Hugging Face's logo

idekoh
/
Multi-3DLLM

Text Generation
English
3d
point-cloud
multimodal
multi-object
pointllm
modelnet40
Model card Files
xet
 Community
idekoh commited on
Commit
c8c6233
·
verified ·
1 Parent(s): c8b54e6

Move checkpoints into subfolders

Browse files
Files changed (11) hide show
  1. added_tokens.json +0 -5
  2. config.json +0 -37
  3. generation_config.json +0 -7
  4. point_proj.bin +0 -3
  5. pytorch_model-00001-of-00003.bin +0 -3
  6. pytorch_model-00002-of-00003.bin +0 -3
  7. pytorch_model-00003-of-00003.bin +0 -3
  8. pytorch_model.bin.index.json +0 -510
  9. special_tokens_map.json +0 -24
  10. tokenizer.model +0 -3
  11. tokenizer_config.json +0 -32
added_tokens.json DELETED
@@ -1,5 +0,0 @@
1
- {
2
- "<point_end>": 32002,
3
- "<point_patch>": 32000,
4
- "<point_start>": 32001
5
- }
 
 
 
 
 
 
config.json DELETED
@@ -1,37 +0,0 @@
1
- {
2
- "DEFAULT_POINT_END_TOKEN": "<point_end>",
3
- "DEFAULT_POINT_PATCH_TOKEN": "<point_patch>",
4
- "DEFAULT_POINT_START_TOKEN": "<point_start>",
5
- "_name_or_path": "/groups/gag51404/ide/BeyondSIngleObject/outputs/finetune/joint_release_uniform3_32gpu_20260526_2142_uniform3",
6
- "architectures": [
7
- "PointLLMCVPRLlamaForCausalLM"
8
- ],
9
- "bos_token_id": 1,
10
- "cvpr_force_object_token_pooling": false,
11
- "cvpr_object_pooling_type": "mean",
12
- "cvpr_relation_mode": "patch",
13
- "cvpr_relation_patch_gamma": 1.0,
14
- "cvpr_relation_use_adaln": false,
15
- "cvpr_use_relation_module": true,
16
- "eos_token_id": 2,
17
- "hidden_act": "silu",
18
- "hidden_size": 4096,
19
- "initializer_range": 0.02,
20
- "intermediate_size": 11008,
21
- "max_position_embeddings": 2048,
22
- "mm_use_point_start_end": true,
23
- "model_type": "pointllm",
24
- "num_attention_heads": 32,
25
- "num_hidden_layers": 32,
26
- "pad_token_id": 0,
27
- "point_backbone": "PointBERT",
28
- "point_backbone_ckpt": "",
29
- "point_backbone_config_name": "PointTransformer_8192point_2layer",
30
- "rms_norm_eps": 1e-06,
31
- "tie_word_embeddings": false,
32
- "torch_dtype": "float32",
33
- "transformers_version": "4.28.0.dev0",
34
- "use_cache": false,
35
- "use_color": true,
36
- "vocab_size": 32003
37
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
generation_config.json DELETED
@@ -1,7 +0,0 @@
1
- {
2
- "_from_model_config": true,
3
- "bos_token_id": 1,
4
- "eos_token_id": 2,
5
- "pad_token_id": 0,
6
- "transformers_version": "4.28.0.dev0"
7
- }
 
 
 
 
 
 
 
 
point_proj.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:6be00bbe048381a1311358b314ef1ae399eade6cfedffee521f2b961ef01e797
3
- size 567885048
 
 
 
 
pytorch_model-00001-of-00003.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:c516359ab4995a23404cba2a886c8d28215e0a9e0d75d671a8f97a126adb69cf
3
- size 9878039688
 
 
 
 
pytorch_model-00002-of-00003.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:33bdb8bb1ab1092add7bf6a6c26ef94bfbb59a5882bfac977a16e70483d16922
3
- size 9894801940
 
 
 
 
pytorch_model-00003-of-00003.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:dd82457d8e8344f58ff2c9acf07dd8cfddcab0c92972316c05b7a33f6f61a859
3
- size 8117611116
 
 
 
 
pytorch_model.bin.index.json DELETED
@@ -1,510 +0,0 @@
1
- {
2
- "metadata": {
3
- "total_size": 27890274832
4
- },
5
- "weight_map": {
6
- "lm_head.weight": "pytorch_model-00003-of-00003.bin",
7
- "model.embed_tokens.weight": "pytorch_model-00001-of-00003.bin",
8
- "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
9
- "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
10
- "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
11
- "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
12
- "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
13
- "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
14
- "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
15
- "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
16
- "model.layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
17
- "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
18
- "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
19
- "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
20
- "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
21
- "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
22
- "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
23
- "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
24
- "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
25
- "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
26
- "model.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
27
- "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
28
- "model.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
29
- "model.layers.10.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
30
- "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
31
- "model.layers.10.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
32
- "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
33
- "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
34
- "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
35
- "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
36
- "model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
37
- "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
38
- "model.layers.11.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
39
- "model.layers.11.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
40
- "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
41
- "model.layers.11.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
42
- "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
43
- "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
44
- "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
45
- "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
46
- "model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
47
- "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
48
- "model.layers.12.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
49
- "model.layers.12.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
50
- "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
51
- "model.layers.12.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
52
- "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
53
- "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
54
- "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
55
- "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
56
- "model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
57
- "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
58
- "model.layers.13.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
59
- "model.layers.13.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
60
- "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
61
- "model.layers.13.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
62
- "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
63
- "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
64
- "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
65
- "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
66
- "model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
67
- "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
68
- "model.layers.14.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
69
- "model.layers.14.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
70
- "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
71
- "model.layers.14.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
72
- "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
73
- "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
74
- "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
75
- "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
76
- "model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
77
- "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
78
- "model.layers.15.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
79
- "model.layers.15.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
80
- "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
81
- "model.layers.15.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
82
- "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
83
- "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
84
- "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
85
- "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
86
- "model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
87
- "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
88
- "model.layers.16.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
89
- "model.layers.16.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
90
- "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
91
- "model.layers.16.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
92
- "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
93
- "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
94
- "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
95
- "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
96
- "model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
97
- "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
98
- "model.layers.17.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
99
- "model.layers.17.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
100
- "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
101
- "model.layers.17.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
102
- "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
103
- "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
104
- "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
105
- "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
106
- "model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
107
- "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
108
- "model.layers.18.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
109
- "model.layers.18.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
110
- "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
111
- "model.layers.18.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
112
- "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
113
- "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
114
- "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
115
- "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
116
- "model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
117
- "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
118
- "model.layers.19.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
119
- "model.layers.19.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
120
- "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
121
- "model.layers.19.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
122
- "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
123
- "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
124
- "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
125
- "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
126
- "model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
127
- "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
128
- "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
129
- "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
130
- "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
131
- "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
132
- "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
133
- "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
134
- "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
135
- "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
136
- "model.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
137
- "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
138
- "model.layers.20.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
139
- "model.layers.20.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
140
- "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
141
- "model.layers.20.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
142
- "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
143
- "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
144
- "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
145
- "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
146
- "model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
147
- "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
148
- "model.layers.21.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
149
- "model.layers.21.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
150
- "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
151
- "model.layers.21.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
152
- "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
153
- "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
154
- "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
155
- "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
156
- "model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
157
- "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
158
- "model.layers.22.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
159
- "model.layers.22.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
160
- "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
161
- "model.layers.22.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
162
- "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
163
- "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
164
- "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
165
- "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
166
- "model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
167
- "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
168
- "model.layers.23.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
169
- "model.layers.23.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
170
- "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
171
- "model.layers.23.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
172
- "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
173
- "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
174
- "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
175
- "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
176
- "model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
177
- "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
178
- "model.layers.24.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
179
- "model.layers.24.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
180
- "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
181
- "model.layers.24.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
182
- "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
183
- "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
184
- "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
185
- "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
186
- "model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
187
- "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
188
- "model.layers.25.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
189
- "model.layers.25.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
190
- "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
191
- "model.layers.25.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
192
- "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
193
- "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
194
- "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
195
- "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
196
- "model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
197
- "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
198
- "model.layers.26.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
199
- "model.layers.26.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
200
- "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
201
- "model.layers.26.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
202
- "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
203
- "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
204
- "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
205
- "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
206
- "model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
207
- "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
208
- "model.layers.27.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
209
- "model.layers.27.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
210
- "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
211
- "model.layers.27.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
212
- "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
213
- "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
214
- "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
215
- "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
216
- "model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
217
- "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
218
- "model.layers.28.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
219
- "model.layers.28.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
220
- "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
221
- "model.layers.28.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
222
- "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
223
- "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
224
- "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
225
- "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
226
- "model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
227
- "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
228
- "model.layers.29.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
229
- "model.layers.29.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
230
- "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
231
- "model.layers.29.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
232
- "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
233
- "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
234
- "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
235
- "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
236
- "model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
237
- "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
238
- "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
239
- "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
240
- "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
241
- "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
242
- "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
243
- "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
244
- "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
245
- "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
246
- "model.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
247
- "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
248
- "model.layers.30.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
249
- "model.layers.30.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
250
- "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
251
- "model.layers.30.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
252
- "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
253
- "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
254
- "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
255
- "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
256
- "model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
257
- "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
258
- "model.layers.31.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
259
- "model.layers.31.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
260
- "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
261
- "model.layers.31.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
262
- "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
263
- "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
264
- "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
265
- "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
266
- "model.layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
267
- "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
268
- "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
269
- "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
270
- "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
271
- "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
272
- "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
273
- "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
274
- "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
275
- "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
276
- "model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
277
- "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
278
- "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
279
- "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
280
- "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
281
- "model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
282
- "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
283
- "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
284
- "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
285
- "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
286
- "model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
287
- "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
288
- "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
289
- "model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
290
- "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
291
- "model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
292
- "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
293
- "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
294
- "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
295
- "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
296
- "model.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
297
- "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
298
- "model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
299
- "model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
300
- "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
301
- "model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
302
- "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
303
- "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
304
- "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
305
- "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
306
- "model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
307
- "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
308
- "model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
309
- "model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
310
- "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
311
- "model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
312
- "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
313
- "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
314
- "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
315
- "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
316
- "model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
317
- "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
318
- "model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
319
- "model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
320
- "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
321
- "model.layers.9.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
322
- "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
323
- "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
324
- "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
325
- "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
326
- "model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
327
- "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
328
- "model.norm.weight": "pytorch_model-00003-of-00003.bin",
329
- "model.point_backbone.blocks.blocks.0.attn.proj.bias": "pytorch_model-00003-of-00003.bin",
330
- "model.point_backbone.blocks.blocks.0.attn.proj.weight": "pytorch_model-00003-of-00003.bin",
331
- "model.point_backbone.blocks.blocks.0.attn.qkv.weight": "pytorch_model-00003-of-00003.bin",
332
- "model.point_backbone.blocks.blocks.0.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
333
- "model.point_backbone.blocks.blocks.0.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
334
- "model.point_backbone.blocks.blocks.0.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
335
- "model.point_backbone.blocks.blocks.0.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
336
- "model.point_backbone.blocks.blocks.0.norm1.bias": "pytorch_model-00003-of-00003.bin",
337
- "model.point_backbone.blocks.blocks.0.norm1.weight": "pytorch_model-00003-of-00003.bin",
338
- "model.point_backbone.blocks.blocks.0.norm2.bias": "pytorch_model-00003-of-00003.bin",
339
- "model.point_backbone.blocks.blocks.0.norm2.weight": "pytorch_model-00003-of-00003.bin",
340
- "model.point_backbone.blocks.blocks.1.attn.proj.bias": "pytorch_model-00003-of-00003.bin",
341
- "model.point_backbone.blocks.blocks.1.attn.proj.weight": "pytorch_model-00003-of-00003.bin",
342
- "model.point_backbone.blocks.blocks.1.attn.qkv.weight": "pytorch_model-00003-of-00003.bin",
343
- "model.point_backbone.blocks.blocks.1.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
344
- "model.point_backbone.blocks.blocks.1.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
345
- "model.point_backbone.blocks.blocks.1.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
346
- "model.point_backbone.blocks.blocks.1.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
347
- "model.point_backbone.blocks.blocks.1.norm1.bias": "pytorch_model-00003-of-00003.bin",
348
- "model.point_backbone.blocks.blocks.1.norm1.weight": "pytorch_model-00003-of-00003.bin",
349
- "model.point_backbone.blocks.blocks.1.norm2.bias": "pytorch_model-00003-of-00003.bin",
350
- "model.point_backbone.blocks.blocks.1.norm2.weight": "pytorch_model-00003-of-00003.bin",
351
- "model.point_backbone.blocks.blocks.10.attn.proj.bias": "pytorch_model-00003-of-00003.bin",
352
- "model.point_backbone.blocks.blocks.10.attn.proj.weight": "pytorch_model-00003-of-00003.bin",
353
- "model.point_backbone.blocks.blocks.10.attn.qkv.weight": "pytorch_model-00003-of-00003.bin",
354
- "model.point_backbone.blocks.blocks.10.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
355
- "model.point_backbone.blocks.blocks.10.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
356
- "model.point_backbone.blocks.blocks.10.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
357
- "model.point_backbone.blocks.blocks.10.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
358
- "model.point_backbone.blocks.blocks.10.norm1.bias": "pytorch_model-00003-of-00003.bin",
359
- "model.point_backbone.blocks.blocks.10.norm1.weight": "pytorch_model-00003-of-00003.bin",
360
- "model.point_backbone.blocks.blocks.10.norm2.bias": "pytorch_model-00003-of-00003.bin",
361
- "model.point_backbone.blocks.blocks.10.norm2.weight": "pytorch_model-00003-of-00003.bin",
362
- "model.point_backbone.blocks.blocks.11.attn.proj.bias": "pytorch_model-00003-of-00003.bin",
363
- "model.point_backbone.blocks.blocks.11.attn.proj.weight": "pytorch_model-00003-of-00003.bin",
364
- "model.point_backbone.blocks.blocks.11.attn.qkv.weight": "pytorch_model-00003-of-00003.bin",
365
- "model.point_backbone.blocks.blocks.11.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
366
- "model.point_backbone.blocks.blocks.11.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
367
- "model.point_backbone.blocks.blocks.11.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
368
- "model.point_backbone.blocks.blocks.11.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
369
- "model.point_backbone.blocks.blocks.11.norm1.bias": "pytorch_model-00003-of-00003.bin",
370
- "model.point_backbone.blocks.blocks.11.norm1.weight": "pytorch_model-00003-of-00003.bin",
371
- "model.point_backbone.blocks.blocks.11.norm2.bias": "pytorch_model-00003-of-00003.bin",
372
- "model.point_backbone.blocks.blocks.11.norm2.weight": "pytorch_model-00003-of-00003.bin",
373
- "model.point_backbone.blocks.blocks.2.attn.proj.bias": "pytorch_model-00003-of-00003.bin",
374
- "model.point_backbone.blocks.blocks.2.attn.proj.weight": "pytorch_model-00003-of-00003.bin",
375
- "model.point_backbone.blocks.blocks.2.attn.qkv.weight": "pytorch_model-00003-of-00003.bin",
376
- "model.point_backbone.blocks.blocks.2.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
377
- "model.point_backbone.blocks.blocks.2.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
378
- "model.point_backbone.blocks.blocks.2.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
379
- "model.point_backbone.blocks.blocks.2.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
380
- "model.point_backbone.blocks.blocks.2.norm1.bias": "pytorch_model-00003-of-00003.bin",
381
- "model.point_backbone.blocks.blocks.2.norm1.weight": "pytorch_model-00003-of-00003.bin",
382
- "model.point_backbone.blocks.blocks.2.norm2.bias": "pytorch_model-00003-of-00003.bin",
383
- "model.point_backbone.blocks.blocks.2.norm2.weight": "pytorch_model-00003-of-00003.bin",
384
- "model.point_backbone.blocks.blocks.3.attn.proj.bias": "pytorch_model-00003-of-00003.bin",
385
- "model.point_backbone.blocks.blocks.3.attn.proj.weight": "pytorch_model-00003-of-00003.bin",
386
- "model.point_backbone.blocks.blocks.3.attn.qkv.weight": "pytorch_model-00003-of-00003.bin",
387
- "model.point_backbone.blocks.blocks.3.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
388
- "model.point_backbone.blocks.blocks.3.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
389
- "model.point_backbone.blocks.blocks.3.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
390
- "model.point_backbone.blocks.blocks.3.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
391
- "model.point_backbone.blocks.blocks.3.norm1.bias": "pytorch_model-00003-of-00003.bin",
392
- "model.point_backbone.blocks.blocks.3.norm1.weight": "pytorch_model-00003-of-00003.bin",
393
- "model.point_backbone.blocks.blocks.3.norm2.bias": "pytorch_model-00003-of-00003.bin",
394
- "model.point_backbone.blocks.blocks.3.norm2.weight": "pytorch_model-00003-of-00003.bin",
395
- "model.point_backbone.blocks.blocks.4.attn.proj.bias": "pytorch_model-00003-of-00003.bin",
396
- "model.point_backbone.blocks.blocks.4.attn.proj.weight": "pytorch_model-00003-of-00003.bin",
397
- "model.point_backbone.blocks.blocks.4.attn.qkv.weight": "pytorch_model-00003-of-00003.bin",
398
- "model.point_backbone.blocks.blocks.4.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
399
- "model.point_backbone.blocks.blocks.4.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
400
- "model.point_backbone.blocks.blocks.4.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
401
- "model.point_backbone.blocks.blocks.4.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
402
- "model.point_backbone.blocks.blocks.4.norm1.bias": "pytorch_model-00003-of-00003.bin",
403
- "model.point_backbone.blocks.blocks.4.norm1.weight": "pytorch_model-00003-of-00003.bin",
404
- "model.point_backbone.blocks.blocks.4.norm2.bias": "pytorch_model-00003-of-00003.bin",
405
- "model.point_backbone.blocks.blocks.4.norm2.weight": "pytorch_model-00003-of-00003.bin",
406
- "model.point_backbone.blocks.blocks.5.attn.proj.bias": "pytorch_model-00003-of-00003.bin",
407
- "model.point_backbone.blocks.blocks.5.attn.proj.weight": "pytorch_model-00003-of-00003.bin",
408
- "model.point_backbone.blocks.blocks.5.attn.qkv.weight": "pytorch_model-00003-of-00003.bin",
409
- "model.point_backbone.blocks.blocks.5.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
410
- "model.point_backbone.blocks.blocks.5.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
411
- "model.point_backbone.blocks.blocks.5.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
412
- "model.point_backbone.blocks.blocks.5.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
413
- "model.point_backbone.blocks.blocks.5.norm1.bias": "pytorch_model-00003-of-00003.bin",
414
- "model.point_backbone.blocks.blocks.5.norm1.weight": "pytorch_model-00003-of-00003.bin",
415
- "model.point_backbone.blocks.blocks.5.norm2.bias": "pytorch_model-00003-of-00003.bin",
416
- "model.point_backbone.blocks.blocks.5.norm2.weight": "pytorch_model-00003-of-00003.bin",
417
- "model.point_backbone.blocks.blocks.6.attn.proj.bias": "pytorch_model-00003-of-00003.bin",
418
- "model.point_backbone.blocks.blocks.6.attn.proj.weight": "pytorch_model-00003-of-00003.bin",
419
- "model.point_backbone.blocks.blocks.6.attn.qkv.weight": "pytorch_model-00003-of-00003.bin",
420
- "model.point_backbone.blocks.blocks.6.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
421
- "model.point_backbone.blocks.blocks.6.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
422
- "model.point_backbone.blocks.blocks.6.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
423
- "model.point_backbone.blocks.blocks.6.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
424
- "model.point_backbone.blocks.blocks.6.norm1.bias": "pytorch_model-00003-of-00003.bin",
425
- "model.point_backbone.blocks.blocks.6.norm1.weight": "pytorch_model-00003-of-00003.bin",
426
- "model.point_backbone.blocks.blocks.6.norm2.bias": "pytorch_model-00003-of-00003.bin",
427
- "model.point_backbone.blocks.blocks.6.norm2.weight": "pytorch_model-00003-of-00003.bin",
428
- "model.point_backbone.blocks.blocks.7.attn.proj.bias": "pytorch_model-00003-of-00003.bin",
429
- "model.point_backbone.blocks.blocks.7.attn.proj.weight": "pytorch_model-00003-of-00003.bin",
430
- "model.point_backbone.blocks.blocks.7.attn.qkv.weight": "pytorch_model-00003-of-00003.bin",
431
- "model.point_backbone.blocks.blocks.7.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
432
- "model.point_backbone.blocks.blocks.7.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
433
- "model.point_backbone.blocks.blocks.7.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
434
- "model.point_backbone.blocks.blocks.7.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
435
- "model.point_backbone.blocks.blocks.7.norm1.bias": "pytorch_model-00003-of-00003.bin",
436
- "model.point_backbone.blocks.blocks.7.norm1.weight": "pytorch_model-00003-of-00003.bin",
437
- "model.point_backbone.blocks.blocks.7.norm2.bias": "pytorch_model-00003-of-00003.bin",
438
- "model.point_backbone.blocks.blocks.7.norm2.weight": "pytorch_model-00003-of-00003.bin",
439
- "model.point_backbone.blocks.blocks.8.attn.proj.bias": "pytorch_model-00003-of-00003.bin",
440
- "model.point_backbone.blocks.blocks.8.attn.proj.weight": "pytorch_model-00003-of-00003.bin",
441
- "model.point_backbone.blocks.blocks.8.attn.qkv.weight": "pytorch_model-00003-of-00003.bin",
442
- "model.point_backbone.blocks.blocks.8.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
443
- "model.point_backbone.blocks.blocks.8.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
444
- "model.point_backbone.blocks.blocks.8.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
445
- "model.point_backbone.blocks.blocks.8.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
446
- "model.point_backbone.blocks.blocks.8.norm1.bias": "pytorch_model-00003-of-00003.bin",
447
- "model.point_backbone.blocks.blocks.8.norm1.weight": "pytorch_model-00003-of-00003.bin",
448
- "model.point_backbone.blocks.blocks.8.norm2.bias": "pytorch_model-00003-of-00003.bin",
449
- "model.point_backbone.blocks.blocks.8.norm2.weight": "pytorch_model-00003-of-00003.bin",
450
- "model.point_backbone.blocks.blocks.9.attn.proj.bias": "pytorch_model-00003-of-00003.bin",
451
- "model.point_backbone.blocks.blocks.9.attn.proj.weight": "pytorch_model-00003-of-00003.bin",
452
- "model.point_backbone.blocks.blocks.9.attn.qkv.weight": "pytorch_model-00003-of-00003.bin",
453
- "model.point_backbone.blocks.blocks.9.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
454
- "model.point_backbone.blocks.blocks.9.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
455
- "model.point_backbone.blocks.blocks.9.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
456
- "model.point_backbone.blocks.blocks.9.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
457
- "model.point_backbone.blocks.blocks.9.norm1.bias": "pytorch_model-00003-of-00003.bin",
458
- "model.point_backbone.blocks.blocks.9.norm1.weight": "pytorch_model-00003-of-00003.bin",
459
- "model.point_backbone.blocks.blocks.9.norm2.bias": "pytorch_model-00003-of-00003.bin",
460
- "model.point_backbone.blocks.blocks.9.norm2.weight": "pytorch_model-00003-of-00003.bin",
461
- "model.point_backbone.cls_pos": "pytorch_model-00003-of-00003.bin",
462
- "model.point_backbone.cls_token": "pytorch_model-00003-of-00003.bin",
463
- "model.point_backbone.encoder.first_conv.0.bias": "pytorch_model-00003-of-00003.bin",
464
- "model.point_backbone.encoder.first_conv.0.weight": "pytorch_model-00003-of-00003.bin",
465
- "model.point_backbone.encoder.first_conv.1.bias": "pytorch_model-00003-of-00003.bin",
466
- "model.point_backbone.encoder.first_conv.1.num_batches_tracked": "pytorch_model-00003-of-00003.bin",
467
- "model.point_backbone.encoder.first_conv.1.running_mean": "pytorch_model-00003-of-00003.bin",
468
- "model.point_backbone.encoder.first_conv.1.running_var": "pytorch_model-00003-of-00003.bin",
469
- "model.point_backbone.encoder.first_conv.1.weight": "pytorch_model-00003-of-00003.bin",
470
- "model.point_backbone.encoder.first_conv.3.bias": "pytorch_model-00003-of-00003.bin",
471
- "model.point_backbone.encoder.first_conv.3.weight": "pytorch_model-00003-of-00003.bin",
472
- "model.point_backbone.encoder.second_conv.0.bias": "pytorch_model-00003-of-00003.bin",
473
- "model.point_backbone.encoder.second_conv.0.weight": "pytorch_model-00003-of-00003.bin",
474
- "model.point_backbone.encoder.second_conv.1.bias": "pytorch_model-00003-of-00003.bin",
475
- "model.point_backbone.encoder.second_conv.1.num_batches_tracked": "pytorch_model-00003-of-00003.bin",
476
- "model.point_backbone.encoder.second_conv.1.running_mean": "pytorch_model-00003-of-00003.bin",
477
- "model.point_backbone.encoder.second_conv.1.running_var": "pytorch_model-00003-of-00003.bin",
478
- "model.point_backbone.encoder.second_conv.1.weight": "pytorch_model-00003-of-00003.bin",
479
- "model.point_backbone.encoder.second_conv.3.bias": "pytorch_model-00003-of-00003.bin",
480
- "model.point_backbone.encoder.second_conv.3.weight": "pytorch_model-00003-of-00003.bin",
481
- "model.point_backbone.norm.bias": "pytorch_model-00003-of-00003.bin",
482
- "model.point_backbone.norm.weight": "pytorch_model-00003-of-00003.bin",
483
- "model.point_backbone.pos_embed.0.bias": "pytorch_model-00003-of-00003.bin",
484
- "model.point_backbone.pos_embed.0.weight": "pytorch_model-00003-of-00003.bin",
485
- "model.point_backbone.pos_embed.2.bias": "pytorch_model-00003-of-00003.bin",
486
- "model.point_backbone.pos_embed.2.weight": "pytorch_model-00003-of-00003.bin",
487
- "model.point_backbone.reduce_dim.bias": "pytorch_model-00003-of-00003.bin",
488
- "model.point_backbone.reduce_dim.weight": "pytorch_model-00003-of-00003.bin",
489
- "model.point_proj.0.bias": "pytorch_model-00003-of-00003.bin",
490
- "model.point_proj.0.weight": "pytorch_model-00003-of-00003.bin",
491
- "model.point_proj.2.bias": "pytorch_model-00003-of-00003.bin",
492
- "model.point_proj.2.weight": "pytorch_model-00003-of-00003.bin",
493
- "model.point_proj.4.bias": "pytorch_model-00003-of-00003.bin",
494
- "model.point_proj.4.weight": "pytorch_model-00003-of-00003.bin",
495
- "model.relation_module.encoder.layers.0.adaln_ffn.norm.bias": "pytorch_model-00003-of-00003.bin",
496
- "model.relation_module.encoder.layers.0.adaln_ffn.norm.weight": "pytorch_model-00003-of-00003.bin",
497
- "model.relation_module.encoder.layers.0.adaln_msa.norm.bias": "pytorch_model-00003-of-00003.bin",
498
- "model.relation_module.encoder.layers.0.adaln_msa.norm.weight": "pytorch_model-00003-of-00003.bin",
499
- "model.relation_module.encoder.layers.0.linear.0.bias": "pytorch_model-00003-of-00003.bin",
500
- "model.relation_module.encoder.layers.0.linear.0.weight": "pytorch_model-00003-of-00003.bin",
501
- "model.relation_module.encoder.layers.0.linear.3.bias": "pytorch_model-00003-of-00003.bin",
502
- "model.relation_module.encoder.layers.0.linear.3.weight": "pytorch_model-00003-of-00003.bin",
503
- "model.relation_module.encoder.layers.0.mhsa.W_0.weight": "pytorch_model-00003-of-00003.bin",
504
- "model.relation_module.encoder.layers.0.mhsa.to_qvk.weight": "pytorch_model-00003-of-00003.bin",
505
- "model.relation_module.encoder.layers.0.norm_1.bias": "pytorch_model-00003-of-00003.bin",
506
- "model.relation_module.encoder.layers.0.norm_1.weight": "pytorch_model-00003-of-00003.bin",
507
- "model.relation_module.encoder.layers.0.norm_2.bias": "pytorch_model-00003-of-00003.bin",
508
- "model.relation_module.encoder.layers.0.norm_2.weight": "pytorch_model-00003-of-00003.bin"
509
- }
510
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
special_tokens_map.json DELETED
@@ -1,24 +0,0 @@
1
- {
2
- "bos_token": {
3
- "content": "<s>",
4
- "lstrip": false,
5
- "normalized": true,
6
- "rstrip": false,
7
- "single_word": false
8
- },
9
- "eos_token": {
10
- "content": "</s>",
11
- "lstrip": false,
12
- "normalized": true,
13
- "rstrip": false,
14
- "single_word": false
15
- },
16
- "pad_token": "<unk>",
17
- "unk_token": {
18
- "content": "<unk>",
19
- "lstrip": false,
20
- "normalized": true,
21
- "rstrip": false,
22
- "single_word": false
23
- }
24
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
tokenizer.model DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
- size 499723
 
 
 
 
tokenizer_config.json DELETED
@@ -1,32 +0,0 @@
1
- {
2
- "bos_token": {
3
- "__type": "AddedToken",
4
- "content": "<s>",
5
- "lstrip": false,
6
- "normalized": true,
7
- "rstrip": false,
8
- "single_word": false
9
- },
10
- "clean_up_tokenization_spaces": false,
11
- "eos_token": {
12
- "__type": "AddedToken",
13
- "content": "</s>",
14
- "lstrip": false,
15
- "normalized": true,
16
- "rstrip": false,
17
- "single_word": false
18
- },
19
- "model_max_length": 2048,
20
- "pad_token": null,
21
- "padding_side": "right",
22
- "special_tokens_map_file": "checkpoints/PointLLM_7B_v1.1_init/special_tokens_map.json",
23
- "tokenizer_class": "LlamaTokenizer",
24
- "unk_token": {
25
- "__type": "AddedToken",
26
- "content": "<unk>",
27
- "lstrip": false,
28
- "normalized": true,
29
- "rstrip": false,
30
- "single_word": false
31
- }
32
- }