初始化项目，由ModelHub XC社区提供模型
Model: gagan3012/llava_ar_pretrain_cc3_595k Source: Original Platform
This commit is contained in:
ModelHub XC
39
.gitattributes
vendored
Normal file
39
.gitattributes
vendored
Normal file
@@ -0,0 +1,39 @@
|
||||
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
||||
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||
*.ftz filter=lfs diff=lfs merge=lfs -text
|
||||
*.gz filter=lfs diff=lfs merge=lfs -text
|
||||
*.h5 filter=lfs diff=lfs merge=lfs -text
|
||||
*.joblib filter=lfs diff=lfs merge=lfs -text
|
||||
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||
*.model filter=lfs diff=lfs merge=lfs -text
|
||||
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
||||
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||
*.onnx filter=lfs diff=lfs merge=lfs -text
|
||||
*.ot filter=lfs diff=lfs merge=lfs -text
|
||||
*.parquet filter=lfs diff=lfs merge=lfs -text
|
||||
*.pb filter=lfs diff=lfs merge=lfs -text
|
||||
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||
*.tflite filter=lfs diff=lfs merge=lfs -text
|
||||
*.tgz filter=lfs diff=lfs merge=lfs -text
|
||||
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
ggml-model-f16.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
llava.clip filter=lfs diff=lfs merge=lfs -text
|
||||
llava.projector filter=lfs diff=lfs merge=lfs -text
|
||||
mmproj-model-f16.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
43
config.json
Normal file
43
config.json
Normal file
@@ -0,0 +1,43 @@
|
||||
{
|
||||
"_name_or_path": "/home/fakhr/scratch/models/AceGPT-7B-chat",
|
||||
"architectures": [
|
||||
"LlavaLlamaForCausalLM"
|
||||
],
|
||||
"bos_token_id": 1,
|
||||
"dropout": 0.0,
|
||||
"end_token_id": 2,
|
||||
"eos_token_id": 2,
|
||||
"freeze_mm_mlp_adapter": false,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 4096,
|
||||
"image_aspect_ratio": "pad",
|
||||
"image_grid_pinpoints": null,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 11008,
|
||||
"max_length": 4096,
|
||||
"max_position_embeddings": 2048,
|
||||
"mm_hidden_size": 1024,
|
||||
"mm_projector_lr": 2e-05,
|
||||
"mm_projector_type": "mlp2x_gelu",
|
||||
"mm_use_im_patch_token": false,
|
||||
"mm_use_im_start_end": false,
|
||||
"mm_vision_select_feature": "patch",
|
||||
"mm_vision_select_layer": -2,
|
||||
"mm_vision_tower": "/home/fakhr/scratch/models/clip-vit-large-patch14-336",
|
||||
"model_type": "llava",
|
||||
"num_attention_heads": 32,
|
||||
"num_hidden_layers": 32,
|
||||
"num_key_value_heads": 32,
|
||||
"pad_token_id": 2,
|
||||
"pretraining_tp": 1,
|
||||
"rms_norm_eps": 1e-05,
|
||||
"rope_scaling": null,
|
||||
"rope_theta": 10000.0,
|
||||
"tie_word_embeddings": false,
|
||||
"torch_dtype": "float16",
|
||||
"transformers_version": "4.31.0",
|
||||
"tune_mm_mlp_adapter": false,
|
||||
"use_cache": true,
|
||||
"use_mm_proj": true,
|
||||
"vocab_size": 32000
|
||||
}
|
||||
8
generation_config.json
Normal file
8
generation_config.json
Normal file
@@ -0,0 +1,8 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 1,
|
||||
"eos_token_id": 2,
|
||||
"max_length": 4096,
|
||||
"pad_token_id": 2,
|
||||
"transformers_version": "4.31.0"
|
||||
}
|
||||
3
ggml-model-f16.gguf
Normal file
3
ggml-model-f16.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:a118794337345653a4d5cc419a135e660722a641b9fd9f5fc52666284278c1a5
|
||||
size 13478104768
|
||||
3
llava.clip
Normal file
3
llava.clip
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:1ba531ae937fc2796cbab5ec5be0540c232d85a093eb04d33030315bc940ce65
|
||||
size 1214138849
|
||||
3
llava.projector
Normal file
3
llava.projector
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:a3df514424a53f7012de66a02fe7bcd3b06e68121ad5a9211ca7373e9dfc5384
|
||||
size 83920211
|
||||
3
mm_projector.bin
Normal file
3
mm_projector.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:d6a02763ce25984e4b82a59a082947b966c8ea1746f84d19bd4ccb15e64b8f51
|
||||
size 41961085
|
||||
3
mmproj-model-f16.gguf
Normal file
3
mmproj-model-f16.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:93d76855290f898d278e57cde99f9a91d1623a34be58e8b068a1746c4a2c922f
|
||||
size 624434336
|
||||
3
pytorch_model-00001-of-00002.bin
Normal file
3
pytorch_model-00001-of-00002.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:03b7e7824955a4e2cc64308ee8143b2f183ac351c5be55bcb8aedb333cacc5a6
|
||||
size 9976634558
|
||||
3
pytorch_model-00002-of-00002.bin
Normal file
3
pytorch_model-00002-of-00002.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:02df85213ab86f1d3c211bf3a571b7c8c9cdea50b6bbb69b02b2d689289bfb70
|
||||
size 3500315539
|
||||
725
pytorch_model.bin.index.json
Normal file
725
pytorch_model.bin.index.json
Normal file
@@ -0,0 +1,725 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 14125813760
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.embed_tokens.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.10.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.10.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.10.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.11.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.11.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.11.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.11.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.11.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.11.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.12.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.12.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.12.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.12.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.12.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.12.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.12.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.12.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.12.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.13.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.13.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.13.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.13.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.13.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.13.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.13.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.13.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.13.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.14.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.14.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.14.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.14.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.14.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.14.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.14.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.14.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.14.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.15.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.15.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.15.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.15.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.15.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.15.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.15.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.15.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.15.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.16.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.16.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.16.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.16.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.16.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.16.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.16.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.16.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.16.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.17.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.17.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.17.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.17.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.17.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.17.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.17.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.17.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.17.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.18.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.18.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.18.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.18.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.18.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.18.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.18.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.18.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.18.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.19.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.19.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.19.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.19.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.19.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.19.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.19.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.19.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.19.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.20.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.20.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.20.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.20.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.20.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.20.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.20.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.20.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.20.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.21.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.21.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.21.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.21.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.21.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.21.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.21.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.21.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.21.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.22.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.22.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.22.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.22.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.22.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.22.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.22.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.22.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.22.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.23.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.23.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.23.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.23.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.23.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.23.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.23.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.23.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.23.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.24.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.24.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.24.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.24.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.24.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.24.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.24.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.24.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.24.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.25.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.25.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.25.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.25.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.25.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.25.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.25.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.25.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.25.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.26.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.26.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.26.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.26.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.26.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.26.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.26.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.26.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.26.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.27.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.27.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.27.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.27.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.27.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.27.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.27.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.27.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.27.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.28.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.28.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.28.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.28.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.28.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.28.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.28.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.28.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.28.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.29.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.29.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.29.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.29.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.29.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.29.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.29.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.29.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.29.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.30.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.30.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.30.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.30.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.30.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.30.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.30.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.30.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.30.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.31.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.31.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.31.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.31.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.31.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.31.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.31.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.31.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.31.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.9.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.9.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.mm_projector.0.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.mm_projector.0.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.mm_projector.2.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.mm_projector.2.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.norm.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.embeddings.class_embedding": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.embeddings.patch_embedding.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.embeddings.position_embedding.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.post_layernorm.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.post_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.pre_layrnorm.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_tower.vision_tower.vision_model.pre_layrnorm.weight": "pytorch_model-00002-of-00002.bin"
|
||||
}
|
||||
}
|
||||
24
special_tokens_map.json
Normal file
24
special_tokens_map.json
Normal file
@@ -0,0 +1,24 @@
|
||||
{
|
||||
"bos_token": {
|
||||
"content": "<s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"eos_token": {
|
||||
"content": "</s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"pad_token": "<unk>",
|
||||
"unk_token": {
|
||||
"content": "<unk>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
3
tokenizer.model
Normal file
3
tokenizer.model
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
||||
size 499723
|
||||
36
tokenizer_config.json
Normal file
36
tokenizer_config.json
Normal file
@@ -0,0 +1,36 @@
|
||||
{
|
||||
"add_bos_token": true,
|
||||
"add_eos_token": false,
|
||||
"bos_token": {
|
||||
"__type": "AddedToken",
|
||||
"content": "<s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": {
|
||||
"__type": "AddedToken",
|
||||
"content": "</s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"legacy": false,
|
||||
"model_max_length": 1000000000000000019884624838656,
|
||||
"pad_token": null,
|
||||
"sp_model_kwargs": {},
|
||||
"spaces_between_special_tokens": false,
|
||||
"tokenizer_class": "LlamaTokenizer",
|
||||
"unk_token": {
|
||||
"__type": "AddedToken",
|
||||
"content": "<unk>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"use_default_system_prompt": true
|
||||
}
|
||||
111661
trainer_state.json
Normal file
111661
trainer_state.json
Normal file
File diff suppressed because it is too large
Load Diff
Reference in New Issue
Block a user