Upload 5 files

config.json

@@ -0,0 +1,40 @@
+{
+  "_name_or_path": "openbmb/MiniCPM-V",
+  "architectures": [
+    "MiniCPMV"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "auto_map": {
+    "AutoConfig": "openbmb/MiniCPM-V--configuration_minicpm.MiniCPMVConfig",
+    "AutoModel": "openbmb/MiniCPM-V--modeling_minicpmv.MiniCPMV",
+    "AutoModelForCausalLM": "openbmb/MiniCPM-V--modeling_minicpmv.MiniCPMV"
+  },
+  "bos_token_id": 1,
+  "dim_model_base": 256,
+  "drop_vision_last_layer": true,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 2304,
+  "image_size": 448,
+  "initializer_range": 0.1,
+  "intermediate_size": 5760,
+  "max_position_embeddings": 4096,
+  "model_type": "minicpmv",
+  "num_attention_heads": 36,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 36,
+  "pretraining_tp": 1,
+  "query_num": 64,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "scale_depth": 1.4,
+  "scale_emb": 12,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.37.2",
+  "use_cache": true,
+  "vision_encoder": "vit_so400m_patch14_siglip_384.webli",
+  "vocab_size": 122753
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.37.2"
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bed8af8e9f7549ffb8c6f1d6423cacfc8eba8a9ff741692c0472a7cbb7e4d69c
+size 4993235928

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9152aea9e0c3488ea78a92169f85647e4264ccd48e8dca853c97b411cfae8030
+size 1876772888

model.safetensors.index.json

@@ -0,0 +1,701 @@
+{
+  "metadata": {
+    "total_size": 6869931584
+  },
+  "weight_map": {
+    "llm.lm_head.weight": "model-00002-of-00002.safetensors",
+    "llm.model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.24.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.25.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.25.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.26.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.26.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.26.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.27.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.27.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.27.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.27.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.27.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.27.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.28.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.28.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.28.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.28.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.28.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.28.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.28.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.28.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.28.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.29.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.29.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.29.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.29.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.29.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.29.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.29.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.29.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.29.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.30.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.30.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.30.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.30.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.30.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.30.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.30.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.30.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.30.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.31.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.31.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.31.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.31.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.31.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.31.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.31.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.31.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.31.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.32.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.32.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.32.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.32.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.32.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.32.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.32.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.32.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.32.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.33.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.33.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.33.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.33.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.33.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.33.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.33.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.33.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.33.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.34.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.34.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.34.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.34.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.34.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.34.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.34.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.34.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.34.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.35.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.35.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.35.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.35.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.35.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.35.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.35.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.35.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.35.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.36.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "llm.model.layers.36.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "llm.model.layers.36.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "llm.model.layers.36.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "llm.model.layers.36.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "llm.model.layers.36.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.36.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "llm.model.layers.36.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.36.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.37.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "llm.model.layers.37.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "llm.model.layers.37.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "llm.model.layers.37.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "llm.model.layers.37.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "llm.model.layers.37.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "llm.model.layers.37.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "llm.model.layers.37.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "llm.model.layers.37.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "llm.model.layers.38.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "llm.model.layers.38.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "llm.model.layers.38.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "llm.model.layers.38.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "llm.model.layers.38.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "llm.model.layers.38.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "llm.model.layers.38.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "llm.model.layers.38.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "llm.model.layers.38.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "llm.model.layers.39.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "llm.model.layers.39.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "llm.model.layers.39.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "llm.model.layers.39.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "llm.model.layers.39.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "llm.model.layers.39.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "llm.model.layers.39.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "llm.model.layers.39.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "llm.model.layers.39.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "llm.model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "llm.model.norm.weight": "model-00002-of-00002.safetensors",
+    "resampler.attn.in_proj_bias": "model-00002-of-00002.safetensors",
+    "resampler.attn.in_proj_weight": "model-00002-of-00002.safetensors",
+    "resampler.attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "resampler.attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "resampler.kv_proj.weight": "model-00002-of-00002.safetensors",
+    "resampler.ln_kv.bias": "model-00002-of-00002.safetensors",
+    "resampler.ln_kv.weight": "model-00002-of-00002.safetensors",
+    "resampler.ln_post.bias": "model-00002-of-00002.safetensors",
+    "resampler.ln_post.weight": "model-00002-of-00002.safetensors",
+    "resampler.ln_q.bias": "model-00002-of-00002.safetensors",
+    "resampler.ln_q.weight": "model-00002-of-00002.safetensors",
+    "resampler.pos_embed": "model-00002-of-00002.safetensors",
+    "resampler.proj": "model-00002-of-00002.safetensors",
+    "resampler.query": "model-00002-of-00002.safetensors",
+    "vpm.blocks.0.attn.proj.bias": "model-00002-of-00002.safetensors",
+    "vpm.blocks.0.attn.proj.weight": "model-00002-of-00002.safetensors",
+    "vpm.blocks.0.attn.qkv.bias": "model-00002-of-00002.safetensors",
+    "vpm.blocks.0.attn.qkv.weight": "model-00002-of-00002.safetensors",
+    "vpm.blocks.0.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "vpm.blocks.0.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "vpm.blocks.0.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "vpm.blocks.0.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "vpm.blocks.0.norm1.bias": "model-00002-of-00002.safetensors",
+    "vpm.blocks.0.norm1.weight": "model-00002-of-00002.safetensors",
+    "vpm.blocks.0.norm2.bias": "model-00002-of-00002.safetensors",
+    "vpm.blocks.0.norm2.weight": "model-00002-of-00002.safetensors",
+    "vpm.blocks.1.attn.proj.bias": "model-00002-of-00002.safetensors",
+    "vpm.blocks.1.attn.proj.weight": "model-00002-of-00002.safetensors",
+    "vpm.blocks.1.attn.qkv.bias": "model-00002-of-00002.safetensors",
+    "vpm.blocks.1.attn.qkv.weight": "model-00002-of-00002.safetensors",
+    "vpm.blocks.1.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "vpm.blocks.1.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "vpm.blocks.1.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "vpm.blocks.1.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "vpm.blocks.1.norm1.bias": "model-00002-of-00002.safetensors",
+    "vpm.blocks.1.norm1.weight": "model-00002-of-00002.safetensors",
+    "vpm.blocks.1.norm2.bias": "model-00002-of-00002.safetensors",
+    "vpm.blocks.1.norm2.weight": "model-00002-of-00002.safetensors",
+    "vpm.blocks.10.attn.proj.bias": "model-00002-of-00002.safetensors",
+    "vpm.blocks.10.attn.proj.weight": "model-00002-of-00002.safetensors",
+    "vpm.blocks.10.attn.qkv.bias": "model-00002-of-00002.safetensors",
+    "vpm.blocks.10.attn.qkv.weight": "model-00002-of-00002.safetensors",
+    "vpm.blocks.10.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "vpm.blocks.10.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "vpm.blocks.10.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "vpm.blocks.10.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "vpm.blocks.10.norm1.bias": "model-00002-of-00002.safetensors",
+    "vpm.blocks.10.norm1.weight": "model-00002-of-00002.safetensors",
+    "vpm.blocks.10.norm2.bias": "model-00002-of-00002.safetensors",
+    "vpm.blocks.10.norm2.weight": "model-00002-of-00002.safetensors",
+    "vpm.blocks.11.attn.proj.bias": "model-00002-of-00002.safetensors",
+    "vpm.blocks.11.attn.proj.weight": "model-00002-of-00002.safetensors",
+    "vpm.blocks.11.attn.qkv.bias": "model-00002-of-00002.safetensors",
+    "vpm.blocks.11.attn.qkv.weight": "model-00002-of-00002.safetensors",
+    "vpm.blocks.11.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "vpm.blocks.11.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "vpm.blocks.11.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "vpm.blocks.11.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "vpm.blocks.11.norm1.bias": "model-00002-of-00002.safetensors",
+    "vpm.blocks.11.norm1.weight": "model-00002-of-00002.safetensors",
+    "vpm.blocks.11.norm2.bias": "model-00002-of-00002.safetensors",
+    "vpm.blocks.11.norm2.weight": "model-00002-of-00002.safetensors",
+    "vpm.blocks.12.attn.proj.bias": "model-00002-of-00002.safetensors",
+    "vpm.blocks.12.attn.proj.weight": "model-00002-of-00002.safetensors",
+    "vpm.blocks.12.attn.qkv.bias": "model-00002-of-00002.safetensors",
+    "vpm.blocks.12.attn.qkv.weight": "model-00002-of-00002.safetensors",
+    "vpm.blocks.12.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "vpm.blocks.12.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "vpm.blocks.12.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "vpm.blocks.12.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "vpm.blocks.12.norm1.bias": "model-00002-of-00002.safetensors",
+    "vpm.blocks.12.norm1.weight": "model-00002-of-00002.safetensors",
+    "vpm.blocks.12.norm2.bias": "model-00002-of-00002.safetensors",
+    "vpm.blocks.12.norm2.weight": "model-00002-of-00002.safetensors",
+    "vpm.blocks.13.attn.proj.bias": "model-00002-of-00002.safetensors",
+    "vpm.blocks.13.attn.proj.weight": "model-00002-of-00002.safetensors",
+    "vpm.blocks.13.attn.qkv.bias": "model-00002-of-00002.safetensors",
+    "vpm.blocks.13.attn.qkv.weight": "model-00002-of-00002.safetensors",
+    "vpm.blocks.13.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "vpm.blocks.13.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "vpm.blocks.13.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "vpm.blocks.13.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "vpm.blocks.13.norm1.bias": "model-00002-of-00002.safetensors",
+    "vpm.blocks.13.norm1.weight": "model-00002-of-00002.safetensors",
+    "vpm.blocks.13.norm2.bias": "model-00002-of-00002.safetensors",
+    "vpm.blocks.13.norm2.weight": "model-00002-of-00002.safetensors",
+    "vpm.blocks.14.attn.proj.bias": "model-00002-of-00002.safetensors",
+    "vpm.blocks.14.attn.proj.weight": "model-00002-of-00002.safetensors",
+    "vpm.blocks.14.attn.qkv.bias": "model-00002-of-00002.safetensors",
+    "vpm.blocks.14.attn.qkv.weight": "model-00002-of-00002.safetensors",
+    "vpm.blocks.14.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "vpm.blocks.14.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "vpm.blocks.14.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "vpm.blocks.14.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "vpm.blocks.14.norm1.bias": "model-00002-of-00002.safetensors",
+    "vpm.blocks.14.norm1.weight": "model-00002-of-00002.safetensors",
+    "vpm.blocks.14.norm2.bias": "model-00002-of-00002.safetensors",
+    "vpm.blocks.14.norm2.weight": "model-00002-of-00002.safetensors",
+    "vpm.blocks.15.attn.proj.bias": "model-00002-of-00002.safetensors",
+    "vpm.blocks.15.attn.proj.weight": "model-00002-of-00002.safetensors",
+    "vpm.blocks.15.attn.qkv.bias": "model-00002-of-00002.safetensors",
+    "vpm.blocks.15.attn.qkv.weight": "model-00002-of-00002.safetensors",
+    "vpm.blocks.15.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "vpm.blocks.15.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "vpm.blocks.15.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "vpm.blocks.15.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "vpm.blocks.15.norm1.bias": "model-00002-of-00002.safetensors",
+    "vpm.blocks.15.norm1.weight": "model-00002-of-00002.safetensors",
+    "vpm.blocks.15.norm2.bias": "model-00002-of-00002.safetensors",
+    "vpm.blocks.15.norm2.weight": "model-00002-of-00002.safetensors",
+    "vpm.blocks.16.attn.proj.bias": "model-00002-of-00002.safetensors",
+    "vpm.blocks.16.attn.proj.weight": "model-00002-of-00002.safetensors",
+    "vpm.blocks.16.attn.qkv.bias": "model-00002-of-00002.safetensors",
+    "vpm.blocks.16.attn.qkv.weight": "model-00002-of-00002.safetensors",
+    "vpm.blocks.16.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "vpm.blocks.16.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "vpm.blocks.16.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "vpm.blocks.16.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "vpm.blocks.16.norm1.bias": "model-00002-of-00002.safetensors",
+    "vpm.blocks.16.norm1.weight": "model-00002-of-00002.safetensors",
+    "vpm.blocks.16.norm2.bias": "model-00002-of-00002.safetensors",
+    "vpm.blocks.16.norm2.weight": "model-00002-of-00002.safetensors",
+    "vpm.blocks.17.attn.proj.bias": "model-00002-of-00002.safetensors",
+    "vpm.blocks.17.attn.proj.weight": "model-00002-of-00002.safetensors",
+    "vpm.blocks.17.attn.qkv.bias": "model-00002-of-00002.safetensors",
+    "vpm.blocks.17.attn.qkv.weight": "model-00002-of-00002.safetensors",
+    "vpm.blocks.17.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "vpm.blocks.17.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "vpm.blocks.17.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "vpm.blocks.17.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "vpm.blocks.17.norm1.bias": "model-00002-of-00002.safetensors",
+    "vpm.blocks.17.norm1.weight": "model-00002-of-00002.safetensors",
+    "vpm.blocks.17.norm2.bias": "model-00002-of-00002.safetensors",
+    "vpm.blocks.17.norm2.weight": "model-00002-of-00002.safetensors",
+    "vpm.blocks.18.attn.proj.bias": "model-00002-of-00002.safetensors",
+    "vpm.blocks.18.attn.proj.weight": "model-00002-of-00002.safetensors",
+    "vpm.blocks.18.attn.qkv.bias": "model-00002-of-00002.safetensors",
+    "vpm.blocks.18.attn.qkv.weight": "model-00002-of-00002.safetensors",
+    "vpm.blocks.18.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "vpm.blocks.18.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "vpm.blocks.18.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "vpm.blocks.18.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "vpm.blocks.18.norm1.bias": "model-00002-of-00002.safetensors",
+    "vpm.blocks.18.norm1.weight": "model-00002-of-00002.safetensors",
+    "vpm.blocks.18.norm2.bias": "model-00002-of-00002.safetensors",
+    "vpm.blocks.18.norm2.weight": "model-00002-of-00002.safetensors",
+    "vpm.blocks.19.attn.proj.bias": "model-00002-of-00002.safetensors",
+    "vpm.blocks.19.attn.proj.weight": "model-00002-of-00002.safetensors",
+    "vpm.blocks.19.attn.qkv.bias": "model-00002-of-00002.safetensors",
+    "vpm.blocks.19.attn.qkv.weight": "model-00002-of-00002.safetensors",
+    "vpm.blocks.19.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "vpm.blocks.19.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "vpm.blocks.19.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "vpm.blocks.19.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "vpm.blocks.19.norm1.bias": "model-00002-of-00002.safetensors",
+    "vpm.blocks.19.norm1.weight": "model-00002-of-00002.safetensors",
+    "vpm.blocks.19.norm2.bias": "model-00002-of-00002.safetensors",
+    "vpm.blocks.19.norm2.weight": "model-00002-of-00002.safetensors",
+    "vpm.blocks.2.attn.proj.bias": "model-00002-of-00002.safetensors",
+    "vpm.blocks.2.attn.proj.weight": "model-00002-of-00002.safetensors",
+    "vpm.blocks.2.attn.qkv.bias": "model-00002-of-00002.safetensors",
+    "vpm.blocks.2.attn.qkv.weight": "model-00002-of-00002.safetensors",
+    "vpm.blocks.2.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "vpm.blocks.2.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "vpm.blocks.2.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "vpm.blocks.2.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "vpm.blocks.2.norm1.bias": "model-00002-of-00002.safetensors",
+    "vpm.blocks.2.norm1.weight": "model-00002-of-00002.safetensors",
+    "vpm.blocks.2.norm2.bias": "model-00002-of-00002.safetensors",
+    "vpm.blocks.2.norm2.weight": "model-00002-of-00002.safetensors",
+    "vpm.blocks.20.attn.proj.bias": "model-00002-of-00002.safetensors",
+    "vpm.blocks.20.attn.proj.weight": "model-00002-of-00002.safetensors",
+    "vpm.blocks.20.attn.qkv.bias": "model-00002-of-00002.safetensors",
+    "vpm.blocks.20.attn.qkv.weight": "model-00002-of-00002.safetensors",
+    "vpm.blocks.20.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "vpm.blocks.20.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "vpm.blocks.20.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "vpm.blocks.20.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "vpm.blocks.20.norm1.bias": "model-00002-of-00002.safetensors",
+    "vpm.blocks.20.norm1.weight": "model-00002-of-00002.safetensors",
+    "vpm.blocks.20.norm2.bias": "model-00002-of-00002.safetensors",
+    "vpm.blocks.20.norm2.weight": "model-00002-of-00002.safetensors",
+    "vpm.blocks.21.attn.proj.bias": "model-00002-of-00002.safetensors",
+    "vpm.blocks.21.attn.proj.weight": "model-00002-of-00002.safetensors",
+    "vpm.blocks.21.attn.qkv.bias": "model-00002-of-00002.safetensors",
+    "vpm.blocks.21.attn.qkv.weight": "model-00002-of-00002.safetensors",
+    "vpm.blocks.21.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "vpm.blocks.21.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "vpm.blocks.21.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "vpm.blocks.21.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "vpm.blocks.21.norm1.bias": "model-00002-of-00002.safetensors",
+    "vpm.blocks.21.norm1.weight": "model-00002-of-00002.safetensors",
+    "vpm.blocks.21.norm2.bias": "model-00002-of-00002.safetensors",
+    "vpm.blocks.21.norm2.weight": "model-00002-of-00002.safetensors",
+    "vpm.blocks.22.attn.proj.bias": "model-00002-of-00002.safetensors",
+    "vpm.blocks.22.attn.proj.weight": "model-00002-of-00002.safetensors",
+    "vpm.blocks.22.attn.qkv.bias": "model-00002-of-00002.safetensors",
+    "vpm.blocks.22.attn.qkv.weight": "model-00002-of-00002.safetensors",
+    "vpm.blocks.22.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "vpm.blocks.22.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "vpm.blocks.22.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "vpm.blocks.22.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "vpm.blocks.22.norm1.bias": "model-00002-of-00002.safetensors",
+    "vpm.blocks.22.norm1.weight": "model-00002-of-00002.safetensors",
+    "vpm.blocks.22.norm2.bias": "model-00002-of-00002.safetensors",
+    "vpm.blocks.22.norm2.weight": "model-00002-of-00002.safetensors",
+    "vpm.blocks.23.attn.proj.bias": "model-00002-of-00002.safetensors",
+    "vpm.blocks.23.attn.proj.weight": "model-00002-of-00002.safetensors",
+    "vpm.blocks.23.attn.qkv.bias": "model-00002-of-00002.safetensors",
+    "vpm.blocks.23.attn.qkv.weight": "model-00002-of-00002.safetensors",
+    "vpm.blocks.23.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "vpm.blocks.23.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "vpm.blocks.23.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "vpm.blocks.23.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "vpm.blocks.23.norm1.bias": "model-00002-of-00002.safetensors",
+    "vpm.blocks.23.norm1.weight": "model-00002-of-00002.safetensors",
+    "vpm.blocks.23.norm2.bias": "model-00002-of-00002.safetensors",
+    "vpm.blocks.23.norm2.weight": "model-00002-of-00002.safetensors",
+    "vpm.blocks.24.attn.proj.bias": "model-00002-of-00002.safetensors",
+    "vpm.blocks.24.attn.proj.weight": "model-00002-of-00002.safetensors",
+    "vpm.blocks.24.attn.qkv.bias": "model-00002-of-00002.safetensors",
+    "vpm.blocks.24.attn.qkv.weight": "model-00002-of-00002.safetensors",
+    "vpm.blocks.24.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "vpm.blocks.24.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "vpm.blocks.24.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "vpm.blocks.24.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "vpm.blocks.24.norm1.bias": "model-00002-of-00002.safetensors",
+    "vpm.blocks.24.norm1.weight": "model-00002-of-00002.safetensors",
+    "vpm.blocks.24.norm2.bias": "model-00002-of-00002.safetensors",
+    "vpm.blocks.24.norm2.weight": "model-00002-of-00002.safetensors",
+    "vpm.blocks.25.attn.proj.bias": "model-00002-of-00002.safetensors",
+    "vpm.blocks.25.attn.proj.weight": "model-00002-of-00002.safetensors",
+    "vpm.blocks.25.attn.qkv.bias": "model-00002-of-00002.safetensors",
+    "vpm.blocks.25.attn.qkv.weight": "model-00002-of-00002.safetensors",
+    "vpm.blocks.25.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "vpm.blocks.25.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "vpm.blocks.25.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "vpm.blocks.25.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "vpm.blocks.25.norm1.bias": "model-00002-of-00002.safetensors",
+    "vpm.blocks.25.norm1.weight": "model-00002-of-00002.safetensors",
+    "vpm.blocks.25.norm2.bias": "model-00002-of-00002.safetensors",
+    "vpm.blocks.25.norm2.weight": "model-00002-of-00002.safetensors",
+    "vpm.blocks.3.attn.proj.bias": "model-00002-of-00002.safetensors",
+    "vpm.blocks.3.attn.proj.weight": "model-00002-of-00002.safetensors",
+    "vpm.blocks.3.attn.qkv.bias": "model-00002-of-00002.safetensors",
+    "vpm.blocks.3.attn.qkv.weight": "model-00002-of-00002.safetensors",
+    "vpm.blocks.3.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "vpm.blocks.3.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "vpm.blocks.3.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "vpm.blocks.3.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "vpm.blocks.3.norm1.bias": "model-00002-of-00002.safetensors",
+    "vpm.blocks.3.norm1.weight": "model-00002-of-00002.safetensors",
+    "vpm.blocks.3.norm2.bias": "model-00002-of-00002.safetensors",
+    "vpm.blocks.3.norm2.weight": "model-00002-of-00002.safetensors",
+    "vpm.blocks.4.attn.proj.bias": "model-00002-of-00002.safetensors",
+    "vpm.blocks.4.attn.proj.weight": "model-00002-of-00002.safetensors",
+    "vpm.blocks.4.attn.qkv.bias": "model-00002-of-00002.safetensors",
+    "vpm.blocks.4.attn.qkv.weight": "model-00002-of-00002.safetensors",
+    "vpm.blocks.4.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "vpm.blocks.4.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "vpm.blocks.4.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "vpm.blocks.4.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "vpm.blocks.4.norm1.bias": "model-00002-of-00002.safetensors",
+    "vpm.blocks.4.norm1.weight": "model-00002-of-00002.safetensors",
+    "vpm.blocks.4.norm2.bias": "model-00002-of-00002.safetensors",
+    "vpm.blocks.4.norm2.weight": "model-00002-of-00002.safetensors",
+    "vpm.blocks.5.attn.proj.bias": "model-00002-of-00002.safetensors",
+    "vpm.blocks.5.attn.proj.weight": "model-00002-of-00002.safetensors",
+    "vpm.blocks.5.attn.qkv.bias": "model-00002-of-00002.safetensors",
+    "vpm.blocks.5.attn.qkv.weight": "model-00002-of-00002.safetensors",
+    "vpm.blocks.5.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "vpm.blocks.5.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "vpm.blocks.5.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "vpm.blocks.5.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "vpm.blocks.5.norm1.bias": "model-00002-of-00002.safetensors",
+    "vpm.blocks.5.norm1.weight": "model-00002-of-00002.safetensors",
+    "vpm.blocks.5.norm2.bias": "model-00002-of-00002.safetensors",
+    "vpm.blocks.5.norm2.weight": "model-00002-of-00002.safetensors",
+    "vpm.blocks.6.attn.proj.bias": "model-00002-of-00002.safetensors",
+    "vpm.blocks.6.attn.proj.weight": "model-00002-of-00002.safetensors",
+    "vpm.blocks.6.attn.qkv.bias": "model-00002-of-00002.safetensors",
+    "vpm.blocks.6.attn.qkv.weight": "model-00002-of-00002.safetensors",
+    "vpm.blocks.6.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "vpm.blocks.6.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "vpm.blocks.6.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "vpm.blocks.6.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "vpm.blocks.6.norm1.bias": "model-00002-of-00002.safetensors",
+    "vpm.blocks.6.norm1.weight": "model-00002-of-00002.safetensors",
+    "vpm.blocks.6.norm2.bias": "model-00002-of-00002.safetensors",
+    "vpm.blocks.6.norm2.weight": "model-00002-of-00002.safetensors",
+    "vpm.blocks.7.attn.proj.bias": "model-00002-of-00002.safetensors",
+    "vpm.blocks.7.attn.proj.weight": "model-00002-of-00002.safetensors",
+    "vpm.blocks.7.attn.qkv.bias": "model-00002-of-00002.safetensors",
+    "vpm.blocks.7.attn.qkv.weight": "model-00002-of-00002.safetensors",
+    "vpm.blocks.7.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "vpm.blocks.7.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "vpm.blocks.7.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "vpm.blocks.7.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "vpm.blocks.7.norm1.bias": "model-00002-of-00002.safetensors",
+    "vpm.blocks.7.norm1.weight": "model-00002-of-00002.safetensors",
+    "vpm.blocks.7.norm2.bias": "model-00002-of-00002.safetensors",
+    "vpm.blocks.7.norm2.weight": "model-00002-of-00002.safetensors",
+    "vpm.blocks.8.attn.proj.bias": "model-00002-of-00002.safetensors",
+    "vpm.blocks.8.attn.proj.weight": "model-00002-of-00002.safetensors",
+    "vpm.blocks.8.attn.qkv.bias": "model-00002-of-00002.safetensors",
+    "vpm.blocks.8.attn.qkv.weight": "model-00002-of-00002.safetensors",
+    "vpm.blocks.8.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "vpm.blocks.8.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "vpm.blocks.8.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "vpm.blocks.8.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "vpm.blocks.8.norm1.bias": "model-00002-of-00002.safetensors",
+    "vpm.blocks.8.norm1.weight": "model-00002-of-00002.safetensors",
+    "vpm.blocks.8.norm2.bias": "model-00002-of-00002.safetensors",
+    "vpm.blocks.8.norm2.weight": "model-00002-of-00002.safetensors",
+    "vpm.blocks.9.attn.proj.bias": "model-00002-of-00002.safetensors",
+    "vpm.blocks.9.attn.proj.weight": "model-00002-of-00002.safetensors",
+    "vpm.blocks.9.attn.qkv.bias": "model-00002-of-00002.safetensors",
+    "vpm.blocks.9.attn.qkv.weight": "model-00002-of-00002.safetensors",
+    "vpm.blocks.9.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "vpm.blocks.9.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "vpm.blocks.9.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "vpm.blocks.9.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "vpm.blocks.9.norm1.bias": "model-00002-of-00002.safetensors",
+    "vpm.blocks.9.norm1.weight": "model-00002-of-00002.safetensors",
+    "vpm.blocks.9.norm2.bias": "model-00002-of-00002.safetensors",
+    "vpm.blocks.9.norm2.weight": "model-00002-of-00002.safetensors",
+    "vpm.norm.bias": "model-00002-of-00002.safetensors",
+    "vpm.norm.weight": "model-00002-of-00002.safetensors",
+    "vpm.patch_embed.proj.bias": "model-00002-of-00002.safetensors",
+    "vpm.patch_embed.proj.weight": "model-00002-of-00002.safetensors",
+    "vpm.pos_embed": "model-00002-of-00002.safetensors"
+  }
+}