Upload 12 files

added_tokens.json

@@ -0,0 +1,17 @@
+{
+  "<bx_end>": 32013,
+  "<bx_start>": 32012,
+  "<im_patch>": 32011,
+  "<|assistant|>": 32001,
+  "<|endoftext|>": 32000,
+  "<|end|>": 32007,
+  "<|placeholder1|>": 32002,
+  "<|placeholder2|>": 32003,
+  "<|placeholder3|>": 32004,
+  "<|placeholder4|>": 32005,
+  "<|placeholder5|>": 32008,
+  "<|placeholder6|>": 32009,
+  "<|system|>": 32006,
+  "<|user|>": 32010,
+  "[SEG]": 32014
+}

config.json

@@ -0,0 +1,57 @@
+{
+  "_name_or_path": "microsoft/Phi-3-mini-4k-instruct",
+  "architectures": [
+    "LamedPhi3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "auto_map": {
+    "AutoConfig": "microsoft/Phi-3-mini-4k-instruct--configuration_phi3.Phi3Config",
+    "AutoModelForCausalLM": "microsoft/Phi-3-mini-4k-instruct--modeling_phi3.Phi3ForCausalLM"
+  },
+  "bos_token_id": 1,
+  "embd_pdrop": 0.0,
+  "eos_token_id": 32000,
+  "hidden_act": "silu",
+  "hidden_size": 3072,
+  "image_channel": 1,
+  "image_size": [
+    32,
+    256,
+    256
+  ],
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "max_position_embeddings": 4096,
+  "mm_hidden_size": 768,
+  "mm_projector_type": "spp",
+  "model_type": "lamed_phi3",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "original_max_position_embeddings": 4096,
+  "pad_token_id": 32000,
+  "patch_size": [
+    4,
+    16,
+    16
+  ],
+  "proj_layer_num": 2,
+  "proj_layer_type": "mlp",
+  "proj_pooling_size": 2,
+  "proj_pooling_type": "spatial",
+  "resid_pdrop": 0.0,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "seg_token_id": 32014,
+  "sliding_window": 2047,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.43.0.dev0",
+  "use_cache": true,
+  "vision_select_feature": "patch",
+  "vision_select_layer": -1,
+  "vision_tower": "vit3d",
+  "vocab_size": 32015
+}

generation_config.json

@@ -0,0 +1,11 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": [
+    32000,
+    32001,
+    32007
+  ],
+  "pad_token_id": 32000,
+  "transformers_version": "4.43.0.dev0"
+}

merged_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ebcb0a6d7b7de318693d085b7bb13dba23448df39243225e93abc1a719a6add2
+size 15680033681

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:344fedb072119ec5639c8cee712d611851a6195c4f2acff9695c6e3b65f3918c
+size 4961250304

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ede843c593b5787cf6b782a391d26f20a98e776e923be327a7fc35e7d20e6ed
+size 4983111176

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa495fb0f778487f13805258d7747413614f4ba89544c712c98178598ab7d601
+size 4992612024

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:084080a35704e7875fea6d4c0a7a8c7d95c9f11ec72636695001fa3ac2989a4a
+size 742948496

model.safetensors.index.json

@@ -0,0 +1,344 @@
+{
+  "metadata": {
+    "total_size": 15679881216
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.qkv_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.qkv_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.self_attn.qkv_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.qkv_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.qkv_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.qkv_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.qkv_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.qkv_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.qkv_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.qkv_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.qkv_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.qkv_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.qkv_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.qkv_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.qkv_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.qkv_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.qkv_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.qkv_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.qkv_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.qkv_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.qkv_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.qkv_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.qkv_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.qkv_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.qkv_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.qkv_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.qkv_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.gate_up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.qkv_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.gate_up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.qkv_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.gate_up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.qkv_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.gate_up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.qkv_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.mlp.gate_up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.qkv_proj.weight": "model-00001-of-00004.safetensors",
+    "model.mm_projector.projector.0.bias": "model-00004-of-00004.safetensors",
+    "model.mm_projector.projector.0.weight": "model-00004-of-00004.safetensors",
+    "model.mm_projector.projector.2.bias": "model-00004-of-00004.safetensors",
+    "model.mm_projector.projector.2.weight": "model-00004-of-00004.safetensors",
+    "model.norm.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.0.attn.out_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.0.attn.out_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.0.attn.qkv.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.0.mlp.linear1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.0.mlp.linear1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.0.mlp.linear2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.0.mlp.linear2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.0.norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.0.norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.0.norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.0.norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.1.attn.out_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.1.attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.1.attn.qkv.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.1.mlp.linear1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.1.mlp.linear1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.1.mlp.linear2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.1.mlp.linear2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.1.norm1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.1.norm1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.1.norm2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.1.norm2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.10.attn.out_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.10.attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.10.attn.qkv.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.10.mlp.linear1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.10.mlp.linear1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.10.mlp.linear2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.10.mlp.linear2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.10.norm1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.10.norm1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.10.norm2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.10.norm2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.11.attn.out_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.11.attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.11.attn.qkv.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.11.mlp.linear1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.11.mlp.linear1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.11.mlp.linear2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.11.mlp.linear2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.11.norm1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.11.norm1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.11.norm2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.11.norm2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.attn.out_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.attn.qkv.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.mlp.linear1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.mlp.linear1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.mlp.linear2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.mlp.linear2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.norm1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.norm1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.norm2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.2.norm2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.3.attn.out_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.3.attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.3.attn.qkv.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.3.mlp.linear1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.3.mlp.linear1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.3.mlp.linear2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.3.mlp.linear2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.3.norm1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.3.norm1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.3.norm2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.3.norm2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.4.attn.out_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.4.attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.4.attn.qkv.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.4.mlp.linear1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.4.mlp.linear1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.4.mlp.linear2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.4.mlp.linear2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.4.norm1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.4.norm1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.4.norm2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.4.norm2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.5.attn.out_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.5.attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.5.attn.qkv.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.5.mlp.linear1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.5.mlp.linear1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.5.mlp.linear2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.5.mlp.linear2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.5.norm1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.5.norm1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.5.norm2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.5.norm2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.6.attn.out_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.6.attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.6.attn.qkv.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.6.mlp.linear1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.6.mlp.linear1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.6.mlp.linear2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.6.mlp.linear2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.6.norm1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.6.norm1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.6.norm2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.6.norm2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.7.attn.out_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.7.attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.7.attn.qkv.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.7.mlp.linear1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.7.mlp.linear1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.7.mlp.linear2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.7.mlp.linear2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.7.norm1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.7.norm1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.7.norm2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.7.norm2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.8.attn.out_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.8.attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.8.attn.qkv.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.8.mlp.linear1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.8.mlp.linear1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.8.mlp.linear2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.8.mlp.linear2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.8.norm1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.8.norm1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.8.norm2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.8.norm2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.9.attn.out_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.9.attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.9.attn.qkv.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.9.mlp.linear1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.9.mlp.linear1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.9.mlp.linear2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.9.mlp.linear2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.9.norm1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.9.norm1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.9.norm2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.blocks.9.norm2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.cls_token": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.norm.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.norm.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.patch_embedding.patch_embeddings.1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.patch_embedding.patch_embeddings.1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.patch_embedding.position_embeddings": "model-00003-of-00004.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,53 @@
+{
+  "additional_special_tokens": [
+    {
+      "content": "<im_patch>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<bx_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<bx_end>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

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

tokenizer_config.json

@@ -0,0 +1,169 @@
+{
+  "add_bos_token": false,
+  "add_eos_token": false,
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "32000": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "<|assistant|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32002": {
+      "content": "<|placeholder1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32003": {
+      "content": "<|placeholder2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32004": {
+      "content": "<|placeholder3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32005": {
+      "content": "<|placeholder4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32006": {
+      "content": "<|system|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32007": {
+      "content": "<|end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32008": {
+      "content": "<|placeholder5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32009": {
+      "content": "<|placeholder6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32010": {
+      "content": "<|user|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32011": {
+      "content": "<im_patch>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32012": {
+      "content": "<bx_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32013": {
+      "content": "<bx_end>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32014": {
+      "content": "[SEG]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<im_patch>",
+    "<bx_start>",
+    "<bx_end>"
+  ],
+  "bos_token": "<s>",
+  "chat_template": "{% for message in messages %}{% if message['role'] == 'system' %}{{'<|system|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'user' %}{{'<|user|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'assistant' %}{{'<|assistant|>\n' + message['content'] + '<|end|>\n'}}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>\n' }}{% else %}{{ eos_token }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "legacy": false,
+  "model_max_length": 4096,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}