upload model files

config.json

@@ -0,0 +1,68 @@
+{
+  "architectures": [
+    "MultiModalityCausalLM"
+  ],
+  "language_config": {
+    "hidden_size": 2048,
+    "intermediate_size": 5632,
+    "max_position_embeddings": 16384,
+    "model_type": "llama",
+    "num_attention_heads": 16,
+    "num_hidden_layers": 24,
+    "num_key_value_heads": 16,
+    "torch_dtype": "bfloat16",
+    "vocab_size": 102400
+  },
+  "model_type": "multi_modality",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.38.1",
+  "vision_gen_dec_config": {
+    "cls": "ShallowUViTDecoder",
+    "model_type": "vision_gen_dec",
+    "params": {
+      "block_out_channels": [
+        768
+      ],
+      "elementwise_affine": true,
+      "hidden_size": 2048,
+      "in_channels": 768,
+      "layers_in_middle": 2,
+      "norm_eps": 1e-06,
+      "out_channels": 4,
+      "upsamples": 1,
+      "use_bias": true,
+      "use_mid_block": true
+    }
+  },
+  "vision_gen_enc_config": {
+    "cls": "ShallowUViTEncoder",
+    "model_type": "vision_gen_enc",
+    "params": {
+      "block_out_channels": [
+        768
+      ],
+      "elementwize_affine": true,
+      "hidden_size": 2048,
+      "input_channels": 4,
+      "kernel_size": 2,
+      "layers_in_middle": 2,
+      "norm_eps": 1e-06,
+      "num_extra_tensors": 5,
+      "padding": 0,
+      "stride": 2,
+      "use_bias": true,
+      "use_mid_block": true
+    }
+  },
+  "vision_und_enc_config": {
+    "cls": "CLIPVisionTower",
+    "model_type": "vision_und_enc",
+    "params": {
+      "image_size": 384,
+      "model_name": "siglip_large_patch16_384",
+      "select_feature": "same",
+      "select_layer": -1,
+      "width": 1024
+    }
+  }
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e43167cf7a74edfaed1c35e7450c0e1f8345ff39f825e5372a0dbda8ef77eeb
+size 4092812280

preprocessor_config.json

@@ -0,0 +1,26 @@
+{
+  "background_color": [
+    127,
+    127,
+    127
+  ],
+  "do_normalize": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "VLMImageProcessor",
+  "image_size": 384,
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "interpolate_mode": "bilinear",
+  "max_size": 1536,
+  "min_size": 14,
+  "processor_class": "OmniProcessor",
+  "rescale_factor": 0.00392156862745098,
+  "resize_strategy": "aspect_ratio_pad"
+}

processor_config.json

@@ -0,0 +1,12 @@
+{
+    "add_special_token": false,
+    "ignore_id": -100,
+    "image_end_tag": "<image_end>",
+    "image_tag": "<image_placeholder>",
+    "mask_prompt": true,
+    "num_image_tokens": 576,
+    "processor_class": "VLChatProcessor",
+    "sft_format": "deepseek",
+    "image_gen_tag": "<\uff5cbegin\u2581of\u2581generation\uff5c>",
+    "image_start_tag": "<image_beg>"
+}

special_tokens_map.json

@@ -0,0 +1,25 @@
+{
+  "additional_special_tokens": [
+    {
+      "content": "<｜begin▁of▁generation｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
+  "bos_token": {
+    "content": "<｜begin▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,84 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "100000": {
+      "content": "<｜begin▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100001": {
+      "content": "<｜end▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100002": {
+      "content": "<｜▁pad▁｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100003": {
+      "content": "<image_placeholder>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100004": {
+      "content": "<patch_placeholder>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100005": {
+      "content": "<image_beg>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100006": {
+      "content": "<image_end>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100007": {
+      "content": "<｜begin▁of▁generation｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<｜begin▁of▁generation｜>"
+  ],
+  "bos_token": "<｜begin▁of▁sentence｜>",
+  "chat_template": "{%- set found_item = false -%}\n{%- for message in messages -%}\n    {%- if message['role'] == 'system' -%}\n        {%- set found_item = true -%}\n    {%- endif -%}\n{%- endfor -%}\n{%- if not found_item -%}\n{{'You are an AI programming assistant, utilizing the Deepseek Coder model, developed by Deepseek Company, and you only answer questions related to computer science. For politically sensitive questions, security and privacy issues, and other non-computer science questions, you will refuse to answer.\\n'}}\n{%- endif %}\n{%- for message in messages %}\n    {%- if message['role'] == 'system' %}\n{{ message['content'] }}\n    {%- else %}\n        {%- if message['role'] == 'user' %}\n{{'### Instruction:\\n' + message['content'] + '\\n'}}\n        {%- else %}\n{{'### Response:\\n' + message['content'] + '\\n<|EOT|>\\n'}}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{{'### Response:\\n'}}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<｜end▁of▁sentence｜>",
+  "legacy": true,
+  "model_max_length": 100000000,
+  "processor_class": "OmniProcessor",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": null,
+  "use_default_system_prompt": false
+}