Upload folder using huggingface_hub

config.json

@@ -0,0 +1,55 @@
+{
+  "_name_or_path": "openbmb/MiniCPM-Llama3-V-2_5",
+  "architectures": [
+    "MiniCPMV"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "auto_map": {
+    "AutoConfig": "openbmb/MiniCPM-Llama3-V-2_5--configuration_minicpm.MiniCPMVConfig",
+    "AutoModel": "openbmb/MiniCPM-Llama3-V-2_5--modeling_minicpmv.MiniCPMV",
+    "AutoModelForCausalLM": "openbmb/MiniCPM-Llama3-V-2_5--modeling_minicpmv.MiniCPMV"
+  },
+  "batch_vision_input": true,
+  "bos_token_id": 128000,
+  "drop_vision_last_layer": false,
+  "eos_token_id": 128001,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "image_size": 448,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 8192,
+  "mlp_bias": false,
+  "mm_use_im_start_end": true,
+  "model_type": "minicpmv",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "patch_size": 14,
+  "pretraining_tp": 1,
+  "query_num": 96,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 500000.0,
+  "slice_config": {
+    "max_slice_nums": 9,
+    "model_type": "minicpmv"
+  },
+  "slice_mode": true,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.2",
+  "use_cache": true,
+  "version": "2.5",
+  "vision_config": {
+    "hidden_size": 1152,
+    "image_size": 980,
+    "intermediate_size": 4304,
+    "model_type": "idefics2",
+    "num_attention_heads": 16,
+    "num_hidden_layers": 27,
+    "patch_size": 14
+  },
+  "vocab_size": 128256
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 128000,
+  "eos_token_id": 128001,
+  "transformers_version": "4.44.2"
+}

model-00001-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c3350b146444782be59f27dd4587b87e164bcef97900048d7b375ad2edeb7af
+size 4886466296

model-00002-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:131e12858a1d09e353a896a245f03f62b923ba440687aab96e7b4fdc3e6b6230
+size 4832007640

model-00003-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08b3bdb1bdd409a0e4dea5f152b36bced3aa53817f6c7d69497e1e26dd78ea82
+size 4999813320

model-00004-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70761f5f040f52cfcbc5b75d373d440b26e3c669aaab19ebe1cf418702fcfe46
+size 4999813336

model-00005-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fae8ec2b8317430f058db4fb1e40f24c0aef6424a41e71bd05a00ed5e78a4ce4
+size 4832007688

model-00006-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2b134870daf5da754288aedf909ea25a95424e4a4138d157a067e4314c89f53
+size 4999813336

model-00007-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b391e4655a42ec35a4103608e29581dd16b167ebf82ac45767850c8e6dc968f1
+size 4598534152

model.safetensors.index.json

@@ -0,0 +1,748 @@
+{
+  "metadata": {
+    "total_size": 34148369344
+  },
+  "weight_map": {
+    "llm.lm_head.weight": "model-00007-of-00007.safetensors",
+    "llm.model.embed_tokens.weight": "model-00001-of-00007.safetensors",
+    "llm.model.layers.0.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "llm.model.layers.0.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "llm.model.layers.0.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "llm.model.layers.0.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "llm.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "llm.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "llm.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "llm.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "llm.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "llm.model.layers.1.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "llm.model.layers.1.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "llm.model.layers.1.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "llm.model.layers.1.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "llm.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "llm.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "llm.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "llm.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "llm.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "llm.model.layers.10.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "llm.model.layers.10.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "llm.model.layers.10.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "llm.model.layers.10.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "llm.model.layers.10.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "llm.model.layers.10.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "llm.model.layers.10.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "llm.model.layers.10.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "llm.model.layers.10.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "llm.model.layers.11.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "llm.model.layers.11.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "llm.model.layers.11.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "llm.model.layers.11.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "llm.model.layers.11.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "llm.model.layers.11.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "llm.model.layers.11.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "llm.model.layers.11.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "llm.model.layers.11.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "llm.model.layers.12.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "llm.model.layers.12.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "llm.model.layers.12.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "llm.model.layers.12.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "llm.model.layers.12.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "llm.model.layers.12.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "llm.model.layers.12.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "llm.model.layers.12.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "llm.model.layers.12.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "llm.model.layers.13.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "llm.model.layers.13.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "llm.model.layers.13.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "llm.model.layers.13.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "llm.model.layers.13.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "llm.model.layers.13.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "llm.model.layers.13.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "llm.model.layers.13.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "llm.model.layers.13.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "llm.model.layers.14.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "llm.model.layers.14.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "llm.model.layers.14.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "llm.model.layers.14.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "llm.model.layers.14.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "llm.model.layers.14.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "llm.model.layers.14.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "llm.model.layers.14.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "llm.model.layers.14.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "llm.model.layers.15.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "llm.model.layers.15.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "llm.model.layers.15.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "llm.model.layers.15.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "llm.model.layers.15.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "llm.model.layers.15.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "llm.model.layers.15.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "llm.model.layers.15.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "llm.model.layers.15.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "llm.model.layers.16.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "llm.model.layers.16.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "llm.model.layers.16.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "llm.model.layers.16.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "llm.model.layers.16.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "llm.model.layers.16.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "llm.model.layers.16.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "llm.model.layers.16.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "llm.model.layers.16.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "llm.model.layers.17.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "llm.model.layers.17.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "llm.model.layers.17.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "llm.model.layers.17.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "llm.model.layers.17.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "llm.model.layers.17.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "llm.model.layers.17.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "llm.model.layers.17.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "llm.model.layers.17.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "llm.model.layers.18.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "llm.model.layers.18.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "llm.model.layers.18.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "llm.model.layers.18.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "llm.model.layers.18.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "llm.model.layers.18.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "llm.model.layers.18.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "llm.model.layers.18.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "llm.model.layers.18.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "llm.model.layers.19.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "llm.model.layers.19.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "llm.model.layers.19.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "llm.model.layers.19.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "llm.model.layers.19.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "llm.model.layers.19.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "llm.model.layers.19.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "llm.model.layers.19.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "llm.model.layers.19.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "llm.model.layers.2.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "llm.model.layers.2.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "llm.model.layers.2.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "llm.model.layers.2.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "llm.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "llm.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "llm.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "llm.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "llm.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "llm.model.layers.20.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "llm.model.layers.20.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "llm.model.layers.20.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "llm.model.layers.20.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "llm.model.layers.20.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "llm.model.layers.20.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "llm.model.layers.20.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "llm.model.layers.20.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "llm.model.layers.20.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "llm.model.layers.21.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "llm.model.layers.21.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "llm.model.layers.21.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "llm.model.layers.21.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "llm.model.layers.21.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "llm.model.layers.21.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "llm.model.layers.21.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "llm.model.layers.21.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "llm.model.layers.21.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "llm.model.layers.22.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "llm.model.layers.22.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "llm.model.layers.22.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "llm.model.layers.22.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "llm.model.layers.22.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "llm.model.layers.22.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "llm.model.layers.22.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "llm.model.layers.22.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "llm.model.layers.22.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "llm.model.layers.23.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "llm.model.layers.23.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "llm.model.layers.23.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "llm.model.layers.23.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "llm.model.layers.23.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "llm.model.layers.23.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "llm.model.layers.23.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "llm.model.layers.23.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "llm.model.layers.23.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "llm.model.layers.24.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "llm.model.layers.24.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "llm.model.layers.24.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "llm.model.layers.24.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "llm.model.layers.24.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "llm.model.layers.24.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "llm.model.layers.24.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "llm.model.layers.24.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "llm.model.layers.24.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "llm.model.layers.25.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "llm.model.layers.25.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "llm.model.layers.25.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "llm.model.layers.25.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "llm.model.layers.25.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "llm.model.layers.25.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "llm.model.layers.25.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "llm.model.layers.25.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "llm.model.layers.25.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "llm.model.layers.26.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "llm.model.layers.26.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "llm.model.layers.26.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "llm.model.layers.26.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "llm.model.layers.26.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "llm.model.layers.26.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "llm.model.layers.26.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "llm.model.layers.26.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "llm.model.layers.26.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "llm.model.layers.27.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "llm.model.layers.27.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "llm.model.layers.27.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "llm.model.layers.27.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "llm.model.layers.27.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "llm.model.layers.27.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "llm.model.layers.27.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "llm.model.layers.27.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "llm.model.layers.27.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "llm.model.layers.28.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "llm.model.layers.28.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "llm.model.layers.28.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "llm.model.layers.28.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "llm.model.layers.28.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "llm.model.layers.28.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "llm.model.layers.28.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "llm.model.layers.28.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "llm.model.layers.28.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "llm.model.layers.29.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "llm.model.layers.29.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "llm.model.layers.29.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "llm.model.layers.29.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "llm.model.layers.29.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "llm.model.layers.29.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "llm.model.layers.29.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "llm.model.layers.29.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "llm.model.layers.29.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "llm.model.layers.3.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "llm.model.layers.3.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "llm.model.layers.3.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "llm.model.layers.3.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "llm.model.layers.3.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "llm.model.layers.3.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "llm.model.layers.3.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "llm.model.layers.3.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "llm.model.layers.3.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "llm.model.layers.30.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "llm.model.layers.30.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "llm.model.layers.30.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "llm.model.layers.30.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "llm.model.layers.30.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "llm.model.layers.30.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "llm.model.layers.30.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "llm.model.layers.30.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "llm.model.layers.30.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "llm.model.layers.31.input_layernorm.weight": "model-00007-of-00007.safetensors",
+    "llm.model.layers.31.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
+    "llm.model.layers.31.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "llm.model.layers.31.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
+    "llm.model.layers.31.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
+    "llm.model.layers.31.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "llm.model.layers.31.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "llm.model.layers.31.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "llm.model.layers.31.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "llm.model.layers.4.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "llm.model.layers.4.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "llm.model.layers.4.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "llm.model.layers.4.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "llm.model.layers.4.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "llm.model.layers.4.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "llm.model.layers.4.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "llm.model.layers.4.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "llm.model.layers.4.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "llm.model.layers.5.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "llm.model.layers.5.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "llm.model.layers.5.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "llm.model.layers.5.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "llm.model.layers.5.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "llm.model.layers.5.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "llm.model.layers.5.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "llm.model.layers.5.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "llm.model.layers.5.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "llm.model.layers.6.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "llm.model.layers.6.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "llm.model.layers.6.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "llm.model.layers.6.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "llm.model.layers.6.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "llm.model.layers.6.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "llm.model.layers.6.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "llm.model.layers.6.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "llm.model.layers.6.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "llm.model.layers.7.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "llm.model.layers.7.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "llm.model.layers.7.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "llm.model.layers.7.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "llm.model.layers.7.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "llm.model.layers.7.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "llm.model.layers.7.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "llm.model.layers.7.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "llm.model.layers.7.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "llm.model.layers.8.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "llm.model.layers.8.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "llm.model.layers.8.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "llm.model.layers.8.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "llm.model.layers.8.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "llm.model.layers.8.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "llm.model.layers.8.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "llm.model.layers.8.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "llm.model.layers.8.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "llm.model.layers.9.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "llm.model.layers.9.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "llm.model.layers.9.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "llm.model.layers.9.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "llm.model.layers.9.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "llm.model.layers.9.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "llm.model.layers.9.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "llm.model.layers.9.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "llm.model.layers.9.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "llm.model.norm.weight": "model-00007-of-00007.safetensors",
+    "resampler.attn.in_proj_bias": "model-00007-of-00007.safetensors",
+    "resampler.attn.in_proj_weight": "model-00007-of-00007.safetensors",
+    "resampler.attn.out_proj.bias": "model-00007-of-00007.safetensors",
+    "resampler.attn.out_proj.weight": "model-00007-of-00007.safetensors",
+    "resampler.kv_proj.weight": "model-00007-of-00007.safetensors",
+    "resampler.ln_kv.bias": "model-00007-of-00007.safetensors",
+    "resampler.ln_kv.weight": "model-00007-of-00007.safetensors",
+    "resampler.ln_post.bias": "model-00007-of-00007.safetensors",
+    "resampler.ln_post.weight": "model-00007-of-00007.safetensors",
+    "resampler.ln_q.bias": "model-00007-of-00007.safetensors",
+    "resampler.ln_q.weight": "model-00007-of-00007.safetensors",
+    "resampler.proj": "model-00007-of-00007.safetensors",
+    "resampler.query": "model-00007-of-00007.safetensors",
+    "vpm.embeddings.patch_embedding.bias": "model-00007-of-00007.safetensors",
+    "vpm.embeddings.patch_embedding.weight": "model-00007-of-00007.safetensors",
+    "vpm.embeddings.position_embedding.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.0.layer_norm1.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.0.layer_norm1.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.0.layer_norm2.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.0.layer_norm2.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.0.mlp.fc1.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.0.mlp.fc1.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.0.mlp.fc2.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.0.mlp.fc2.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.0.self_attn.k_proj.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.0.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.0.self_attn.out_proj.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.0.self_attn.out_proj.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.0.self_attn.q_proj.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.0.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.0.self_attn.v_proj.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.0.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.1.layer_norm1.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.1.layer_norm1.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.1.layer_norm2.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.1.layer_norm2.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.1.mlp.fc1.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.1.mlp.fc1.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.1.mlp.fc2.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.1.mlp.fc2.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.1.self_attn.k_proj.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.1.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.1.self_attn.out_proj.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.1.self_attn.out_proj.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.1.self_attn.q_proj.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.1.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.1.self_attn.v_proj.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.1.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.10.layer_norm1.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.10.layer_norm1.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.10.layer_norm2.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.10.layer_norm2.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.10.mlp.fc1.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.10.mlp.fc1.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.10.mlp.fc2.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.10.mlp.fc2.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.10.self_attn.k_proj.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.10.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.10.self_attn.out_proj.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.10.self_attn.out_proj.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.10.self_attn.q_proj.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.10.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.10.self_attn.v_proj.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.10.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.11.layer_norm1.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.11.layer_norm1.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.11.layer_norm2.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.11.layer_norm2.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.11.mlp.fc1.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.11.mlp.fc1.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.11.mlp.fc2.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.11.mlp.fc2.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.11.self_attn.k_proj.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.11.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.11.self_attn.out_proj.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.11.self_attn.out_proj.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.11.self_attn.q_proj.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.11.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.11.self_attn.v_proj.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.11.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.12.layer_norm1.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.12.layer_norm1.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.12.layer_norm2.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.12.layer_norm2.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.12.mlp.fc1.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.12.mlp.fc1.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.12.mlp.fc2.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.12.mlp.fc2.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.12.self_attn.k_proj.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.12.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.12.self_attn.out_proj.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.12.self_attn.out_proj.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.12.self_attn.q_proj.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.12.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.12.self_attn.v_proj.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.12.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.13.layer_norm1.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.13.layer_norm1.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.13.layer_norm2.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.13.layer_norm2.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.13.mlp.fc1.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.13.mlp.fc1.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.13.mlp.fc2.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.13.mlp.fc2.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.13.self_attn.k_proj.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.13.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.13.self_attn.out_proj.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.13.self_attn.out_proj.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.13.self_attn.q_proj.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.13.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.13.self_attn.v_proj.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.13.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.14.layer_norm1.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.14.layer_norm1.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.14.layer_norm2.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.14.layer_norm2.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.14.mlp.fc1.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.14.mlp.fc1.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.14.mlp.fc2.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.14.mlp.fc2.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.14.self_attn.k_proj.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.14.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.14.self_attn.out_proj.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.14.self_attn.out_proj.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.14.self_attn.q_proj.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.14.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.14.self_attn.v_proj.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.14.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.15.layer_norm1.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.15.layer_norm1.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.15.layer_norm2.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.15.layer_norm2.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.15.mlp.fc1.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.15.mlp.fc1.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.15.mlp.fc2.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.15.mlp.fc2.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.15.self_attn.k_proj.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.15.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.15.self_attn.out_proj.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.15.self_attn.out_proj.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.15.self_attn.q_proj.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.15.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.15.self_attn.v_proj.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.15.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.16.layer_norm1.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.16.layer_norm1.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.16.layer_norm2.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.16.layer_norm2.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.16.mlp.fc1.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.16.mlp.fc1.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.16.mlp.fc2.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.16.mlp.fc2.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.16.self_attn.k_proj.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.16.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.16.self_attn.out_proj.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.16.self_attn.out_proj.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.16.self_attn.q_proj.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.16.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.16.self_attn.v_proj.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.16.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.17.layer_norm1.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.17.layer_norm1.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.17.layer_norm2.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.17.layer_norm2.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.17.mlp.fc1.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.17.mlp.fc1.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.17.mlp.fc2.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.17.mlp.fc2.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.17.self_attn.k_proj.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.17.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.17.self_attn.out_proj.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.17.self_attn.out_proj.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.17.self_attn.q_proj.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.17.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.17.self_attn.v_proj.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.17.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.18.layer_norm1.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.18.layer_norm1.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.18.layer_norm2.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.18.layer_norm2.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.18.mlp.fc1.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.18.mlp.fc1.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.18.mlp.fc2.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.18.mlp.fc2.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.18.self_attn.k_proj.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.18.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.18.self_attn.out_proj.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.18.self_attn.out_proj.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.18.self_attn.q_proj.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.18.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.18.self_attn.v_proj.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.18.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.19.layer_norm1.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.19.layer_norm1.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.19.layer_norm2.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.19.layer_norm2.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.19.mlp.fc1.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.19.mlp.fc1.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.19.mlp.fc2.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.19.mlp.fc2.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.19.self_attn.k_proj.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.19.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.19.self_attn.out_proj.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.19.self_attn.out_proj.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.19.self_attn.q_proj.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.19.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.19.self_attn.v_proj.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.19.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.2.layer_norm1.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.2.layer_norm1.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.2.layer_norm2.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.2.layer_norm2.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.2.mlp.fc1.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.2.mlp.fc1.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.2.mlp.fc2.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.2.mlp.fc2.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.2.self_attn.k_proj.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.2.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.2.self_attn.out_proj.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.2.self_attn.out_proj.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.2.self_attn.q_proj.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.2.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.2.self_attn.v_proj.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.2.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.20.layer_norm1.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.20.layer_norm1.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.20.layer_norm2.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.20.layer_norm2.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.20.mlp.fc1.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.20.mlp.fc1.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.20.mlp.fc2.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.20.mlp.fc2.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.20.self_attn.k_proj.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.20.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.20.self_attn.out_proj.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.20.self_attn.out_proj.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.20.self_attn.q_proj.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.20.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.20.self_attn.v_proj.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.20.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.21.layer_norm1.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.21.layer_norm1.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.21.layer_norm2.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.21.layer_norm2.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.21.mlp.fc1.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.21.mlp.fc1.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.21.mlp.fc2.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.21.mlp.fc2.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.21.self_attn.k_proj.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.21.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.21.self_attn.out_proj.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.21.self_attn.out_proj.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.21.self_attn.q_proj.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.21.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.21.self_attn.v_proj.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.21.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.22.layer_norm1.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.22.layer_norm1.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.22.layer_norm2.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.22.layer_norm2.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.22.mlp.fc1.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.22.mlp.fc1.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.22.mlp.fc2.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.22.mlp.fc2.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.22.self_attn.k_proj.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.22.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.22.self_attn.out_proj.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.22.self_attn.out_proj.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.22.self_attn.q_proj.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.22.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.22.self_attn.v_proj.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.22.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.23.layer_norm1.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.23.layer_norm1.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.23.layer_norm2.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.23.layer_norm2.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.23.mlp.fc1.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.23.mlp.fc1.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.23.mlp.fc2.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.23.mlp.fc2.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.23.self_attn.k_proj.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.23.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.23.self_attn.out_proj.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.23.self_attn.out_proj.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.23.self_attn.q_proj.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.23.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.23.self_attn.v_proj.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.23.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.24.layer_norm1.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.24.layer_norm1.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.24.layer_norm2.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.24.layer_norm2.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.24.mlp.fc1.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.24.mlp.fc1.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.24.mlp.fc2.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.24.mlp.fc2.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.24.self_attn.k_proj.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.24.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.24.self_attn.out_proj.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.24.self_attn.out_proj.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.24.self_attn.q_proj.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.24.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.24.self_attn.v_proj.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.24.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.25.layer_norm1.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.25.layer_norm1.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.25.layer_norm2.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.25.layer_norm2.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.25.mlp.fc1.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.25.mlp.fc1.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.25.mlp.fc2.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.25.mlp.fc2.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.25.self_attn.k_proj.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.25.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.25.self_attn.out_proj.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.25.self_attn.out_proj.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.25.self_attn.q_proj.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.25.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.25.self_attn.v_proj.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.25.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.26.layer_norm1.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.26.layer_norm1.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.26.layer_norm2.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.26.layer_norm2.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.26.mlp.fc1.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.26.mlp.fc1.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.26.mlp.fc2.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.26.mlp.fc2.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.26.self_attn.k_proj.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.26.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.26.self_attn.out_proj.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.26.self_attn.out_proj.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.26.self_attn.q_proj.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.26.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.26.self_attn.v_proj.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.26.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.3.layer_norm1.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.3.layer_norm1.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.3.layer_norm2.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.3.layer_norm2.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.3.mlp.fc1.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.3.mlp.fc1.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.3.mlp.fc2.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.3.mlp.fc2.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.3.self_attn.k_proj.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.3.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.3.self_attn.out_proj.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.3.self_attn.out_proj.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.3.self_attn.q_proj.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.3.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.3.self_attn.v_proj.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.3.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.4.layer_norm1.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.4.layer_norm1.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.4.layer_norm2.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.4.layer_norm2.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.4.mlp.fc1.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.4.mlp.fc1.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.4.mlp.fc2.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.4.mlp.fc2.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.4.self_attn.k_proj.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.4.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.4.self_attn.out_proj.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.4.self_attn.out_proj.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.4.self_attn.q_proj.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.4.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.4.self_attn.v_proj.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.4.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.5.layer_norm1.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.5.layer_norm1.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.5.layer_norm2.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.5.layer_norm2.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.5.mlp.fc1.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.5.mlp.fc1.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.5.mlp.fc2.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.5.mlp.fc2.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.5.self_attn.k_proj.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.5.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.5.self_attn.out_proj.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.5.self_attn.out_proj.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.5.self_attn.q_proj.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.5.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.5.self_attn.v_proj.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.5.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.6.layer_norm1.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.6.layer_norm1.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.6.layer_norm2.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.6.layer_norm2.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.6.mlp.fc1.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.6.mlp.fc1.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.6.mlp.fc2.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.6.mlp.fc2.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.6.self_attn.k_proj.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.6.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.6.self_attn.out_proj.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.6.self_attn.out_proj.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.6.self_attn.q_proj.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.6.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.6.self_attn.v_proj.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.6.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.7.layer_norm1.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.7.layer_norm1.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.7.layer_norm2.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.7.layer_norm2.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.7.mlp.fc1.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.7.mlp.fc1.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.7.mlp.fc2.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.7.mlp.fc2.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.7.self_attn.k_proj.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.7.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.7.self_attn.out_proj.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.7.self_attn.out_proj.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.7.self_attn.q_proj.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.7.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.7.self_attn.v_proj.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.7.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.8.layer_norm1.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.8.layer_norm1.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.8.layer_norm2.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.8.layer_norm2.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.8.mlp.fc1.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.8.mlp.fc1.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.8.mlp.fc2.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.8.mlp.fc2.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.8.self_attn.k_proj.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.8.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.8.self_attn.out_proj.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.8.self_attn.out_proj.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.8.self_attn.q_proj.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.8.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.8.self_attn.v_proj.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.8.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.9.layer_norm1.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.9.layer_norm1.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.9.layer_norm2.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.9.layer_norm2.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.9.mlp.fc1.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.9.mlp.fc1.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.9.mlp.fc2.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.9.mlp.fc2.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.9.self_attn.k_proj.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.9.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.9.self_attn.out_proj.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.9.self_attn.out_proj.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.9.self_attn.q_proj.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.9.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.9.self_attn.v_proj.bias": "model-00007-of-00007.safetensors",
+    "vpm.encoder.layers.9.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
+    "vpm.post_layernorm.bias": "model-00007-of-00007.safetensors",
+    "vpm.post_layernorm.weight": "model-00007-of-00007.safetensors"
+  }
+}