Upload merged VLM (LLM + Vision Tower + Projector)

.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

chat_template.jinja

@@ -0,0 +1 @@
+{% for message in messages %}{% if message['role'] == 'user' %}{{ '\n\n### 指示:\n' + message['content'] }}{% elif message['role'] == 'system' %}{{ '以下は、タスクを説明する指示です。要求を適切に満たす応答を書きなさい。' }}{% elif message['role'] == 'assistant' %}{{ '\n\n### 応答:\n' + message['content'] + eos_token }}{% endif %}{% if loop.last and add_generation_prompt %}{{ '\n\n### 応答:\n' }}{% endif %}{% endfor %}

config.json

@@ -0,0 +1,32 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "dtype": "bfloat16",
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 4096,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pad_token_id": null,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_parameters": {
+    "rope_theta": 500000,
+    "rope_type": "default"
+  },
+  "tie_word_embeddings": false,
+  "transformers_version": "5.2.0",
+  "use_cache": true,
+  "vocab_size": 196610
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "5.2.0"
+}

image_newline.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85e690f2df4fb3d088126461be5ea4878158a2c5831c6c8cf2fb9aeb04b5c772
+size 17594

mm_projector.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0bd33f96f6c4e6d9d538020df0d27a75b2f641da96bc0963f7ff58d53202bb5
+size 43010232

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ae2e3b988815ad9f172f3d1c08f93d853527392d7e5055bc6b145e43fc58fb6
+size 17180468600

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:842b33fbab6e4610e177c7e9afcad2592c7932fcc488a2afaf81b1b94fd2bd1b
+size 12869165

tokenizer_config.json

@@ -0,0 +1,31 @@
+{
+  "backend": "tokenizers",
+  "bos_token": "<|bos|>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<|cls|>",
+  "eod_token": "<|eod|>",
+  "eos_token": "<|eos|>",
+  "extra_ids": 0,
+  "extra_special_tokens": [
+    "<image>",
+    "</image>"
+  ],
+  "is_local": true,
+  "mask_token": "<|mask|>",
+  "max_length": null,
+  "model_max_length": 1000000000000000019884624838656,
+  "model_specific_special_tokens": {
+    "eod_token": "<|eod|>"
+  },
+  "pad_to_multiple_of": null,
+  "pad_token": "<|pad|>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "<|sep|>",
+  "sp_model_kwargs": {},
+  "stride": 0,
+  "tokenizer_class": "TokenizersBackend",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<|unk|>"
+}

vision_tower/config.json

@@ -0,0 +1,40 @@
+{
+  "architectures": [
+    "SiglipModel"
+  ],
+  "dtype": "bfloat16",
+  "initializer_factor": 1.0,
+  "model_type": "siglip",
+  "text_config": {
+    "attention_dropout": 0.0,
+    "bos_token_id": 49406,
+    "dtype": "bfloat16",
+    "eos_token_id": 49407,
+    "hidden_act": "gelu_pytorch_tanh",
+    "hidden_size": 1152,
+    "intermediate_size": 4304,
+    "layer_norm_eps": 1e-06,
+    "max_position_embeddings": 64,
+    "model_type": "siglip_text_model",
+    "num_attention_heads": 16,
+    "num_hidden_layers": 27,
+    "pad_token_id": 1,
+    "projection_size": 1152,
+    "vocab_size": 256000
+  },
+  "transformers_version": "5.2.0",
+  "vision_config": {
+    "attention_dropout": 0.0,
+    "dtype": "bfloat16",
+    "hidden_act": "gelu_pytorch_tanh",
+    "hidden_size": 1152,
+    "image_size": 384,
+    "intermediate_size": 4304,
+    "layer_norm_eps": 1e-06,
+    "model_type": "siglip_vision_model",
+    "num_attention_heads": 16,
+    "num_channels": 3,
+    "num_hidden_layers": 27,
+    "patch_size": 14
+  }
+}

vision_tower/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c61702b1e68ee065dabecd86ac50e8ad2f608f2a62a6878159b121a6a72e2bb6
+size 2272126532

vlm_config.json

@@ -0,0 +1,11 @@
+{
+  "vision_hidden_size": 1152,
+  "llm_hidden_size": 4096,
+  "use_s2_wrapper": false,
+  "use_anyres": false,
+  "num_anyres_crops": 9,
+  "anyres_max_grid_tiles": 9,
+  "freeze_vision_tower": false,
+  "freeze_llm": false,
+  "use_lora": true
+}