight": "pytorch_model-00002-of-00002.bin",
|
700 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.9.conv_dw.bias": "pytorch_model-00002-of-00002.bin",
|
701 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.9.conv_dw.weight": "pytorch_model-00002-of-00002.bin",
|
702 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.9.gamma": "pytorch_model-00002-of-00002.bin",
|
703 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.9.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
|
704 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.9.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
|
705 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.9.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
|
706 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.9.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
|
707 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.9.norm.bias": "pytorch_model-00002-of-00002.bin",
|
708 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.blocks.9.norm.weight": "pytorch_model-00002-of-00002.bin",
|
709 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.downsample.0.bias": "pytorch_model-00002-of-00002.bin",
|
710 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.downsample.0.weight": "pytorch_model-00002-of-00002.bin",
|
711 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.downsample.1.bias": "pytorch_model-00002-of-00002.bin",
|
712 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.2.downsample.1.weight": "pytorch_model-00002-of-00002.bin",
|
713 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.3.blocks.0.conv_dw.bias": "pytorch_model-00002-of-00002.bin",
|
714 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.3.blocks.0.conv_dw.weight": "pytorch_model-00002-of-00002.bin",
|
715 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.3.blocks.0.gamma": "pytorch_model-00002-of-00002.bin",
|
716 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.3.blocks.0.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
|
717 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.3.blocks.0.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
|
718 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.3.blocks.0.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
|
719 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.3.blocks.0.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
|
720 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.3.blocks.0.norm.bias": "pytorch_model-00002-of-00002.bin",
|
721 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.3.blocks.0.norm.weight": "pytorch_model-00002-of-00002.bin",
|
722 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.3.blocks.1.conv_dw.bias": "pytorch_model-00002-of-00002.bin",
|
723 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.3.blocks.1.conv_dw.weight": "pytorch_model-00002-of-00002.bin",
|
724 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.3.blocks.1.gamma": "pytorch_model-00002-of-00002.bin",
|
725 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.3.blocks.1.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
|
726 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.3.blocks.1.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
|
727 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.3.blocks.1.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
|
728 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.3.blocks.1.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
|
729 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.3.blocks.1.norm.bias": "pytorch_model-00002-of-00002.bin",
|
730 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.3.blocks.1.norm.weight": "pytorch_model-00002-of-00002.bin",
|
731 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.3.blocks.2.conv_dw.bias": "pytorch_model-00002-of-00002.bin",
|
732 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.3.blocks.2.conv_dw.weight": "pytorch_model-00002-of-00002.bin",
|
733 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.3.blocks.2.gamma": "pytorch_model-00002-of-00002.bin",
|
734 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.3.blocks.2.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
|
735 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.3.blocks.2.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
|
736 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.3.blocks.2.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
|
737 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.3.blocks.2.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
|
738 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.3.blocks.2.norm.bias": "pytorch_model-00002-of-00002.bin",
|
739 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.3.blocks.2.norm.weight": "pytorch_model-00002-of-00002.bin",
|
740 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.3.downsample.0.bias": "pytorch_model-00002-of-00002.bin",
|
741 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.3.downsample.0.weight": "pytorch_model-00002-of-00002.bin",
|
742 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.3.downsample.1.bias": "pytorch_model-00002-of-00002.bin",
|
743 |
-
"model.vision_tower.vision_tower.visual.trunk.stages.3.downsample.1.weight": "pytorch_model-00002-of-00002.bin",
|
744 |
-
"model.vision_tower.vision_tower.visual.trunk.stem.0.bias": "pytorch_model-00002-of-00002.bin",
|
745 |
-
"model.vision_tower.vision_tower.visual.trunk.stem.0.weight": "pytorch_model-00002-of-00002.bin",
|
746 |
-
"model.vision_tower.vision_tower.visual.trunk.stem.1.bias": "pytorch_model-00002-of-00002.bin",
|
747 |
-
"model.vision_tower.vision_tower.visual.trunk.stem.1.weight": "pytorch_model-00002-of-00002.bin"
|
748 |
-
}
|
749 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoints/SEAGULL-7B/special_tokens_map.json
DELETED
@@ -1,24 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"bos_token": {
|
3 |
-
"content": "<s>",
|
4 |
-
"lstrip": false,
|
5 |
-
"normalized": false,
|
6 |
-
"rstrip": false,
|
7 |
-
"single_word": false
|
8 |
-
},
|
9 |
-
"eos_token": {
|
10 |
-
"content": "</s>",
|
11 |
-
"lstrip": false,
|
12 |
-
"normalized": false,
|
13 |
-
"rstrip": false,
|
14 |
-
"single_word": false
|
15 |
-
},
|
16 |
-
"pad_token": "<unk>",
|
17 |
-
"unk_token": {
|
18 |
-
"content": "<unk>",
|
19 |
-
"lstrip": false,
|
20 |
-
"normalized": false,
|
21 |
-
"rstrip": false,
|
22 |
-
"single_word": false
|
23 |
-
}
|
24 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoints/SEAGULL-7B/tokenizer.model
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
3 |
-
size 499723
|
|
|
|
|
|
|
|
checkpoints/SEAGULL-7B/tokenizer_config.json
DELETED
@@ -1,35 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"add_bos_token": true,
|
3 |
-
"add_eos_token": false,
|
4 |
-
"bos_token": {
|
5 |
-
"__type": "AddedToken",
|
6 |
-
"content": "<s>",
|
7 |
-
"lstrip": false,
|
8 |
-
"normalized": false,
|
9 |
-
"rstrip": false,
|
10 |
-
"single_word": false
|
11 |
-
},
|
12 |
-
"clean_up_tokenization_spaces": false,
|
13 |
-
"eos_token": {
|
14 |
-
"__type": "AddedToken",
|
15 |
-
"content": "</s>",
|
16 |
-
"lstrip": false,
|
17 |
-
"normalized": false,
|
18 |
-
"rstrip": false,
|
19 |
-
"single_word": false
|
20 |
-
},
|
21 |
-
"legacy": false,
|
22 |
-
"model_max_length": 2048,
|
23 |
-
"pad_token": null,
|
24 |
-
"padding_side": "right",
|
25 |
-
"sp_model_kwargs": {},
|
26 |
-
"tokenizer_class": "LlamaTokenizer",
|
27 |
-
"unk_token": {
|
28 |
-
"__type": "AddedToken",
|
29 |
-
"content": "<unk>",
|
30 |
-
"lstrip": false,
|
31 |
-
"normalized": false,
|
32 |
-
"rstrip": false,
|
33 |
-
"single_word": false
|
34 |
-
}
|
35 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|