Upload 20 files

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

added_tokens.json

@@ -0,0 +1,7 @@
+{
+  "<image>": 151646,
+  "<video>": 151647,
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644
+}

chat_template.json

@@ -0,0 +1,3 @@
+{
+  "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + ' '}}{# Render all images first #}{% for content in message['content'] | selectattr('type', 'equalto', 'image') %}{{ '<image>' }}{% endfor %}{# Render all video then #}{% for content in message['content'] | selectattr('type', 'equalto', 'video') %}{{ '<video>' }}{% endfor %}{# Render all text next #}{% if message['role'] != 'assistant' %}{% for content in message['content'] | selectattr('type', 'equalto', 'text') %}{{ '\n' + content['text'] }}{% endfor %}{% else %}{% for content in message['content'] | selectattr('type', 'equalto', 'text') %}{% generation %}{{ '\n' + content['text'] }}{% endgeneration %}{% endfor %}{% endif %}{{'<|im_end|>'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}"
+}

config.json

@@ -0,0 +1,121 @@
+{
+  "architectures": [
+    "HaploForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "attention_rope": false,
+  "base_config": {
+    "bos_token_id": 151643,
+    "eos_token_id": 151645,
+    "hidden_size": 3584,
+    "intermediate_size": 18944,
+    "model_type": "haplo",
+    "num_attention_heads": 28,
+    "num_hidden_layers": 28,
+    "num_key_value_heads": 4,
+    "rope_theta": 1000000.0,
+    "sliding_window": 131072
+  },
+  "bos_token_id": 151643,
+  "default_image_size": 336,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "image_aspect_ratio": "anyres_max_6",
+  "image_grid_pinpoints": [
+    [
+      336,
+      336
+    ],
+    [
+      336,
+      672
+    ],
+    [
+      336,
+      1008
+    ],
+    [
+      336,
+      1344
+    ],
+    [
+      336,
+      1680
+    ],
+    [
+      336,
+      2016
+    ],
+    [
+      672,
+      336
+    ],
+    [
+      672,
+      672
+    ],
+    [
+      672,
+      1008
+    ],
+    [
+      1008,
+      336
+    ],
+    [
+      1008,
+      672
+    ],
+    [
+      1344,
+      336
+    ],
+    [
+      1680,
+      336
+    ],
+    [
+      2016,
+      336
+    ]
+  ],
+  "image_newline": true,
+  "image_token_index": 151646,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "haplo",
+  "norm_mode": "rmsnorm",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "patch_size": 14,
+  "post_config": {
+    "model_type": "haplo"
+  },
+  "pre_config": {
+    "attention_rope": true,
+    "hidden_act": "gelu",
+    "hidden_size": 1024,
+    "intermediate_size": 4096,
+    "model_type": "haplo",
+    "norm_mode": "layernorm",
+    "num_attention_heads": 16,
+    "num_hidden_layers": 24,
+    "num_key_value_heads": 16,
+    "rope_theta": 1000000.0
+  },
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": 131072,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.49.0",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "video_token_index": 151647,
+  "vocab_size": 152064
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "transformers_version": "4.49.0"
+}

model-00001-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81a11f718f8a912f86bead2e1868e94447c09ad4780a853fba9d6abf5b292c46
+size 4801066272

model-00002-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76f6c32d9583b5cf3d05b48dde6125bed0f55539e82221fdac8152fe748ac2c8
+size 4933723136

model-00003-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e6d907860aa05193e591ef0bca3a23305c94f584a0a819122c5289f03c20bf8
+size 4999769992

model-00004-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f13bb25d5d743849133aee7a94e7ecd0bc19355b2736f7d22a19ab647b135574
+size 4985117920

model-00005-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a4a1186b9b9cff23d110bc6ed48a2276071646507eba6aba42fd456d6f69132
+size 4933723136

model-00006-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4320641b70999fee7a8301503a3c6a45d1621a4bddef83b9f41a9edc7fb6d6c
+size 3708830016

model-00007-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07a6cc232f7b7b36a213c5c1151f7afecfc4002de6e51b0e997c05e253506e71
+size 2179989632

model.safetensors.index.json

@@ -0,0 +1,896 @@
+{
+  "metadata": {
+    "total_size": 30542120960
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00007-of-00007.safetensors",
+    "model.embed_tokens.weight": "model-00006-of-00007.safetensors",
+    "model.image_newline": "model-00001-of-00007.safetensors",
+    "model.layers.0.input_layernorm.bias": "model-00001-of-00007.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.mlp.down_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.mlp.gate_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.mlp.up_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.post_attention_layernorm.bias": "model-00001-of-00007.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.o_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.input_layernorm.bias": "model-00001-of-00007.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.mlp.down_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.mlp.gate_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.mlp.up_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.post_attention_layernorm.bias": "model-00001-of-00007.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.o_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.10.input_layernorm.bias": "model-00001-of-00007.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.10.mlp.down_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.10.mlp.gate_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.10.mlp.up_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.10.post_attention_layernorm.bias": "model-00001-of-00007.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.10.self_attn.o_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.11.input_layernorm.bias": "model-00001-of-00007.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.11.mlp.down_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.11.mlp.gate_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.11.mlp.up_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.11.post_attention_layernorm.bias": "model-00001-of-00007.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.11.self_attn.o_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.12.input_layernorm.bias": "model-00001-of-00007.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.12.mlp.down_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.12.mlp.gate_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.12.mlp.up_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.12.post_attention_layernorm.bias": "model-00001-of-00007.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.12.self_attn.o_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.13.input_layernorm.bias": "model-00001-of-00007.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.13.mlp.down_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.13.mlp.gate_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.13.mlp.up_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.13.post_attention_layernorm.bias": "model-00001-of-00007.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.13.self_attn.o_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.14.input_layernorm.bias": "model-00001-of-00007.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.14.mlp.down_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.14.mlp.gate_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.14.mlp.up_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.14.post_attention_layernorm.bias": "model-00001-of-00007.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.14.self_attn.o_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.15.input_layernorm.bias": "model-00001-of-00007.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.15.mlp.down_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.15.mlp.gate_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.15.mlp.up_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.15.post_attention_layernorm.bias": "model-00001-of-00007.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.15.self_attn.o_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.16.input_layernorm.bias": "model-00001-of-00007.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.16.mlp.down_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.16.mlp.gate_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.16.mlp.up_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.16.post_attention_layernorm.bias": "model-00001-of-00007.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.16.self_attn.o_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.17.input_layernorm.bias": "model-00001-of-00007.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.17.mlp.down_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.17.mlp.gate_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.17.mlp.up_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.17.post_attention_layernorm.bias": "model-00001-of-00007.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.17.self_attn.o_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.18.input_layernorm.bias": "model-00001-of-00007.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.18.mlp.down_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.18.mlp.gate_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.18.mlp.up_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.18.post_attention_layernorm.bias": "model-00001-of-00007.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.18.self_attn.o_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.19.input_layernorm.bias": "model-00001-of-00007.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.19.mlp.down_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.19.mlp.gate_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.19.mlp.up_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.19.post_attention_layernorm.bias": "model-00001-of-00007.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.19.self_attn.o_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.input_layernorm.bias": "model-00001-of-00007.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.mlp.down_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.mlp.gate_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.mlp.up_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.post_attention_layernorm.bias": "model-00001-of-00007.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.o_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.20.input_layernorm.bias": "model-00001-of-00007.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.20.mlp.down_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.20.mlp.gate_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.20.mlp.up_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.20.post_attention_layernorm.bias": "model-00001-of-00007.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.20.self_attn.o_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.21.input_layernorm.bias": "model-00001-of-00007.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.21.mlp.down_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.21.mlp.gate_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.21.mlp.up_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.21.post_attention_layernorm.bias": "model-00001-of-00007.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.21.self_attn.o_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.22.input_layernorm.bias": "model-00001-of-00007.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.22.mlp.down_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.22.mlp.gate_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.22.mlp.up_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.22.post_attention_layernorm.bias": "model-00001-of-00007.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.22.self_attn.o_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.23.input_layernorm.bias": "model-00001-of-00007.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.23.mlp.down_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.23.mlp.gate_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.23.mlp.up_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.23.post_attention_layernorm.bias": "model-00001-of-00007.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.23.self_attn.o_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.24.mlp.down_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.24.mlp.gate_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.24.mlp.up_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.24.self_attn.o_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.25.mlp.down_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.25.mlp.gate_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.25.mlp.up_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.25.self_attn.o_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.26.mlp.down_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.26.mlp.gate_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.26.mlp.up_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.26.self_attn.o_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.27.mlp.down_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.27.mlp.gate_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.27.mlp.up_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.27.self_attn.o_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.28.mlp.down_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.28.mlp.gate_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.28.mlp.up_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.28.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.28.self_attn.o_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.28.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.28.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.29.mlp.down_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.29.mlp.gate_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.29.mlp.up_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.29.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.29.self_attn.o_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.29.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.29.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.input_layernorm.bias": "model-00001-of-00007.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.3.mlp.down_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.3.mlp.gate_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.3.mlp.up_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.3.post_attention_layernorm.bias": "model-00001-of-00007.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.3.self_attn.o_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.30.mlp.down_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.30.mlp.gate_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.30.mlp.up_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.30.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.30.self_attn.o_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.30.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.30.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.31.mlp.down_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.31.mlp.gate_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.31.mlp.up_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.31.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.31.self_attn.o_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.31.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.31.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.32.mlp.down_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.32.mlp.gate_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.32.mlp.up_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.32.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.32.self_attn.o_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.32.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.32.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.33.mlp.down_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.33.mlp.gate_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.33.mlp.up_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.33.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.33.self_attn.o_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.33.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.33.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.34.mlp.down_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.34.mlp.gate_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.34.mlp.up_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.34.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.34.self_attn.o_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.34.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.34.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.35.mlp.down_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.35.mlp.gate_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.35.mlp.up_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.35.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.35.self_attn.o_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.35.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.35.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.36.mlp.down_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.36.mlp.gate_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.36.mlp.up_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.36.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.36.self_attn.o_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.36.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.36.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.37.mlp.down_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.37.mlp.gate_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.37.mlp.up_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.37.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.37.self_attn.o_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.37.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.37.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.38.mlp.down_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.38.mlp.gate_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.38.mlp.up_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.38.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.38.self_attn.o_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.38.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.38.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.39.mlp.down_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.39.mlp.gate_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.39.mlp.up_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.39.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.39.self_attn.o_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.39.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.39.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.4.input_layernorm.bias": "model-00001-of-00007.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.4.mlp.down_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.4.mlp.gate_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.4.mlp.up_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.4.post_attention_layernorm.bias": "model-00001-of-00007.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.4.self_attn.o_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.40.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.40.mlp.down_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.40.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.40.mlp.gate_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.40.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.40.mlp.up_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.40.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.40.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.40.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.40.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.40.self_attn.o_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.40.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.40.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.40.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.40.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.40.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.41.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.41.mlp.down_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.41.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.41.mlp.gate_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.41.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.41.mlp.up_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.41.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.41.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.41.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.41.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.41.self_attn.o_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.41.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.41.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.41.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.41.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.41.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.42.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.42.mlp.down_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.42.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.42.mlp.gate_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.42.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.42.mlp.up_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.42.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.42.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.42.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.42.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.42.self_attn.o_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.42.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.42.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.42.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.42.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.42.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.43.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.43.mlp.down_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.43.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.43.mlp.gate_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.43.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.43.mlp.up_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.43.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.43.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.43.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.43.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.43.self_attn.o_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.43.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.43.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.43.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.43.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.43.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.44.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.44.mlp.down_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.44.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.44.mlp.gate_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.44.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.44.mlp.up_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.44.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.44.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.44.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.44.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.44.self_attn.o_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.44.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.44.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.44.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.44.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.44.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.45.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.45.mlp.down_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.45.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.45.mlp.gate_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.45.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.45.mlp.up_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.45.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.45.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.45.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.45.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.45.self_attn.o_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.45.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.45.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.45.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.45.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.45.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.46.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.46.mlp.down_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.46.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.46.mlp.gate_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.46.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.46.mlp.up_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.46.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.46.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.46.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.46.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.46.self_attn.o_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.46.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.46.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.46.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.46.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.46.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.47.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.47.mlp.down_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.47.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.47.mlp.gate_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.47.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.47.mlp.up_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.47.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.47.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.47.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.47.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.47.self_attn.o_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.47.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.47.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.47.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.47.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.47.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.48.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.48.mlp.down_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.48.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.48.mlp.gate_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.48.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.48.mlp.up_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.48.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.48.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.48.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.48.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.48.self_attn.o_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.48.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.48.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.48.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.48.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.48.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.49.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.49.mlp.down_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.49.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.49.mlp.gate_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.49.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.49.mlp.up_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.49.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.49.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.49.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.49.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.49.self_attn.o_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.49.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.49.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.49.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.49.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.49.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.5.input_layernorm.bias": "model-00001-of-00007.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.5.mlp.down_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.5.mlp.gate_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.5.mlp.up_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.5.post_attention_layernorm.bias": "model-00001-of-00007.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.5.self_attn.o_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.50.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.50.mlp.down_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.50.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.50.mlp.gate_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.50.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.50.mlp.up_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.50.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.50.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.50.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.50.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.50.self_attn.o_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.50.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.50.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.50.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.50.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.50.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.51.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.51.mlp.down_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.51.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.51.mlp.gate_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.51.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.51.mlp.up_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.51.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.51.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.51.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.51.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.51.self_attn.o_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.51.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.51.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.51.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.51.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.51.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.6.input_layernorm.bias": "model-00001-of-00007.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.6.mlp.down_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.6.mlp.gate_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.6.mlp.up_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.6.post_attention_layernorm.bias": "model-00001-of-00007.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.6.self_attn.o_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.7.input_layernorm.bias": "model-00001-of-00007.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.7.mlp.down_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.7.mlp.gate_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.7.mlp.up_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.7.post_attention_layernorm.bias": "model-00001-of-00007.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.7.self_attn.o_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.8.input_layernorm.bias": "model-00001-of-00007.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.8.mlp.down_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.8.mlp.gate_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.8.mlp.up_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.8.post_attention_layernorm.bias": "model-00001-of-00007.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.8.self_attn.o_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.9.input_layernorm.bias": "model-00001-of-00007.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.9.mlp.down_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.9.mlp.gate_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.9.mlp.up_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.9.post_attention_layernorm.bias": "model-00001-of-00007.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.9.self_attn.o_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.norm.weight": "model-00006-of-00007.safetensors",
+    "model.patch_embed.proj.weight": "model-00006-of-00007.safetensors",
+    "model.pre_connector.weight": "model-00006-of-00007.safetensors",
+    "model.pre_norm.bias": "model-00006-of-00007.safetensors",
+    "model.pre_norm.weight": "model-00006-of-00007.safetensors",
+    "model.pre_pos_embed": "model-00001-of-00007.safetensors"
+  }
+}

preprocessor_config.json

@@ -0,0 +1,83 @@
+{
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_pad": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_grid_pinpoints": [
+    [
+      336,
+      336
+    ],
+    [
+      336,
+      672
+    ],
+    [
+      336,
+      1008
+    ],
+    [
+      336,
+      1344
+    ],
+    [
+      336,
+      1680
+    ],
+    [
+      336,
+      2016
+    ],
+    [
+      672,
+      336
+    ],
+    [
+      672,
+      672
+    ],
+    [
+      672,
+      1008
+    ],
+    [
+      1008,
+      336
+    ],
+    [
+      1008,
+      672
+    ],
+    [
+      1344,
+      336
+    ],
+    [
+      1680,
+      336
+    ],
+    [
+      2016,
+      336
+    ]
+  ],
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "HaploImageProcessor",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "processor_class": "HaploProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 336,
+    "width": 336
+  }
+}

processor_config.json

@@ -0,0 +1,6 @@
+{
+  "image_token": "<image>",
+  "num_image_tokens": 576,
+  "processor_class": "HaploProcessor",
+  "video_token": "<video>"
+}

special_tokens_map.json

@@ -0,0 +1,20 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e09f1889210ae8f16539761f6a6d645641eb8e583d22c6f36c92d253e247887f
+size 11418634

tokenizer_config.json

@@ -0,0 +1,65 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<image>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<video>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "max_length": null,
+  "model_max_length": 131072,
+  "pad_to_multiple_of": null,
+  "pad_token": "<|endoftext|>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "processor_class": "HaploProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

video_processor/preprocessor_config.json

@@ -0,0 +1,23 @@
+{
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "HaploVideoProcessor",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 336,
+    "width": 336
+  }
+}