update vision encoder

MLLM/llava-longclip336-mcl-v1.5-13b-pretrain/config.json

@@ -1,45 +0,0 @@
-{
-  "_name_or_path": "lmsys/vicuna-13b-v1.5",
-  "architectures": [
-    "LlamaForCausalLM"
-  ],
-  "attention_bias": false,
-  "attention_dropout": 0.0,
-  "bos_token_id": 1,
-  "eos_token_id": 2,
-  "freeze_mm_mlp_adapter": false,
-  "hidden_act": "silu",
-  "hidden_size": 5120,
-  "image_aspect_ratio": "square",
-  "initializer_range": 0.02,
-  "intermediate_size": 13824,
-  "max_length": 4096,
-  "max_position_embeddings": 4096,
-  "mm_hidden_size": 4096,
-  "mm_patch_merge_type": "flat",
-  "mm_projector_lr": null,
-  "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": "openai/clip-vit-large-patch14-336",
-  "model_type": "llava_llama",
-  "num_attention_heads": 40,
-  "num_hidden_layers": 40,
-  "num_key_value_heads": 40,
-  "pad_token_id": 0,
-  "pretraining_tp": 1,
-  "rms_norm_eps": 1e-05,
-  "rope_scaling": null,
-  "rope_theta": 10000.0,
-  "tie_word_embeddings": false,
-  "tokenizer_model_max_length": 2048,
-  "tokenizer_padding_side": "right",
-  "torch_dtype": "float16",
-  "transformers_version": "4.37.2",
-  "tune_mm_mlp_adapter": true,
-  "use_cache": true,
-  "use_mm_proj": true,
-  "vocab_size": 32000
-}

MLLM/llava-longclip336-mcl-v1.5-13b-pretrain/mm_projector.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:ae0600580b0e3e4dda63fd311ccd9e1d0cbb316fd27262b612bccb5d2724516e
-size 94394424

MLLM/llava-longclip336-mcl-v1.5-13b/config.json

@@ -1,45 +0,0 @@
-{
-  "_name_or_path": "lmsys/vicuna-13b-v1.5",
-  "architectures": [
-    "LlavaLlamaForCausalLM"
-  ],
-  "attention_bias": false,
-  "attention_dropout": 0.0,
-  "bos_token_id": 1,
-  "eos_token_id": 2,
-  "freeze_mm_mlp_adapter": false,
-  "hidden_act": "silu",
-  "hidden_size": 5120,
-  "image_aspect_ratio": "pad",
-  "initializer_range": 0.02,
-  "intermediate_size": 13824,
-  "max_length": 4096,
-  "max_position_embeddings": 4096,
-  "mm_hidden_size": 4096,
-  "mm_patch_merge_type": "flat",
-  "mm_projector_lr": null,
-  "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": "openai/clip-vit-large-patch14-336",
-  "model_type": "llava_llama",
-  "num_attention_heads": 40,
-  "num_hidden_layers": 40,
-  "num_key_value_heads": 40,
-  "pad_token_id": 0,
-  "pretraining_tp": 1,
-  "rms_norm_eps": 1e-05,
-  "rope_scaling": null,
-  "rope_theta": 10000.0,
-  "tie_word_embeddings": false,
-  "tokenizer_model_max_length": 2048,
-  "tokenizer_padding_side": "right",
-  "torch_dtype": "bfloat16",
-  "transformers_version": "4.37.2",
-  "tune_mm_mlp_adapter": false,
-  "use_cache": true,
-  "use_mm_proj": true,
-  "vocab_size": 32000
-}

MLLM/llava-longclip336-mcl-v1.5-13b/generation_config.json

@@ -1,11 +0,0 @@
-{
-  "_from_model_config": true,
-  "bos_token_id": 1,
-  "do_sample": true,
-  "eos_token_id": 2,
-  "max_length": 4096,
-  "pad_token_id": 0,
-  "temperature": 0.9,
-  "top_p": 0.6,
-  "transformers_version": "4.37.2"
-}

MLLM/llava-longclip336-mcl-v1.5-13b/model-00001-of-00006.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:cc8f811f81e5b9c02be2204fdad90f0a34e6503b5819714c2589fd550b7a46b0
-size 4978265800

MLLM/llava-longclip336-mcl-v1.5-13b/model-00002-of-00006.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:ead636d793520d17ab6d021a61c49927d53271fd448af2b09eafaa719355cf2b
-size 4970422232

MLLM/llava-longclip336-mcl-v1.5-13b/model-00003-of-00006.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:bc221f1a9d864ae9dd54dc3f52712e8a97c04b71f7c9bd8e962928900d9f28cf
-size 4970422256

MLLM/llava-longclip336-mcl-v1.5-13b/model-00004-of-00006.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:91f9d8b591f35c8cdeb9c8caed608d5e122e2baad6c0228cf85e424caf6c89a2
-size 4933701504

MLLM/llava-longclip336-mcl-v1.5-13b/model-00005-of-00006.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:b854087be5f32e4c872d1af3bf304c130375d90f923e48c5347b3bfa8482a397
-size 4933722216

MLLM/llava-longclip336-mcl-v1.5-13b/model-00006-of-00006.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:f7f71f17d7da73523820421e95acc4be614fb2d49dd51822dfb8aedc7fb6de58
-size 2173426656

MLLM/llava-longclip336-mcl-v1.5-13b/model.safetensors.index.json

@@ -1,775 +0,0 @@
-{
-  "metadata": {
-    "total_size": 26959863808
-  },
-  "weight_map": {
-    "lm_head.weight": "model-00006-of-00006.safetensors",
-    "model.embed_tokens.weight": "model-00001-of-00006.safetensors",
-    "model.layers.0.input_layernorm.weight": "model-00001-of-00006.safetensors",
-    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
-    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.1.input_layernorm.weight": "model-00001-of-00006.safetensors",
-    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
-    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.10.input_layernorm.weight": "model-00002-of-00006.safetensors",
-    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
-    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.11.input_layernorm.weight": "model-00002-of-00006.safetensors",
-    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
-    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.12.input_layernorm.weight": "model-00002-of-00006.safetensors",
-    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
-    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.13.input_layernorm.weight": "model-00002-of-00006.safetensors",
-    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
-    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.14.input_layernorm.weight": "model-00002-of-00006.safetensors",
-    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
-    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.15.input_layernorm.weight": "model-00003-of-00006.safetensors",
-    "model.layers.15.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.15.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
-    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.16.input_layernorm.weight": "model-00003-of-00006.safetensors",
-    "model.layers.16.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.16.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
-    "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.17.input_layernorm.weight": "model-00003-of-00006.safetensors",
-    "model.layers.17.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.17.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
-    "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.18.input_layernorm.weight": "model-00003-of-00006.safetensors",
-    "model.layers.18.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.18.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
-    "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.19.input_layernorm.weight": "model-00003-of-00006.safetensors",
-    "model.layers.19.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.19.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
-    "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.2.input_layernorm.weight": "model-00001-of-00006.safetensors",
-    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
-    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.20.input_layernorm.weight": "model-00003-of-00006.safetensors",
-    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
-    "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.21.input_layernorm.weight": "model-00003-of-00006.safetensors",
-    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
-    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.22.input_layernorm.weight": "model-00003-of-00006.safetensors",
-    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
-    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.23.input_layernorm.weight": "model-00004-of-00006.safetensors",
-    "model.layers.23.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.23.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.23.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.23.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
-    "model.layers.23.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.23.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.23.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.23.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.24.input_layernorm.weight": "model-00004-of-00006.safetensors",
-    "model.layers.24.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.24.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.24.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.24.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
-    "model.layers.24.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.24.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.24.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.24.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.25.input_layernorm.weight": "model-00004-of-00006.safetensors",
-    "model.layers.25.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.25.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.25.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
-    "model.layers.25.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.25.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.25.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.25.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.26.input_layernorm.weight": "model-00004-of-00006.safetensors",
-    "model.layers.26.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.26.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.26.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
-    "model.layers.26.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.26.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.26.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.26.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.27.input_layernorm.weight": "model-00004-of-00006.safetensors",
-    "model.layers.27.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.27.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
-    "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.28.input_layernorm.weight": "model-00004-of-00006.safetensors",
-    "model.layers.28.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.28.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.28.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.28.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
-    "model.layers.28.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.28.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.28.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.28.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.29.input_layernorm.weight": "model-00004-of-00006.safetensors",
-    "model.layers.29.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.29.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.29.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.29.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
-    "model.layers.29.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.29.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.29.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.29.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.3.input_layernorm.weight": "model-00001-of-00006.safetensors",
-    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
-    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.30.input_layernorm.weight": "model-00005-of-00006.safetensors",
-    "model.layers.30.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.30.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.30.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.30.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
-    "model.layers.30.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.30.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.30.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.30.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.31.input_layernorm.weight": "model-00005-of-00006.safetensors",
-    "model.layers.31.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.31.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.31.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.31.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
-    "model.layers.31.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.31.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.31.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.31.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.32.input_layernorm.weight": "model-00005-of-00006.safetensors",
-    "model.layers.32.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.32.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.32.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.32.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
-    "model.layers.32.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.32.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.32.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.32.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.33.input_layernorm.weight": "model-00005-of-00006.safetensors",
-    "model.layers.33.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.33.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.33.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.33.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
-    "model.layers.33.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.33.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.33.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.33.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.34.input_layernorm.weight": "model-00005-of-00006.safetensors",
-    "model.layers.34.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.34.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.34.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.34.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
-    "model.layers.34.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.34.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.34.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.34.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.35.input_layernorm.weight": "model-00005-of-00006.safetensors",
-    "model.layers.35.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.35.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.35.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.35.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
-    "model.layers.35.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.35.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.35.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.35.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.36.input_layernorm.weight": "model-00005-of-00006.safetensors",
-    "model.layers.36.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.36.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.36.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.36.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
-    "model.layers.36.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.36.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.36.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.36.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.37.input_layernorm.weight": "model-00005-of-00006.safetensors",
-    "model.layers.37.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.37.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.37.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.37.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
-    "model.layers.37.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.37.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.37.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.37.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.38.input_layernorm.weight": "model-00006-of-00006.safetensors",
-    "model.layers.38.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
-    "model.layers.38.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.38.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
-    "model.layers.38.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
-    "model.layers.38.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.38.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.38.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.38.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.39.input_layernorm.weight": "model-00006-of-00006.safetensors",
-    "model.layers.39.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
-    "model.layers.39.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
-    "model.layers.39.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
-    "model.layers.39.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
-    "model.layers.39.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
-    "model.layers.39.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
-    "model.layers.39.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
-    "model.layers.39.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
-    "model.layers.4.input_layernorm.weight": "model-00001-of-00006.safetensors",
-    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
-    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.5.input_layernorm.weight": "model-00001-of-00006.safetensors",
-    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
-    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.6.input_layernorm.weight": "model-00001-of-00006.safetensors",
-    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
-    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.7.input_layernorm.weight": "model-00002-of-00006.safetensors",
-    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
-    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.8.input_layernorm.weight": "model-00002-of-00006.safetensors",
-    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
-    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.9.input_layernorm.weight": "model-00002-of-00006.safetensors",
-    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
-    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
-    "model.mm_projector.0.bias": "model-00006-of-00006.safetensors",
-    "model.mm_projector.0.weight": "model-00006-of-00006.safetensors",
-    "model.mm_projector.2.bias": "model-00006-of-00006.safetensors",
-    "model.mm_projector.2.weight": "model-00006-of-00006.safetensors",
-    "model.norm.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.class_embedding": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.0.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.1.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.1.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.0.attn.in_proj_bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.0.attn.in_proj_weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.0.attn.out_proj.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.0.attn.out_proj.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.0.ln_1.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.0.ln_1.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.0.ln_2.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.0.ln_2.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.0.mlp.c_fc.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.0.mlp.c_fc.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.0.mlp.c_proj.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.0.mlp.c_proj.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.1.attn.in_proj_bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.1.attn.in_proj_weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.1.attn.out_proj.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.1.attn.out_proj.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.1.ln_1.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.1.ln_1.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.1.ln_2.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.1.ln_2.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.1.mlp.c_fc.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.1.mlp.c_fc.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.1.mlp.c_proj.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.1.mlp.c_proj.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.10.attn.in_proj_bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.10.attn.in_proj_weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.10.attn.out_proj.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.10.attn.out_proj.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.10.ln_1.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.10.ln_1.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.10.ln_2.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.10.ln_2.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.10.mlp.c_fc.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.10.mlp.c_fc.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.10.mlp.c_proj.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.10.mlp.c_proj.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.11.attn.in_proj_bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.11.attn.in_proj_weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.11.attn.out_proj.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.11.attn.out_proj.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.11.ln_1.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.11.ln_1.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.11.ln_2.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.11.ln_2.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.11.mlp.c_fc.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.11.mlp.c_fc.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.11.mlp.c_proj.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.11.mlp.c_proj.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.12.attn.in_proj_bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.12.attn.in_proj_weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.12.attn.out_proj.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.12.attn.out_proj.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.12.ln_1.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.12.ln_1.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.12.ln_2.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.12.ln_2.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.12.mlp.c_fc.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.12.mlp.c_fc.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.12.mlp.c_proj.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.12.mlp.c_proj.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.13.attn.in_proj_bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.13.attn.in_proj_weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.13.attn.out_proj.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.13.attn.out_proj.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.13.ln_1.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.13.ln_1.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.13.ln_2.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.13.ln_2.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.13.mlp.c_fc.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.13.mlp.c_fc.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.13.mlp.c_proj.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.13.mlp.c_proj.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.14.attn.in_proj_bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.14.attn.in_proj_weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.14.attn.out_proj.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.14.attn.out_proj.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.14.ln_1.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.14.ln_1.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.14.ln_2.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.14.ln_2.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.14.mlp.c_fc.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.14.mlp.c_fc.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.14.mlp.c_proj.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.14.mlp.c_proj.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.15.attn.in_proj_bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.15.attn.in_proj_weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.15.attn.out_proj.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.15.attn.out_proj.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.15.ln_1.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.15.ln_1.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.15.ln_2.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.15.ln_2.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.15.mlp.c_fc.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.15.mlp.c_fc.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.15.mlp.c_proj.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.15.mlp.c_proj.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.16.attn.in_proj_bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.16.attn.in_proj_weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.16.attn.out_proj.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.16.attn.out_proj.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.16.ln_1.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.16.ln_1.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.16.ln_2.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.16.ln_2.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.16.mlp.c_fc.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.16.mlp.c_fc.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.16.mlp.c_proj.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.16.mlp.c_proj.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.17.attn.in_proj_bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.17.attn.in_proj_weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.17.attn.out_proj.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.17.attn.out_proj.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.17.ln_1.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.17.ln_1.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.17.ln_2.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.17.ln_2.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.17.mlp.c_fc.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.17.mlp.c_fc.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.17.mlp.c_proj.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.17.mlp.c_proj.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.18.attn.in_proj_bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.18.attn.in_proj_weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.18.attn.out_proj.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.18.attn.out_proj.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.18.ln_1.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.18.ln_1.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.18.ln_2.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.18.ln_2.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.18.mlp.c_fc.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.18.mlp.c_fc.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.18.mlp.c_proj.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.18.mlp.c_proj.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.19.attn.in_proj_bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.19.attn.in_proj_weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.19.attn.out_proj.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.19.attn.out_proj.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.19.ln_1.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.19.ln_1.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.19.ln_2.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.19.ln_2.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.19.mlp.c_fc.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.19.mlp.c_fc.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.19.mlp.c_proj.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.19.mlp.c_proj.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.2.attn.in_proj_bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.2.attn.in_proj_weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.2.attn.out_proj.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.2.attn.out_proj.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.2.ln_1.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.2.ln_1.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.2.ln_2.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.2.ln_2.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.2.mlp.c_fc.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.2.mlp.c_fc.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.2.mlp.c_proj.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.2.mlp.c_proj.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.3.attn.in_proj_bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.3.attn.in_proj_weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.3.attn.out_proj.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.3.attn.out_proj.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.3.ln_1.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.3.ln_1.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.3.ln_2.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.3.ln_2.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.3.mlp.c_fc.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.3.mlp.c_fc.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.3.mlp.c_proj.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.3.mlp.c_proj.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.4.attn.in_proj_bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.4.attn.in_proj_weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.4.attn.out_proj.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.4.attn.out_proj.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.4.ln_1.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.4.ln_1.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.4.ln_2.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.4.ln_2.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.4.mlp.c_fc.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.4.mlp.c_fc.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.4.mlp.c_proj.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.4.mlp.c_proj.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.5.attn.in_proj_bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.5.attn.in_proj_weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.5.attn.out_proj.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.5.attn.out_proj.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.5.ln_1.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.5.ln_1.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.5.ln_2.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.5.ln_2.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.5.mlp.c_fc.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.5.mlp.c_fc.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.5.mlp.c_proj.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.5.mlp.c_proj.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.6.attn.in_proj_bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.6.attn.in_proj_weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.6.attn.out_proj.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.6.attn.out_proj.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.6.ln_1.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.6.ln_1.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.6.ln_2.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.6.ln_2.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.6.mlp.c_fc.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.6.mlp.c_fc.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.6.mlp.c_proj.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.6.mlp.c_proj.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.7.attn.in_proj_bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.7.attn.in_proj_weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.7.attn.out_proj.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.7.attn.out_proj.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.7.ln_1.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.7.ln_1.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.7.ln_2.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.7.ln_2.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.7.mlp.c_fc.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.7.mlp.c_fc.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.7.mlp.c_proj.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.7.mlp.c_proj.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.8.attn.in_proj_bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.8.attn.in_proj_weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.8.attn.out_proj.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.8.attn.out_proj.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.8.ln_1.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.8.ln_1.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.8.ln_2.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.8.ln_2.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.8.mlp.c_fc.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.8.mlp.c_fc.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.8.mlp.c_proj.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.8.mlp.c_proj.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.9.attn.in_proj_bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.9.attn.in_proj_weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.9.attn.out_proj.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.9.attn.out_proj.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.9.ln_1.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.9.ln_1.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.9.ln_2.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.9.ln_2.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.9.mlp.c_fc.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.9.mlp.c_fc.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.9.mlp.c_proj.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.fixed_vision_encoder.2.9.mlp.c_proj.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.positional_embedding": "model-00006-of-00006.safetensors",
-    "model.vision_tower.tuned_vision_encoders.0.20.attn.in_proj_bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.tuned_vision_encoders.0.20.attn.in_proj_weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.tuned_vision_encoders.0.20.attn.out_proj.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.tuned_vision_encoders.0.20.attn.out_proj.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.tuned_vision_encoders.0.20.ln_1.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.tuned_vision_encoders.0.20.ln_1.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.tuned_vision_encoders.0.20.ln_2.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.tuned_vision_encoders.0.20.ln_2.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.tuned_vision_encoders.0.20.mlp.c_fc.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.tuned_vision_encoders.0.20.mlp.c_fc.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.tuned_vision_encoders.0.20.mlp.c_proj.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.tuned_vision_encoders.0.20.mlp.c_proj.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.tuned_vision_encoders.0.21.attn.in_proj_bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.tuned_vision_encoders.0.21.attn.in_proj_weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.tuned_vision_encoders.0.21.attn.out_proj.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.tuned_vision_encoders.0.21.attn.out_proj.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.tuned_vision_encoders.0.21.ln_1.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.tuned_vision_encoders.0.21.ln_1.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.tuned_vision_encoders.0.21.ln_2.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.tuned_vision_encoders.0.21.ln_2.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.tuned_vision_encoders.0.21.mlp.c_fc.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.tuned_vision_encoders.0.21.mlp.c_fc.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.tuned_vision_encoders.0.21.mlp.c_proj.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.tuned_vision_encoders.0.21.mlp.c_proj.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.tuned_vision_encoders.0.22.attn.in_proj_bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.tuned_vision_encoders.0.22.attn.in_proj_weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.tuned_vision_encoders.0.22.attn.out_proj.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.tuned_vision_encoders.0.22.attn.out_proj.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.tuned_vision_encoders.0.22.ln_1.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.tuned_vision_encoders.0.22.ln_1.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.tuned_vision_encoders.0.22.ln_2.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.tuned_vision_encoders.0.22.ln_2.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.tuned_vision_encoders.0.22.mlp.c_fc.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.tuned_vision_encoders.0.22.mlp.c_fc.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.tuned_vision_encoders.0.22.mlp.c_proj.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.tuned_vision_encoders.0.22.mlp.c_proj.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.tuned_vision_encoders.0.23.attn.in_proj_bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.tuned_vision_encoders.0.23.attn.in_proj_weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.tuned_vision_encoders.0.23.attn.out_proj.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.tuned_vision_encoders.0.23.attn.out_proj.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.tuned_vision_encoders.0.23.ln_1.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.tuned_vision_encoders.0.23.ln_1.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.tuned_vision_encoders.0.23.ln_2.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.tuned_vision_encoders.0.23.ln_2.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.tuned_vision_encoders.0.23.mlp.c_fc.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.tuned_vision_encoders.0.23.mlp.c_fc.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.tuned_vision_encoders.0.23.mlp.c_proj.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.tuned_vision_encoders.0.23.mlp.c_proj.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.tuned_vision_encoders.1.20.attn.in_proj_bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.tuned_vision_encoders.1.20.attn.in_proj_weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.tuned_vision_encoders.1.20.attn.out_proj.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.tuned_vision_encoders.1.20.attn.out_proj.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.tuned_vision_encoders.1.20.ln_1.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.tuned_vision_encoders.1.20.ln_1.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.tuned_vision_encoders.1.20.ln_2.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.tuned_vision_encoders.1.20.ln_2.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.tuned_vision_encoders.1.20.mlp.c_fc.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.tuned_vision_encoders.1.20.mlp.c_fc.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.tuned_vision_encoders.1.20.mlp.c_proj.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.tuned_vision_encoders.1.20.mlp.c_proj.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.tuned_vision_encoders.1.21.attn.in_proj_bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.tuned_vision_encoders.1.21.attn.in_proj_weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.tuned_vision_encoders.1.21.attn.out_proj.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.tuned_vision_encoders.1.21.attn.out_proj.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.tuned_vision_encoders.1.21.ln_1.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.tuned_vision_encoders.1.21.ln_1.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.tuned_vision_encoders.1.21.ln_2.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.tuned_vision_encoders.1.21.ln_2.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.tuned_vision_encoders.1.21.mlp.c_fc.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.tuned_vision_encoders.1.21.mlp.c_fc.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.tuned_vision_encoders.1.21.mlp.c_proj.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.tuned_vision_encoders.1.21.mlp.c_proj.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.tuned_vision_encoders.1.22.attn.in_proj_bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.tuned_vision_encoders.1.22.attn.in_proj_weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.tuned_vision_encoders.1.22.attn.out_proj.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.tuned_vision_encoders.1.22.attn.out_proj.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.tuned_vision_encoders.1.22.ln_1.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.tuned_vision_encoders.1.22.ln_1.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.tuned_vision_encoders.1.22.ln_2.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.tuned_vision_encoders.1.22.ln_2.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.tuned_vision_encoders.1.22.mlp.c_fc.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.tuned_vision_encoders.1.22.mlp.c_fc.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.tuned_vision_encoders.1.22.mlp.c_proj.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.tuned_vision_encoders.1.22.mlp.c_proj.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.tuned_vision_encoders.2.20.attn.in_proj_bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.tuned_vision_encoders.2.20.attn.in_proj_weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.tuned_vision_encoders.2.20.attn.out_proj.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.tuned_vision_encoders.2.20.attn.out_proj.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.tuned_vision_encoders.2.20.ln_1.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.tuned_vision_encoders.2.20.ln_1.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.tuned_vision_encoders.2.20.ln_2.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.tuned_vision_encoders.2.20.ln_2.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.tuned_vision_encoders.2.20.mlp.c_fc.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.tuned_vision_encoders.2.20.mlp.c_fc.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.tuned_vision_encoders.2.20.mlp.c_proj.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.tuned_vision_encoders.2.20.mlp.c_proj.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.tuned_vision_encoders.2.21.attn.in_proj_bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.tuned_vision_encoders.2.21.attn.in_proj_weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.tuned_vision_encoders.2.21.attn.out_proj.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.tuned_vision_encoders.2.21.attn.out_proj.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.tuned_vision_encoders.2.21.ln_1.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.tuned_vision_encoders.2.21.ln_1.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.tuned_vision_encoders.2.21.ln_2.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.tuned_vision_encoders.2.21.ln_2.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.tuned_vision_encoders.2.21.mlp.c_fc.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.tuned_vision_encoders.2.21.mlp.c_fc.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.tuned_vision_encoders.2.21.mlp.c_proj.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.tuned_vision_encoders.2.21.mlp.c_proj.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.tuned_vision_encoders.2.22.attn.in_proj_bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.tuned_vision_encoders.2.22.attn.in_proj_weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.tuned_vision_encoders.2.22.attn.out_proj.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.tuned_vision_encoders.2.22.attn.out_proj.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.tuned_vision_encoders.2.22.ln_1.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.tuned_vision_encoders.2.22.ln_1.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.tuned_vision_encoders.2.22.ln_2.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.tuned_vision_encoders.2.22.ln_2.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.tuned_vision_encoders.2.22.mlp.c_fc.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.tuned_vision_encoders.2.22.mlp.c_fc.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.tuned_vision_encoders.2.22.mlp.c_proj.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.tuned_vision_encoders.2.22.mlp.c_proj.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.tuned_vision_encoders.3.20.attn.in_proj_bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.tuned_vision_encoders.3.20.attn.in_proj_weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.tuned_vision_encoders.3.20.attn.out_proj.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.tuned_vision_encoders.3.20.attn.out_proj.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.tuned_vision_encoders.3.20.ln_1.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.tuned_vision_encoders.3.20.ln_1.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.tuned_vision_encoders.3.20.ln_2.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.tuned_vision_encoders.3.20.ln_2.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.tuned_vision_encoders.3.20.mlp.c_fc.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.tuned_vision_encoders.3.20.mlp.c_fc.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.tuned_vision_encoders.3.20.mlp.c_proj.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.tuned_vision_encoders.3.20.mlp.c_proj.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.tuned_vision_encoders.3.21.attn.in_proj_bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.tuned_vision_encoders.3.21.attn.in_proj_weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.tuned_vision_encoders.3.21.attn.out_proj.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.tuned_vision_encoders.3.21.attn.out_proj.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.tuned_vision_encoders.3.21.ln_1.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.tuned_vision_encoders.3.21.ln_1.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.tuned_vision_encoders.3.21.ln_2.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.tuned_vision_encoders.3.21.ln_2.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.tuned_vision_encoders.3.21.mlp.c_fc.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.tuned_vision_encoders.3.21.mlp.c_fc.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.tuned_vision_encoders.3.21.mlp.c_proj.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.tuned_vision_encoders.3.21.mlp.c_proj.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.tuned_vision_encoders.3.22.attn.in_proj_bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.tuned_vision_encoders.3.22.attn.in_proj_weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.tuned_vision_encoders.3.22.attn.out_proj.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.tuned_vision_encoders.3.22.attn.out_proj.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.tuned_vision_encoders.3.22.ln_1.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.tuned_vision_encoders.3.22.ln_1.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.tuned_vision_encoders.3.22.ln_2.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.tuned_vision_encoders.3.22.ln_2.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.tuned_vision_encoders.3.22.mlp.c_fc.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.tuned_vision_encoders.3.22.mlp.c_fc.weight": "model-00006-of-00006.safetensors",
-    "model.vision_tower.tuned_vision_encoders.3.22.mlp.c_proj.bias": "model-00006-of-00006.safetensors",
-    "model.vision_tower.tuned_vision_encoders.3.22.mlp.c_proj.weight": "model-00006-of-00006.safetensors"
-  }
-}

MLLM/llava-longclip336-mcl-v1.5-13b/special_tokens_map.json

@@ -1,24 +0,0 @@
-{
-  "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
-  }
-}

MLLM/llava-longclip336-mcl-v1.5-13b/tokenizer.model

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
-size 499723

MLLM/llava-longclip336-mcl-v1.5-13b/tokenizer_config.json

@@ -1,42 +0,0 @@
-{
-  "add_bos_token": true,
-  "add_eos_token": false,
-  "added_tokens_decoder": {
-    "0": {
-      "content": "<unk>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "1": {
-      "content": "<s>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "2": {
-      "content": "</s>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    }
-  },
-  "bos_token": "<s>",
-  "clean_up_tokenization_spaces": false,
-  "eos_token": "</s>",
-  "legacy": false,
-  "model_max_length": 2048,
-  "pad_token": "<unk>",
-  "padding_side": "right",
-  "sp_model_kwargs": {},
-  "spaces_between_special_tokens": false,
-  "tokenizer_class": "LlamaTokenizer",
-  "unk_token": "<unk>",
-  "use_default_system_prompt": false
-}

MLLM/llava-longclip336-mcl-v1.5-13b/training_args.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:c2763320ea3632c31c6b05173e8eacb48a5327b6cbe98faf8a2f6c87f8875187
-size 6328

checkpoints_dc/dft-full-dc-lr1e-5.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:46123d4d28988d47956c63fd110b0469db7a992d598795e01d7301a7bee0490e
-size 1711930026

checkpoints_dc/dft-full-share-lr1e-5.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:2d87079117de23f2140f5fa6868d3263530e7bd022d0b0e66d508d847b2717fd
-size 1711930026

checkpoints_dc/uc-6-dc-lr1e-4.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:e43f875d1bcf2240ebf80ee3f635bf5adf9429389b661e6483c450d4821d5b11
-size 2656536170

checkpoints_dc/uc-6-share-lr1e-4.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:4ac919f0c60cd7b23dc940acb430ecfbc9ac39851a784670b929426f6dc78d95
-size 2656536170

checkpoints_dc/uc-6-share-lr5e-5.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:5c61d2be7ef00455e74db513cd8f32a7dccbd2a99dbdcce8b4dc04d4fb015058
-size 2656536170

checkpoints_new/clip224-openai.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:1f91cffdb625f15d3a7de917da585b8e097cdcefca090722d5ab9c36285999e0
-size 1711930026

vision_encoder/longclip336-lr1e-6-epoch1-stage0.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:de7b1c51895f686e2cd845dc2aef3575074be15b340a6b39aaf52cf46ae08f0c
-size 1713240746

vision_encoder/longclip336-lr1e-6-epoch1-stage1.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:bbce9f8eacbdd4cf7f5a6341d10210a96e000bece062f1a823b802f71475f4b4
-size 1713240746

vision_encoder/longclip336-lr1e-6-epoch1-stage2.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:97b401daa12e69f5d7700f12157c18018c2e18b856c335368539eb721f980645
-size 1713240746