Upload model
Browse files- CXR_LLAVA_HF.py +35 -1
- config.json +5 -4
- generation_config.json +1 -1
- model-00001-of-00003.safetensors +3 -0
- model-00002-of-00003.safetensors +3 -0
- model-00003-of-00003.safetensors +3 -0
- model.safetensors.index.json +596 -0
CXR_LLAVA_HF.py
CHANGED
@@ -7,6 +7,7 @@ from functools import partial
|
|
7 |
from transformers import TextIteratorStreamer
|
8 |
from transformers import StoppingCriteria, GenerationConfig
|
9 |
from threading import Thread
|
|
|
10 |
|
11 |
# Model Constants
|
12 |
IGNORE_INDEX = -100
|
@@ -19,6 +20,11 @@ class AttrDict(dict):
|
|
19 |
def __init__(self, *args, **kwargs):
|
20 |
super(AttrDict, self).__init__(*args, **kwargs)
|
21 |
self.__dict__ = self
|
|
|
|
|
|
|
|
|
|
|
22 |
|
23 |
class CXRLLAVAConfig(PretrainedConfig):
|
24 |
model_type = "CXR-LLAVA"
|
@@ -45,7 +51,6 @@ class CXRLLAVAModel(PreTrainedModel):
|
|
45 |
self.tokenizer.cls_token = self.tokenizer.unk_token
|
46 |
self.tokenizer.mask_token = self.tokenizer.unk_token
|
47 |
|
48 |
-
from open_clip.model import CLIPVisionCfg
|
49 |
vision_cfg = CLIPVisionCfg(**config.clip_vision_cfg)
|
50 |
|
51 |
self.generation_config = GenerationConfig.from_pretrained(config._name_or_path)
|
@@ -669,3 +674,32 @@ class KeywordsStoppingCriteria(StoppingCriteria):
|
|
669 |
if keyword in outputs:
|
670 |
return True
|
671 |
return False
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
7 |
from transformers import TextIteratorStreamer
|
8 |
from transformers import StoppingCriteria, GenerationConfig
|
9 |
from threading import Thread
|
10 |
+
from dataclasses import dataclass
|
11 |
|
12 |
# Model Constants
|
13 |
IGNORE_INDEX = -100
|
|
|
20 |
def __init__(self, *args, **kwargs):
|
21 |
super(AttrDict, self).__init__(*args, **kwargs)
|
22 |
self.__dict__ = self
|
23 |
+
def __getattr__(self, key):
|
24 |
+
if key in self:
|
25 |
+
return self[key]
|
26 |
+
raise AttributeError(f"'AttrDict' object has no attribute '{key}'")
|
27 |
+
|
28 |
|
29 |
class CXRLLAVAConfig(PretrainedConfig):
|
30 |
model_type = "CXR-LLAVA"
|
|
|
51 |
self.tokenizer.cls_token = self.tokenizer.unk_token
|
52 |
self.tokenizer.mask_token = self.tokenizer.unk_token
|
53 |
|
|
|
54 |
vision_cfg = CLIPVisionCfg(**config.clip_vision_cfg)
|
55 |
|
56 |
self.generation_config = GenerationConfig.from_pretrained(config._name_or_path)
|
|
|
674 |
if keyword in outputs:
|
675 |
return True
|
676 |
return False
|
677 |
+
@dataclass
|
678 |
+
class CLIPVisionCfg:
|
679 |
+
layers: Union[Tuple[int, int, int, int], int] = 12
|
680 |
+
width: int = 768
|
681 |
+
head_width: int = 64
|
682 |
+
mlp_ratio: float = 4.0
|
683 |
+
patch_size: int = 16
|
684 |
+
image_size: Union[Tuple[int, int], int] = 224
|
685 |
+
|
686 |
+
ls_init_value: Optional[float] = None # layer scale initial value
|
687 |
+
patch_dropout: float = 0. # what fraction of patches to dropout during training (0 would mean disabled and no patches dropped) - 0.5 to 0.75 recommended in the paper for optimal results
|
688 |
+
attentional_pool: bool = False # whether to use attentional pooler in the last embedding layer (overrides pool_type)
|
689 |
+
attn_pooler_queries: int = 256 # n_queries for attentional pooler
|
690 |
+
attn_pooler_heads: int = 8 # n heads for attentional_pooling
|
691 |
+
no_ln_pre: bool = False # disable pre transformer LayerNorm
|
692 |
+
pos_embed_type: str = 'learnable'
|
693 |
+
final_ln_after_pool: bool = False # apply final LayerNorm after pooling
|
694 |
+
pool_type: str = 'tok'
|
695 |
+
output_tokens: bool = False
|
696 |
+
act_kwargs: Optional[dict] = None
|
697 |
+
norm_kwargs: Optional[dict] = None
|
698 |
+
|
699 |
+
timm_model_name: Optional[str] = None # a valid model name overrides layers, width, patch_size
|
700 |
+
timm_model_pretrained: bool = False # use (imagenet) pretrained weights for named model
|
701 |
+
timm_pool: str = 'avg' # feature pooling for timm model ('abs_attn', 'rot_attn', 'avg', '')
|
702 |
+
timm_proj: str = 'linear' # linear projection for timm model output ('linear', 'mlp', '')
|
703 |
+
timm_proj_bias: bool = False # enable bias final projection
|
704 |
+
timm_drop: float = 0. # head dropout
|
705 |
+
timm_drop_path: Optional[float] = None # backbone stochastic depth
|
config.json
CHANGED
@@ -1,8 +1,9 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
"architectures": [
|
4 |
"CXRLLAVAModel"
|
5 |
],
|
|
|
6 |
"auto_map": {
|
7 |
"AutoConfig": "CXR_LLAVA_HF.CXRLLAVAConfig",
|
8 |
"AutoModel": "CXR_LLAVA_HF.CXRLLAVAModel"
|
@@ -25,7 +26,7 @@
|
|
25 |
"std": 0.3821719215686275
|
26 |
},
|
27 |
"llama": {
|
28 |
-
"_name_or_path": "
|
29 |
"add_cross_attention": false,
|
30 |
"architectures": [
|
31 |
"LlamaForCausalLM"
|
@@ -104,7 +105,7 @@
|
|
104 |
"vocab_size": 32000
|
105 |
},
|
106 |
"llama_model_dtype": "bf16",
|
107 |
-
"llama_model_path": "
|
108 |
"mm_projector_dim": 1024,
|
109 |
"mm_projector_dtype": "fp32",
|
110 |
"mm_projector_path": null,
|
@@ -112,7 +113,7 @@
|
|
112 |
"mm_use_im_start_end": false,
|
113 |
"model_type": "CXR-LLAVA",
|
114 |
"torch_dtype": "bfloat16",
|
115 |
-
"transformers_version": "4.
|
116 |
"tune_mm_mlp_adapter": false,
|
117 |
"use_cache": false
|
118 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "G:\\Temp\\finetune_result\\LLAMA2-7B-CHAT_ViT-L-16-512_MOREKEYWORD_LN_PATCH_FINETUNE_ChexpertJSON_POSTTRAIN_25000_DIST",
|
3 |
"architectures": [
|
4 |
"CXRLLAVAModel"
|
5 |
],
|
6 |
+
"attn_implementation": null,
|
7 |
"auto_map": {
|
8 |
"AutoConfig": "CXR_LLAVA_HF.CXRLLAVAConfig",
|
9 |
"AutoModel": "CXR_LLAVA_HF.CXRLLAVAModel"
|
|
|
26 |
"std": 0.3821719215686275
|
27 |
},
|
28 |
"llama": {
|
29 |
+
"_name_or_path": "/home/jovyan/llava/SW_LLAVA/LLAMA2-7B-CHAT_ViT-L-16-512_MOREKEYWORD_LN_PATCH_FINETUNE_ChexpertJSON_POSTTRAIN",
|
30 |
"add_cross_attention": false,
|
31 |
"architectures": [
|
32 |
"LlamaForCausalLM"
|
|
|
105 |
"vocab_size": 32000
|
106 |
},
|
107 |
"llama_model_dtype": "bf16",
|
108 |
+
"llama_model_path": "/home/jovyan/llava/SW_LLAVA/LLAMA2-7B-CHAT_ViT-L-16-512_MOREKEYWORD_LN_PATCH_FINETUNE_ChexpertJSON_POSTTRAIN",
|
109 |
"mm_projector_dim": 1024,
|
110 |
"mm_projector_dtype": "fp32",
|
111 |
"mm_projector_path": null,
|
|
|
113 |
"mm_use_im_start_end": false,
|
114 |
"model_type": "CXR-LLAVA",
|
115 |
"torch_dtype": "bfloat16",
|
116 |
+
"transformers_version": "4.36.2",
|
117 |
"tune_mm_mlp_adapter": false,
|
118 |
"use_cache": false
|
119 |
}
|
generation_config.json
CHANGED
@@ -1,4 +1,4 @@
|
|
1 |
{
|
2 |
"_from_model_config": true,
|
3 |
-
"transformers_version": "4.
|
4 |
}
|
|
|
1 |
{
|
2 |
"_from_model_config": true,
|
3 |
+
"transformers_version": "4.36.2"
|
4 |
}
|
model-00001-of-00003.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2a30a3337ea0e778627c417863e19621d3df385d2b843ac98c97fd23737f5053
|
3 |
+
size 4917365472
|
model-00002-of-00003.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6f34846c3dcbf1115a4ed3992fbd3325729a3991bae7ff6418fd6161c561a604
|
3 |
+
size 4947390880
|
model-00003-of-00003.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:42a5c74885378cc22d42cd4d2159e648fd5a13821c22a7c7daef33cdf31c53e7
|
3 |
+
size 4228057888
|
model.safetensors.index.json
ADDED
@@ -0,0 +1,596 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"metadata": {
|
3 |
+
"total_size": 14092742656
|
4 |
+
},
|
5 |
+
"weight_map": {
|
6 |
+
"llama.embed_tokens.weight": "model-00001-of-00003.safetensors",
|
7 |
+
"llama.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
8 |
+
"llama.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
9 |
+
"llama.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
10 |
+
"llama.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
11 |
+
"llama.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
12 |
+
"llama.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
13 |
+
"llama.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
14 |
+
"llama.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
15 |
+
"llama.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
16 |
+
"llama.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
17 |
+
"llama.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
18 |
+
"llama.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
19 |
+
"llama.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
20 |
+
"llama.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
21 |
+
"llama.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
22 |
+
"llama.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
23 |
+
"llama.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
24 |
+
"llama.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
25 |
+
"llama.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
26 |
+
"llama.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
27 |
+
"llama.layers.10.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
28 |
+
"llama.layers.10.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
29 |
+
"llama.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
30 |
+
"llama.layers.10.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
31 |
+
"llama.layers.10.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
32 |
+
"llama.layers.10.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
33 |
+
"llama.layers.10.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
34 |
+
"llama.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
35 |
+
"llama.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
36 |
+
"llama.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
37 |
+
"llama.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
38 |
+
"llama.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
39 |
+
"llama.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
40 |
+
"llama.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
41 |
+
"llama.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
42 |
+
"llama.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
43 |
+
"llama.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
44 |
+
"llama.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
45 |
+
"llama.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
46 |
+
"llama.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
47 |
+
"llama.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
48 |
+
"llama.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
49 |
+
"llama.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
50 |
+
"llama.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
51 |
+
"llama.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
52 |
+
"llama.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
53 |
+
"llama.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
54 |
+
"llama.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
55 |
+
"llama.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
56 |
+
"llama.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
57 |
+
"llama.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
58 |
+
"llama.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
59 |
+
"llama.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
60 |
+
"llama.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
61 |
+
"llama.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
62 |
+
"llama.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
63 |
+
"llama.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
64 |
+
"llama.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
65 |
+
"llama.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
66 |
+
"llama.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
67 |
+
"llama.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
68 |
+
"llama.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
69 |
+
"llama.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
70 |
+
"llama.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
71 |
+
"llama.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
72 |
+
"llama.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
73 |
+
"llama.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
74 |
+
"llama.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
75 |
+
"llama.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
76 |
+
"llama.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
77 |
+
"llama.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
78 |
+
"llama.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
79 |
+
"llama.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
80 |
+
"llama.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
81 |
+
"llama.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
82 |
+
"llama.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
83 |
+
"llama.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
84 |
+
"llama.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
85 |
+
"llama.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
86 |
+
"llama.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
87 |
+
"llama.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
88 |
+
"llama.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
89 |
+
"llama.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
90 |
+
"llama.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
91 |
+
"llama.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
92 |
+
"llama.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
93 |
+
"llama.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
94 |
+
"llama.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
95 |
+
"llama.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
96 |
+
"llama.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
97 |
+
"llama.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
98 |
+
"llama.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
99 |
+
"llama.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
100 |
+
"llama.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
101 |
+
"llama.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
102 |
+
"llama.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
103 |
+
"llama.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
104 |
+
"llama.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
105 |
+
"llama.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
106 |
+
"llama.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
107 |
+
"llama.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
108 |
+
"llama.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
109 |
+
"llama.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
110 |
+
"llama.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
111 |
+
"llama.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
112 |
+
"llama.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
113 |
+
"llama.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
114 |
+
"llama.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
115 |
+
"llama.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
116 |
+
"llama.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
117 |
+
"llama.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
118 |
+
"llama.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
119 |
+
"llama.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
120 |
+
"llama.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
121 |
+
"llama.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
122 |
+
"llama.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
123 |
+
"llama.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
124 |
+
"llama.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
125 |
+
"llama.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
126 |
+
"llama.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
127 |
+
"llama.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
128 |
+
"llama.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
129 |
+
"llama.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
130 |
+
"llama.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
131 |
+
"llama.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
132 |
+
"llama.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
133 |
+
"llama.layers.21.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
134 |
+
"llama.layers.21.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
135 |
+
"llama.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
136 |
+
"llama.layers.21.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
137 |
+
"llama.layers.21.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
138 |
+
"llama.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
139 |
+
"llama.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
140 |
+
"llama.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
141 |
+
"llama.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
142 |
+
"llama.layers.22.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
143 |
+
"llama.layers.22.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
144 |
+
"llama.layers.22.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
145 |
+
"llama.layers.22.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
146 |
+
"llama.layers.22.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
147 |
+
"llama.layers.22.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
148 |
+
"llama.layers.22.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
149 |
+
"llama.layers.22.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
150 |
+
"llama.layers.22.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
151 |
+
"llama.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
152 |
+
"llama.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
153 |
+
"llama.layers.23.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
154 |
+
"llama.layers.23.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
155 |
+
"llama.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
156 |
+
"llama.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
157 |
+
"llama.layers.23.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
158 |
+
"llama.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
159 |
+
"llama.layers.23.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
160 |
+
"llama.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
161 |
+
"llama.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
162 |
+
"llama.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
163 |
+
"llama.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
164 |
+
"llama.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
165 |
+
"llama.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
166 |
+
"llama.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
167 |
+
"llama.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
168 |
+
"llama.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
169 |
+
"llama.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
170 |
+
"llama.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
171 |
+
"llama.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
172 |
+
"llama.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
173 |
+
"llama.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
174 |
+
"llama.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
175 |
+
"llama.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
176 |
+
"llama.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
177 |
+
"llama.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
178 |
+
"llama.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
179 |
+
"llama.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
180 |
+
"llama.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
181 |
+
"llama.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
182 |
+
"llama.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
183 |
+
"llama.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
184 |
+
"llama.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
185 |
+
"llama.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
186 |
+
"llama.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
187 |
+
"llama.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
188 |
+
"llama.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
189 |
+
"llama.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
190 |
+
"llama.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
191 |
+
"llama.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
192 |
+
"llama.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
193 |
+
"llama.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
194 |
+
"llama.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
195 |
+
"llama.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
196 |
+
"llama.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
197 |
+
"llama.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
198 |
+
"llama.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
199 |
+
"llama.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
200 |
+
"llama.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
201 |
+
"llama.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
202 |
+
"llama.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
203 |
+
"llama.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
204 |
+
"llama.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
205 |
+
"llama.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
206 |
+
"llama.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
207 |
+
"llama.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
208 |
+
"llama.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
209 |
+
"llama.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
210 |
+
"llama.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
211 |
+
"llama.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
212 |
+
"llama.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
213 |
+
"llama.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
214 |
+
"llama.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
215 |
+
"llama.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
216 |
+
"llama.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
217 |
+
"llama.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
218 |
+
"llama.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
219 |
+
"llama.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
220 |
+
"llama.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
221 |
+
"llama.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
222 |
+
"llama.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
223 |
+
"llama.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
224 |
+
"llama.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
225 |
+
"llama.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
226 |
+
"llama.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
227 |
+
"llama.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
228 |
+
"llama.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
229 |
+
"llama.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
230 |
+
"llama.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
231 |
+
"llama.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
232 |
+
"llama.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
233 |
+
"llama.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
234 |
+
"llama.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
235 |
+
"llama.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
236 |
+
"llama.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
237 |
+
"llama.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
238 |
+
"llama.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
239 |
+
"llama.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
240 |
+
"llama.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
241 |
+
"llama.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
242 |
+
"llama.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
243 |
+
"llama.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
244 |
+
"llama.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
245 |
+
"llama.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
246 |
+
"llama.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
247 |
+
"llama.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
248 |
+
"llama.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
249 |
+
"llama.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
250 |
+
"llama.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
251 |
+
"llama.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
252 |
+
"llama.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
253 |
+
"llama.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
254 |
+
"llama.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
255 |
+
"llama.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
256 |
+
"llama.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
257 |
+
"llama.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
258 |
+
"llama.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
259 |
+
"llama.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
260 |
+
"llama.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
261 |
+
"llama.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
262 |
+
"llama.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
263 |
+
"llama.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
264 |
+
"llama.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
265 |
+
"llama.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
266 |
+
"llama.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
267 |
+
"llama.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
268 |
+
"llama.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
269 |
+
"llama.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
270 |
+
"llama.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
271 |
+
"llama.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
272 |
+
"llama.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
273 |
+
"llama.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
274 |
+
"llama.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
275 |
+
"llama.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
276 |
+
"llama.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
277 |
+
"llama.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
278 |
+
"llama.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
279 |
+
"llama.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
280 |
+
"llama.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
281 |
+
"llama.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
282 |
+
"llama.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
283 |
+
"llama.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
284 |
+
"llama.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
285 |
+
"llama.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
286 |
+
"llama.layers.9.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
287 |
+
"llama.layers.9.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
288 |
+
"llama.layers.9.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
289 |
+
"llama.layers.9.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
290 |
+
"llama.layers.9.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
291 |
+
"llama.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
292 |
+
"llama.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
293 |
+
"llama.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
294 |
+
"llama.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
295 |
+
"llama.norm.weight": "model-00003-of-00003.safetensors",
|
296 |
+
"lm_head.weight": "model-00001-of-00003.safetensors",
|
297 |
+
"mm_projector.bias": "model-00001-of-00003.safetensors",
|
298 |
+
"mm_projector.weight": "model-00001-of-00003.safetensors",
|
299 |
+
"vision_tower.class_embedding": "model-00001-of-00003.safetensors",
|
300 |
+
"vision_tower.conv1.weight": "model-00001-of-00003.safetensors",
|
301 |
+
"vision_tower.ln_post.bias": "model-00001-of-00003.safetensors",
|
302 |
+
"vision_tower.ln_post.weight": "model-00001-of-00003.safetensors",
|
303 |
+
"vision_tower.ln_pre.bias": "model-00001-of-00003.safetensors",
|
304 |
+
"vision_tower.ln_pre.weight": "model-00001-of-00003.safetensors",
|
305 |
+
"vision_tower.positional_embedding": "model-00001-of-00003.safetensors",
|
306 |
+
"vision_tower.proj": "model-00001-of-00003.safetensors",
|
307 |
+
"vision_tower.transformer.resblocks.0.attn.in_proj_bias": "model-00001-of-00003.safetensors",
|
308 |
+
"vision_tower.transformer.resblocks.0.attn.in_proj_weight": "model-00001-of-00003.safetensors",
|
309 |
+
"vision_tower.transformer.resblocks.0.attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
310 |
+
"vision_tower.transformer.resblocks.0.attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
311 |
+
"vision_tower.transformer.resblocks.0.ln_1.bias": "model-00001-of-00003.safetensors",
|
312 |
+
"vision_tower.transformer.resblocks.0.ln_1.weight": "model-00001-of-00003.safetensors",
|
313 |
+
"vision_tower.transformer.resblocks.0.ln_2.bias": "model-00001-of-00003.safetensors",
|
314 |
+
"vision_tower.transformer.resblocks.0.ln_2.weight": "model-00001-of-00003.safetensors",
|
315 |
+
"vision_tower.transformer.resblocks.0.mlp.c_fc.bias": "model-00001-of-00003.safetensors",
|
316 |
+
"vision_tower.transformer.resblocks.0.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
|
317 |
+
"vision_tower.transformer.resblocks.0.mlp.c_proj.bias": "model-00001-of-00003.safetensors",
|
318 |
+
"vision_tower.transformer.resblocks.0.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
|
319 |
+
"vision_tower.transformer.resblocks.1.attn.in_proj_bias": "model-00001-of-00003.safetensors",
|
320 |
+
"vision_tower.transformer.resblocks.1.attn.in_proj_weight": "model-00001-of-00003.safetensors",
|
321 |
+
"vision_tower.transformer.resblocks.1.attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
322 |
+
"vision_tower.transformer.resblocks.1.attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
323 |
+
"vision_tower.transformer.resblocks.1.ln_1.bias": "model-00001-of-00003.safetensors",
|
324 |
+
"vision_tower.transformer.resblocks.1.ln_1.weight": "model-00001-of-00003.safetensors",
|
325 |
+
"vision_tower.transformer.resblocks.1.ln_2.bias": "model-00001-of-00003.safetensors",
|
326 |
+
"vision_tower.transformer.resblocks.1.ln_2.weight": "model-00001-of-00003.safetensors",
|
327 |
+
"vision_tower.transformer.resblocks.1.mlp.c_fc.bias": "model-00001-of-00003.safetensors",
|
328 |
+
"vision_tower.transformer.resblocks.1.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
|
329 |
+
"vision_tower.transformer.resblocks.1.mlp.c_proj.bias": "model-00001-of-00003.safetensors",
|
330 |
+
"vision_tower.transformer.resblocks.1.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
|
331 |
+
"vision_tower.transformer.resblocks.10.attn.in_proj_bias": "model-00001-of-00003.safetensors",
|
332 |
+
"vision_tower.transformer.resblocks.10.attn.in_proj_weight": "model-00001-of-00003.safetensors",
|
333 |
+
"vision_tower.transformer.resblocks.10.attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
334 |
+
"vision_tower.transformer.resblocks.10.attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
335 |
+
"vision_tower.transformer.resblocks.10.ln_1.bias": "model-00001-of-00003.safetensors",
|
336 |
+
"vision_tower.transformer.resblocks.10.ln_1.weight": "model-00001-of-00003.safetensors",
|
337 |
+
"vision_tower.transformer.resblocks.10.ln_2.bias": "model-00001-of-00003.safetensors",
|
338 |
+
"vision_tower.transformer.resblocks.10.ln_2.weight": "model-00001-of-00003.safetensors",
|
339 |
+
"vision_tower.transformer.resblocks.10.mlp.c_fc.bias": "model-00001-of-00003.safetensors",
|
340 |
+
"vision_tower.transformer.resblocks.10.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
|
341 |
+
"vision_tower.transformer.resblocks.10.mlp.c_proj.bias": "model-00001-of-00003.safetensors",
|
342 |
+
"vision_tower.transformer.resblocks.10.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
|
343 |
+
"vision_tower.transformer.resblocks.11.attn.in_proj_bias": "model-00001-of-00003.safetensors",
|
344 |
+
"vision_tower.transformer.resblocks.11.attn.in_proj_weight": "model-00001-of-00003.safetensors",
|
345 |
+
"vision_tower.transformer.resblocks.11.attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
346 |
+
"vision_tower.transformer.resblocks.11.attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
347 |
+
"vision_tower.transformer.resblocks.11.ln_1.bias": "model-00001-of-00003.safetensors",
|
348 |
+
"vision_tower.transformer.resblocks.11.ln_1.weight": "model-00001-of-00003.safetensors",
|
349 |
+
"vision_tower.transformer.resblocks.11.ln_2.bias": "model-00001-of-00003.safetensors",
|
350 |
+
"vision_tower.transformer.resblocks.11.ln_2.weight": "model-00001-of-00003.safetensors",
|
351 |
+
"vision_tower.transformer.resblocks.11.mlp.c_fc.bias": "model-00001-of-00003.safetensors",
|
352 |
+
"vision_tower.transformer.resblocks.11.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
|
353 |
+
"vision_tower.transformer.resblocks.11.mlp.c_proj.bias": "model-00001-of-00003.safetensors",
|
354 |
+
"vision_tower.transformer.resblocks.11.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
|
355 |
+
"vision_tower.transformer.resblocks.12.attn.in_proj_bias": "model-00001-of-00003.safetensors",
|
356 |
+
"vision_tower.transformer.resblocks.12.attn.in_proj_weight": "model-00001-of-00003.safetensors",
|
357 |
+
"vision_tower.transformer.resblocks.12.attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
358 |
+
"vision_tower.transformer.resblocks.12.attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
359 |
+
"vision_tower.transformer.resblocks.12.ln_1.bias": "model-00001-of-00003.safetensors",
|
360 |
+
"vision_tower.transformer.resblocks.12.ln_1.weight": "model-00001-of-00003.safetensors",
|
361 |
+
"vision_tower.transformer.resblocks.12.ln_2.bias": "model-00001-of-00003.safetensors",
|
362 |
+
"vision_tower.transformer.resblocks.12.ln_2.weight": "model-00001-of-00003.safetensors",
|
363 |
+
"vision_tower.transformer.resblocks.12.mlp.c_fc.bias": "model-00001-of-00003.safetensors",
|
364 |
+
"vision_tower.transformer.resblocks.12.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
|
365 |
+
"vision_tower.transformer.resblocks.12.mlp.c_proj.bias": "model-00001-of-00003.safetensors",
|
366 |
+
"vision_tower.transformer.resblocks.12.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
|
367 |
+
"vision_tower.transformer.resblocks.13.attn.in_proj_bias": "model-00001-of-00003.safetensors",
|
368 |
+
"vision_tower.transformer.resblocks.13.attn.in_proj_weight": "model-00001-of-00003.safetensors",
|
369 |
+
"vision_tower.transformer.resblocks.13.attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
370 |
+
"vision_tower.transformer.resblocks.13.attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
371 |
+
"vision_tower.transformer.resblocks.13.ln_1.bias": "model-00001-of-00003.safetensors",
|
372 |
+
"vision_tower.transformer.resblocks.13.ln_1.weight": "model-00001-of-00003.safetensors",
|
373 |
+
"vision_tower.transformer.resblocks.13.ln_2.bias": "model-00001-of-00003.safetensors",
|
374 |
+
"vision_tower.transformer.resblocks.13.ln_2.weight": "model-00001-of-00003.safetensors",
|
375 |
+
"vision_tower.transformer.resblocks.13.mlp.c_fc.bias": "model-00001-of-00003.safetensors",
|
376 |
+
"vision_tower.transformer.resblocks.13.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
|
377 |
+
"vision_tower.transformer.resblocks.13.mlp.c_proj.bias": "model-00001-of-00003.safetensors",
|
378 |
+
"vision_tower.transformer.resblocks.13.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
|
379 |
+
"vision_tower.transformer.resblocks.14.attn.in_proj_bias": "model-00001-of-00003.safetensors",
|
380 |
+
"vision_tower.transformer.resblocks.14.attn.in_proj_weight": "model-00001-of-00003.safetensors",
|
381 |
+
"vision_tower.transformer.resblocks.14.attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
382 |
+
"vision_tower.transformer.resblocks.14.attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
383 |
+
"vision_tower.transformer.resblocks.14.ln_1.bias": "model-00001-of-00003.safetensors",
|
384 |
+
"vision_tower.transformer.resblocks.14.ln_1.weight": "model-00001-of-00003.safetensors",
|
385 |
+
"vision_tower.transformer.resblocks.14.ln_2.bias": "model-00001-of-00003.safetensors",
|
386 |
+
"vision_tower.transformer.resblocks.14.ln_2.weight": "model-00001-of-00003.safetensors",
|
387 |
+
"vision_tower.transformer.resblocks.14.mlp.c_fc.bias": "model-00001-of-00003.safetensors",
|
388 |
+
"vision_tower.transformer.resblocks.14.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
|
389 |
+
"vision_tower.transformer.resblocks.14.mlp.c_proj.bias": "model-00001-of-00003.safetensors",
|
390 |
+
"vision_tower.transformer.resblocks.14.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
|
391 |
+
"vision_tower.transformer.resblocks.15.attn.in_proj_bias": "model-00001-of-00003.safetensors",
|
392 |
+
"vision_tower.transformer.resblocks.15.attn.in_proj_weight": "model-00001-of-00003.safetensors",
|
393 |
+
"vision_tower.transformer.resblocks.15.attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
394 |
+
"vision_tower.transformer.resblocks.15.attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
395 |
+
"vision_tower.transformer.resblocks.15.ln_1.bias": "model-00001-of-00003.safetensors",
|
396 |
+
"vision_tower.transformer.resblocks.15.ln_1.weight": "model-00001-of-00003.safetensors",
|
397 |
+
"vision_tower.transformer.resblocks.15.ln_2.bias": "model-00001-of-00003.safetensors",
|
398 |
+
"vision_tower.transformer.resblocks.15.ln_2.weight": "model-00001-of-00003.safetensors",
|
399 |
+
"vision_tower.transformer.resblocks.15.mlp.c_fc.bias": "model-00001-of-00003.safetensors",
|
400 |
+
"vision_tower.transformer.resblocks.15.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
|
401 |
+
"vision_tower.transformer.resblocks.15.mlp.c_proj.bias": "model-00001-of-00003.safetensors",
|
402 |
+
"vision_tower.transformer.resblocks.15.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
|
403 |
+
"vision_tower.transformer.resblocks.16.attn.in_proj_bias": "model-00001-of-00003.safetensors",
|
404 |
+
"vision_tower.transformer.resblocks.16.attn.in_proj_weight": "model-00001-of-00003.safetensors",
|
405 |
+
"vision_tower.transformer.resblocks.16.attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
406 |
+
"vision_tower.transformer.resblocks.16.attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
407 |
+
"vision_tower.transformer.resblocks.16.ln_1.bias": "model-00001-of-00003.safetensors",
|
408 |
+
"vision_tower.transformer.resblocks.16.ln_1.weight": "model-00001-of-00003.safetensors",
|
409 |
+
"vision_tower.transformer.resblocks.16.ln_2.bias": "model-00001-of-00003.safetensors",
|
410 |
+
"vision_tower.transformer.resblocks.16.ln_2.weight": "model-00001-of-00003.safetensors",
|
411 |
+
"vision_tower.transformer.resblocks.16.mlp.c_fc.bias": "model-00001-of-00003.safetensors",
|
412 |
+
"vision_tower.transformer.resblocks.16.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
|
413 |
+
"vision_tower.transformer.resblocks.16.mlp.c_proj.bias": "model-00001-of-00003.safetensors",
|
414 |
+
"vision_tower.transformer.resblocks.16.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
|
415 |
+
"vision_tower.transformer.resblocks.17.attn.in_proj_bias": "model-00001-of-00003.safetensors",
|
416 |
+
"vision_tower.transformer.resblocks.17.attn.in_proj_weight": "model-00001-of-00003.safetensors",
|
417 |
+
"vision_tower.transformer.resblocks.17.attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
418 |
+
"vision_tower.transformer.resblocks.17.attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
419 |
+
"vision_tower.transformer.resblocks.17.ln_1.bias": "model-00001-of-00003.safetensors",
|
420 |
+
"vision_tower.transformer.resblocks.17.ln_1.weight": "model-00001-of-00003.safetensors",
|
421 |
+
"vision_tower.transformer.resblocks.17.ln_2.bias": "model-00001-of-00003.safetensors",
|
422 |
+
"vision_tower.transformer.resblocks.17.ln_2.weight": "model-00001-of-00003.safetensors",
|
423 |
+
"vision_tower.transformer.resblocks.17.mlp.c_fc.bias": "model-00001-of-00003.safetensors",
|
424 |
+
"vision_tower.transformer.resblocks.17.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
|
425 |
+
"vision_tower.transformer.resblocks.17.mlp.c_proj.bias": "model-00001-of-00003.safetensors",
|
426 |
+
"vision_tower.transformer.resblocks.17.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
|
427 |
+
"vision_tower.transformer.resblocks.18.attn.in_proj_bias": "model-00001-of-00003.safetensors",
|
428 |
+
"vision_tower.transformer.resblocks.18.attn.in_proj_weight": "model-00001-of-00003.safetensors",
|
429 |
+
"vision_tower.transformer.resblocks.18.attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
430 |
+
"vision_tower.transformer.resblocks.18.attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
431 |
+
"vision_tower.transformer.resblocks.18.ln_1.bias": "model-00001-of-00003.safetensors",
|
432 |
+
"vision_tower.transformer.resblocks.18.ln_1.weight": "model-00001-of-00003.safetensors",
|
433 |
+
"vision_tower.transformer.resblocks.18.ln_2.bias": "model-00001-of-00003.safetensors",
|
434 |
+
"vision_tower.transformer.resblocks.18.ln_2.weight": "model-00001-of-00003.safetensors",
|
435 |
+
"vision_tower.transformer.resblocks.18.mlp.c_fc.bias": "model-00001-of-00003.safetensors",
|
436 |
+
"vision_tower.transformer.resblocks.18.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
|
437 |
+
"vision_tower.transformer.resblocks.18.mlp.c_proj.bias": "model-00001-of-00003.safetensors",
|
438 |
+
"vision_tower.transformer.resblocks.18.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
|
439 |
+
"vision_tower.transformer.resblocks.19.attn.in_proj_bias": "model-00001-of-00003.safetensors",
|
440 |
+
"vision_tower.transformer.resblocks.19.attn.in_proj_weight": "model-00001-of-00003.safetensors",
|
441 |
+
"vision_tower.transformer.resblocks.19.attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
442 |
+
"vision_tower.transformer.resblocks.19.attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
443 |
+
"vision_tower.transformer.resblocks.19.ln_1.bias": "model-00001-of-00003.safetensors",
|
444 |
+
"vision_tower.transformer.resblocks.19.ln_1.weight": "model-00001-of-00003.safetensors",
|
445 |
+
"vision_tower.transformer.resblocks.19.ln_2.bias": "model-00001-of-00003.safetensors",
|
446 |
+
"vision_tower.transformer.resblocks.19.ln_2.weight": "model-00001-of-00003.safetensors",
|
447 |
+
"vision_tower.transformer.resblocks.19.mlp.c_fc.bias": "model-00001-of-00003.safetensors",
|
448 |
+
"vision_tower.transformer.resblocks.19.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
|
449 |
+
"vision_tower.transformer.resblocks.19.mlp.c_proj.bias": "model-00001-of-00003.safetensors",
|
450 |
+
"vision_tower.transformer.resblocks.19.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
|
451 |
+
"vision_tower.transformer.resblocks.2.attn.in_proj_bias": "model-00001-of-00003.safetensors",
|
452 |
+
"vision_tower.transformer.resblocks.2.attn.in_proj_weight": "model-00001-of-00003.safetensors",
|
453 |
+
"vision_tower.transformer.resblocks.2.attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
454 |
+
"vision_tower.transformer.resblocks.2.attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
455 |
+
"vision_tower.transformer.resblocks.2.ln_1.bias": "model-00001-of-00003.safetensors",
|
456 |
+
"vision_tower.transformer.resblocks.2.ln_1.weight": "model-00001-of-00003.safetensors",
|
457 |
+
"vision_tower.transformer.resblocks.2.ln_2.bias": "model-00001-of-00003.safetensors",
|
458 |
+
"vision_tower.transformer.resblocks.2.ln_2.weight": "model-00001-of-00003.safetensors",
|
459 |
+
"vision_tower.transformer.resblocks.2.mlp.c_fc.bias": "model-00001-of-00003.safetensors",
|
460 |
+
"vision_tower.transformer.resblocks.2.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
|
461 |
+
"vision_tower.transformer.resblocks.2.mlp.c_proj.bias": "model-00001-of-00003.safetensors",
|
462 |
+
"vision_tower.transformer.resblocks.2.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
|
463 |
+
"vision_tower.transformer.resblocks.20.attn.in_proj_bias": "model-00001-of-00003.safetensors",
|
464 |
+
"vision_tower.transformer.resblocks.20.attn.in_proj_weight": "model-00001-of-00003.safetensors",
|
465 |
+
"vision_tower.transformer.resblocks.20.attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
466 |
+
"vision_tower.transformer.resblocks.20.attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
467 |
+
"vision_tower.transformer.resblocks.20.ln_1.bias": "model-00001-of-00003.safetensors",
|
468 |
+
"vision_tower.transformer.resblocks.20.ln_1.weight": "model-00001-of-00003.safetensors",
|
469 |
+
"vision_tower.transformer.resblocks.20.ln_2.bias": "model-00001-of-00003.safetensors",
|
470 |
+
"vision_tower.transformer.resblocks.20.ln_2.weight": "model-00001-of-00003.safetensors",
|
471 |
+
"vision_tower.transformer.resblocks.20.mlp.c_fc.bias": "model-00001-of-00003.safetensors",
|
472 |
+
"vision_tower.transformer.resblocks.20.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
|
473 |
+
"vision_tower.transformer.resblocks.20.mlp.c_proj.bias": "model-00001-of-00003.safetensors",
|
474 |
+
"vision_tower.transformer.resblocks.20.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
|
475 |
+
"vision_tower.transformer.resblocks.21.attn.in_proj_bias": "model-00001-of-00003.safetensors",
|
476 |
+
"vision_tower.transformer.resblocks.21.attn.in_proj_weight": "model-00001-of-00003.safetensors",
|
477 |
+
"vision_tower.transformer.resblocks.21.attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
478 |
+
"vision_tower.transformer.resblocks.21.attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
479 |
+
"vision_tower.transformer.resblocks.21.ln_1.bias": "model-00001-of-00003.safetensors",
|
480 |
+
"vision_tower.transformer.resblocks.21.ln_1.weight": "model-00001-of-00003.safetensors",
|
481 |
+
"vision_tower.transformer.resblocks.21.ln_2.bias": "model-00001-of-00003.safetensors",
|
482 |
+
"vision_tower.transformer.resblocks.21.ln_2.weight": "model-00001-of-00003.safetensors",
|
483 |
+
"vision_tower.transformer.resblocks.21.mlp.c_fc.bias": "model-00001-of-00003.safetensors",
|
484 |
+
"vision_tower.transformer.resblocks.21.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
|
485 |
+
"vision_tower.transformer.resblocks.21.mlp.c_proj.bias": "model-00001-of-00003.safetensors",
|
486 |
+
"vision_tower.transformer.resblocks.21.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
|
487 |
+
"vision_tower.transformer.resblocks.22.attn.in_proj_bias": "model-00001-of-00003.safetensors",
|
488 |
+
"vision_tower.transformer.resblocks.22.attn.in_proj_weight": "model-00001-of-00003.safetensors",
|
489 |
+
"vision_tower.transformer.resblocks.22.attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
490 |
+
"vision_tower.transformer.resblocks.22.attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
491 |
+
"vision_tower.transformer.resblocks.22.ln_1.bias": "model-00001-of-00003.safetensors",
|
492 |
+
"vision_tower.transformer.resblocks.22.ln_1.weight": "model-00001-of-00003.safetensors",
|
493 |
+
"vision_tower.transformer.resblocks.22.ln_2.bias": "model-00001-of-00003.safetensors",
|
494 |
+
"vision_tower.transformer.resblocks.22.ln_2.weight": "model-00001-of-00003.safetensors",
|
495 |
+
"vision_tower.transformer.resblocks.22.mlp.c_fc.bias": "model-00001-of-00003.safetensors",
|
496 |
+
"vision_tower.transformer.resblocks.22.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
|
497 |
+
"vision_tower.transformer.resblocks.22.mlp.c_proj.bias": "model-00001-of-00003.safetensors",
|
498 |
+
"vision_tower.transformer.resblocks.22.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
|
499 |
+
"vision_tower.transformer.resblocks.23.attn.in_proj_bias": "model-00001-of-00003.safetensors",
|
500 |
+
"vision_tower.transformer.resblocks.23.attn.in_proj_weight": "model-00001-of-00003.safetensors",
|
501 |
+
"vision_tower.transformer.resblocks.23.attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
502 |
+
"vision_tower.transformer.resblocks.23.attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
503 |
+
"vision_tower.transformer.resblocks.23.ln_1.bias": "model-00001-of-00003.safetensors",
|
504 |
+
"vision_tower.transformer.resblocks.23.ln_1.weight": "model-00001-of-00003.safetensors",
|
505 |
+
"vision_tower.transformer.resblocks.23.ln_2.bias": "model-00001-of-00003.safetensors",
|
506 |
+
"vision_tower.transformer.resblocks.23.ln_2.weight": "model-00001-of-00003.safetensors",
|
507 |
+
"vision_tower.transformer.resblocks.23.mlp.c_fc.bias": "model-00001-of-00003.safetensors",
|
508 |
+
"vision_tower.transformer.resblocks.23.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
|
509 |
+
"vision_tower.transformer.resblocks.23.mlp.c_proj.bias": "model-00001-of-00003.safetensors",
|
510 |
+
"vision_tower.transformer.resblocks.23.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
|
511 |
+
"vision_tower.transformer.resblocks.3.attn.in_proj_bias": "model-00001-of-00003.safetensors",
|
512 |
+
"vision_tower.transformer.resblocks.3.attn.in_proj_weight": "model-00001-of-00003.safetensors",
|
513 |
+
"vision_tower.transformer.resblocks.3.attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
514 |
+
"vision_tower.transformer.resblocks.3.attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
515 |
+
"vision_tower.transformer.resblocks.3.ln_1.bias": "model-00001-of-00003.safetensors",
|
516 |
+
"vision_tower.transformer.resblocks.3.ln_1.weight": "model-00001-of-00003.safetensors",
|
517 |
+
"vision_tower.transformer.resblocks.3.ln_2.bias": "model-00001-of-00003.safetensors",
|
518 |
+
"vision_tower.transformer.resblocks.3.ln_2.weight": "model-00001-of-00003.safetensors",
|
519 |
+
"vision_tower.transformer.resblocks.3.mlp.c_fc.bias": "model-00001-of-00003.safetensors",
|
520 |
+
"vision_tower.transformer.resblocks.3.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
|
521 |
+
"vision_tower.transformer.resblocks.3.mlp.c_proj.bias": "model-00001-of-00003.safetensors",
|
522 |
+
"vision_tower.transformer.resblocks.3.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
|
523 |
+
"vision_tower.transformer.resblocks.4.attn.in_proj_bias": "model-00001-of-00003.safetensors",
|
524 |
+
"vision_tower.transformer.resblocks.4.attn.in_proj_weight": "model-00001-of-00003.safetensors",
|
525 |
+
"vision_tower.transformer.resblocks.4.attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
526 |
+
"vision_tower.transformer.resblocks.4.attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
527 |
+
"vision_tower.transformer.resblocks.4.ln_1.bias": "model-00001-of-00003.safetensors",
|
528 |
+
"vision_tower.transformer.resblocks.4.ln_1.weight": "model-00001-of-00003.safetensors",
|
529 |
+
"vision_tower.transformer.resblocks.4.ln_2.bias": "model-00001-of-00003.safetensors",
|
530 |
+
"vision_tower.transformer.resblocks.4.ln_2.weight": "model-00001-of-00003.safetensors",
|
531 |
+
"vision_tower.transformer.resblocks.4.mlp.c_fc.bias": "model-00001-of-00003.safetensors",
|
532 |
+
"vision_tower.transformer.resblocks.4.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
|
533 |
+
"vision_tower.transformer.resblocks.4.mlp.c_proj.bias": "model-00001-of-00003.safetensors",
|
534 |
+
"vision_tower.transformer.resblocks.4.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
|
535 |
+
"vision_tower.transformer.resblocks.5.attn.in_proj_bias": "model-00001-of-00003.safetensors",
|
536 |
+
"vision_tower.transformer.resblocks.5.attn.in_proj_weight": "model-00001-of-00003.safetensors",
|
537 |
+
"vision_tower.transformer.resblocks.5.attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
538 |
+
"vision_tower.transformer.resblocks.5.attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
539 |
+
"vision_tower.transformer.resblocks.5.ln_1.bias": "model-00001-of-00003.safetensors",
|
540 |
+
"vision_tower.transformer.resblocks.5.ln_1.weight": "model-00001-of-00003.safetensors",
|
541 |
+
"vision_tower.transformer.resblocks.5.ln_2.bias": "model-00001-of-00003.safetensors",
|
542 |
+
"vision_tower.transformer.resblocks.5.ln_2.weight": "model-00001-of-00003.safetensors",
|
543 |
+
"vision_tower.transformer.resblocks.5.mlp.c_fc.bias": "model-00001-of-00003.safetensors",
|
544 |
+
"vision_tower.transformer.resblocks.5.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
|
545 |
+
"vision_tower.transformer.resblocks.5.mlp.c_proj.bias": "model-00001-of-00003.safetensors",
|
546 |
+
"vision_tower.transformer.resblocks.5.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
|
547 |
+
"vision_tower.transformer.resblocks.6.attn.in_proj_bias": "model-00001-of-00003.safetensors",
|
548 |
+
"vision_tower.transformer.resblocks.6.attn.in_proj_weight": "model-00001-of-00003.safetensors",
|
549 |
+
"vision_tower.transformer.resblocks.6.attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
550 |
+
"vision_tower.transformer.resblocks.6.attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
551 |
+
"vision_tower.transformer.resblocks.6.ln_1.bias": "model-00001-of-00003.safetensors",
|
552 |
+
"vision_tower.transformer.resblocks.6.ln_1.weight": "model-00001-of-00003.safetensors",
|
553 |
+
"vision_tower.transformer.resblocks.6.ln_2.bias": "model-00001-of-00003.safetensors",
|
554 |
+
"vision_tower.transformer.resblocks.6.ln_2.weight": "model-00001-of-00003.safetensors",
|
555 |
+
"vision_tower.transformer.resblocks.6.mlp.c_fc.bias": "model-00001-of-00003.safetensors",
|
556 |
+
"vision_tower.transformer.resblocks.6.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
|
557 |
+
"vision_tower.transformer.resblocks.6.mlp.c_proj.bias": "model-00001-of-00003.safetensors",
|
558 |
+
"vision_tower.transformer.resblocks.6.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
|
559 |
+
"vision_tower.transformer.resblocks.7.attn.in_proj_bias": "model-00001-of-00003.safetensors",
|
560 |
+
"vision_tower.transformer.resblocks.7.attn.in_proj_weight": "model-00001-of-00003.safetensors",
|
561 |
+
"vision_tower.transformer.resblocks.7.attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
562 |
+
"vision_tower.transformer.resblocks.7.attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
563 |
+
"vision_tower.transformer.resblocks.7.ln_1.bias": "model-00001-of-00003.safetensors",
|
564 |
+
"vision_tower.transformer.resblocks.7.ln_1.weight": "model-00001-of-00003.safetensors",
|
565 |
+
"vision_tower.transformer.resblocks.7.ln_2.bias": "model-00001-of-00003.safetensors",
|
566 |
+
"vision_tower.transformer.resblocks.7.ln_2.weight": "model-00001-of-00003.safetensors",
|
567 |
+
"vision_tower.transformer.resblocks.7.mlp.c_fc.bias": "model-00001-of-00003.safetensors",
|
568 |
+
"vision_tower.transformer.resblocks.7.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
|
569 |
+
"vision_tower.transformer.resblocks.7.mlp.c_proj.bias": "model-00001-of-00003.safetensors",
|
570 |
+
"vision_tower.transformer.resblocks.7.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
|
571 |
+
"vision_tower.transformer.resblocks.8.attn.in_proj_bias": "model-00001-of-00003.safetensors",
|
572 |
+
"vision_tower.transformer.resblocks.8.attn.in_proj_weight": "model-00001-of-00003.safetensors",
|
573 |
+
"vision_tower.transformer.resblocks.8.attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
574 |
+
"vision_tower.transformer.resblocks.8.attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
575 |
+
"vision_tower.transformer.resblocks.8.ln_1.bias": "model-00001-of-00003.safetensors",
|
576 |
+
"vision_tower.transformer.resblocks.8.ln_1.weight": "model-00001-of-00003.safetensors",
|
577 |
+
"vision_tower.transformer.resblocks.8.ln_2.bias": "model-00001-of-00003.safetensors",
|
578 |
+
"vision_tower.transformer.resblocks.8.ln_2.weight": "model-00001-of-00003.safetensors",
|
579 |
+
"vision_tower.transformer.resblocks.8.mlp.c_fc.bias": "model-00001-of-00003.safetensors",
|
580 |
+
"vision_tower.transformer.resblocks.8.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
|
581 |
+
"vision_tower.transformer.resblocks.8.mlp.c_proj.bias": "model-00001-of-00003.safetensors",
|
582 |
+
"vision_tower.transformer.resblocks.8.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
|
583 |
+
"vision_tower.transformer.resblocks.9.attn.in_proj_bias": "model-00001-of-00003.safetensors",
|
584 |
+
"vision_tower.transformer.resblocks.9.attn.in_proj_weight": "model-00001-of-00003.safetensors",
|
585 |
+
"vision_tower.transformer.resblocks.9.attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
586 |
+
"vision_tower.transformer.resblocks.9.attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
587 |
+
"vision_tower.transformer.resblocks.9.ln_1.bias": "model-00001-of-00003.safetensors",
|
588 |
+
"vision_tower.transformer.resblocks.9.ln_1.weight": "model-00001-of-00003.safetensors",
|
589 |
+
"vision_tower.transformer.resblocks.9.ln_2.bias": "model-00001-of-00003.safetensors",
|
590 |
+
"vision_tower.transformer.resblocks.9.ln_2.weight": "model-00001-of-00003.safetensors",
|
591 |
+
"vision_tower.transformer.resblocks.9.mlp.c_fc.bias": "model-00001-of-00003.safetensors",
|
592 |
+
"vision_tower.transformer.resblocks.9.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
|
593 |
+
"vision_tower.transformer.resblocks.9.mlp.c_proj.bias": "model-00001-of-00003.safetensors",
|
594 |
+
"vision_tower.transformer.resblocks.9.mlp.c_proj.weight": "model-00001-of-00003.safetensors"
|
595 |
+
}
|
596 |
+
}
|