Add files using upload-large-folder tool

.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.json

@@ -0,0 +1,3 @@
+{
+  "chat_template": "{{ bos_token }}<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|>You are Aya Vision, a brilliant, sophisticated, AI-assistant chatbot trained to assist human users by providing thorough responses. You are a large vision language model built by the Cohere For AI. You are capable of interpreting images, including describing them, answering questions about their contents, extracting textual information, and analyzing visual context.<|END_OF_TURN_TOKEN|>\n{%- for message in messages -%}\n    <|START_OF_TURN_TOKEN|>{{ message.role | replace(\"user\", \"<|USER_TOKEN|>\") | replace(\"assistant\", \"<|CHATBOT_TOKEN|><|START_RESPONSE|>\") | replace(\"system\", \"<|SYSTEM_TOKEN|>\") }}\n    {%- if message.content is defined -%}\n        {%- if message.content is string -%}\n{{ message.content }}\n        {%- else -%}\n            {%- for item in message.content | selectattr('type', 'equalto', 'image') -%}\n<image>\n            {%- endfor -%}\n            {%- for item in message.content | selectattr('type', 'equalto', 'text') -%}\n{{ item.text }}\n            {%- endfor -%}\n        {%- endif -%}\n    {%- elif message.message is defined -%}\n        {%- if message.message is string -%}\n{{ message.message }}\n        {%- else -%}\n            {%- for item in message.message | selectattr('type', 'equalto', 'image') -%}\n<image>\n            {%- endfor -%}\n            {%- for item in message.message | selectattr('type', 'equalto', 'text') -%}\n{{ item.text }}\n            {%- endfor -%}\n        {%- endif -%}\n    {%- endif -%}\n    {%- if message.role == \"assistant\" -%}\n<|END_RESPONSE|>\n    {%- endif -%}\n<|END_OF_TURN_TOKEN|>\n{%- endfor -%}\n{%- if add_generation_prompt -%}\n<|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>\n{%- endif -%}\n"
+}

config.json

@@ -0,0 +1,77 @@
+{
+  "adapter_layer_norm_eps": 1e-06,
+  "alignment_activation_fn": "swiglu",
+  "alignment_intermediate_size": 49152,
+  "architectures": [
+    "AyaVisionForConditionalGeneration"
+  ],
+  "bos_token_id": 5,
+  "downsample_factor": 2,
+  "eos_token_id": 255001,
+  "image_token_index": 255022,
+  "max_splits_per_img": 12,
+  "model_type": "aya_vision",
+  "pad_token_id": 0,
+  "projector_hidden_act": "gelu",
+  "quantization_config": {
+    "_load_in_4bit": true,
+    "_load_in_8bit": false,
+    "bnb_4bit_compute_dtype": "bfloat16",
+    "bnb_4bit_quant_storage": "uint8",
+    "bnb_4bit_quant_type": "nf4",
+    "bnb_4bit_use_double_quant": true,
+    "llm_int8_enable_fp32_cpu_offload": false,
+    "llm_int8_has_fp16_weight": false,
+    "llm_int8_skip_modules": [
+      "lm_head",
+      "multi_modal_projector",
+      "merger",
+      "modality_projection"
+    ],
+    "llm_int8_threshold": 6.0,
+    "load_in_4bit": true,
+    "load_in_8bit": false,
+    "quant_method": "bitsandbytes"
+  },
+  "text_config": {
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "hidden_act": "silu",
+    "hidden_size": 8192,
+    "initializer_range": 0.02,
+    "intermediate_size": 24576,
+    "layer_norm_eps": 1e-05,
+    "logit_scale": 0.0625,
+    "max_position_embeddings": 8192,
+    "model_type": "cohere",
+    "num_attention_heads": 64,
+    "num_hidden_layers": 40,
+    "num_key_value_heads": 8,
+    "rope_scaling": null,
+    "rope_theta": 4000000,
+    "torch_dtype": "bfloat16",
+    "use_cache": true,
+    "use_qk_norm": false,
+    "vocab_size": 256000
+  },
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.50.0.dev0",
+  "unsloth_fixed": true,
+  "vision_config": {
+    "attention_dropout": 0.0,
+    "hidden_act": "gelu_pytorch_tanh",
+    "hidden_size": 1152,
+    "image_size": 364,
+    "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,
+    "torch_dtype": "bfloat16",
+    "vision_use_head": false
+  },
+  "vision_feature_layer": -1,
+  "vision_feature_select_strategy": "full"
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 5,
+  "eos_token_id": 255001,
+  "pad_token_id": 0,
+  "transformers_version": "4.50.0.dev0"
+}

model-00001-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7152cee63ccc2f5f6617aeac2f80a6ddfffa4ff23b8674c9c04a13a3c11276a2
+size 1071923074

model-00002-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e9f7b3c4f519ebe12fbcd9b20db4eb57bc02f46d0bc7a36e059d48d5f63aac4
+size 4973302372

model-00003-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc8865e43a28abb69e604335c9ab8fcb4a2ff759299c60cc575a6bc6ec35cf4c
+size 4959612110

model-00004-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d50e3970a9a9451b14d6bb8451608fd162cfdd6b4aac81e308f615e9912c2d6
+size 4959628980

model-00005-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ab3b7ac3278586975df5488c999e7353c521f9b0955494db2e6aa85c5d8ad0e
+size 4881743496

preprocessor_config.json

@@ -0,0 +1,27 @@
+{
+  "crop_to_patches": false,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "GotOcr2ImageProcessor",
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "max_patches": 12,
+  "min_patches": 1,
+  "processor_class": "AyaVisionProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 364,
+    "width": 364
+  }
+}

processor_config.json

@@ -0,0 +1,13 @@
+{
+  "end_of_img_token": "<|END_OF_IMG|>",
+  "image_token": "<image>",
+  "img_line_break_token": "<|IMG_LINE_BREAK|>",
+  "img_patch_token": "<|IMG_PATCH|>",
+  "img_size": 364,
+  "patch_size": 28,
+  "processor_class": "AyaVisionProcessor",
+  "start_of_img_token": "<|START_OF_IMG|>",
+  "tile_global_token": "TILE_GLOBAL",
+  "tile_token": "TILE",
+  "vision_feature_select_strategy": "full"
+}

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<BOS_TOKEN>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|END_OF_TURN_TOKEN|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<PAD>",
+    "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:dbb2974c7ff2633f0dce4490be28531dca552e3ecfafad7a2dfd0e8b212534fc
+size 20124863

tokenizer_config.json

@@ -0,0 +1,352 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<PAD>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<UNK>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<CLS>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<SEP>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<MASK_TOKEN>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<BOS_TOKEN>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "<EOS_TOKEN>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": "<EOP_TOKEN>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "255000": {
+      "content": "<|START_OF_TURN_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255001": {
+      "content": "<|END_OF_TURN_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "255002": {
+      "content": "<|YES_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255003": {
+      "content": "<|NO_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255004": {
+      "content": "<|GOOD_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255005": {
+      "content": "<|BAD_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255006": {
+      "content": "<|USER_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255007": {
+      "content": "<|CHATBOT_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255008": {
+      "content": "<|SYSTEM_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255009": {
+      "content": "<|USER_0_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255010": {
+      "content": "<|USER_1_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255011": {
+      "content": "<|USER_2_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255012": {
+      "content": "<|USER_3_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255013": {
+      "content": "<|USER_4_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255014": {
+      "content": "<|USER_5_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255015": {
+      "content": "<|USER_6_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255016": {
+      "content": "<|USER_7_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255017": {
+      "content": "<|USER_8_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255018": {
+      "content": "<|USER_9_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255019": {
+      "content": "<|START_OF_IMG|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255020": {
+      "content": "<|END_OF_IMG|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255021": {
+      "content": "<|IMG_LINE_BREAK|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255022": {
+      "content": "<|IMG_PATCH|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255023": {
+      "content": "<|EXTRA_0_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255024": {
+      "content": "<|EXTRA_1_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255025": {
+      "content": "<|EXTRA_2_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255026": {
+      "content": "<|EXTRA_3_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255027": {
+      "content": "<|EXTRA_4_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255028": {
+      "content": "<|EXTRA_5_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255029": {
+      "content": "<|EXTRA_6_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255030": {
+      "content": "<|EXTRA_7_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255031": {
+      "content": "<|EXTRA_8_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255032": {
+      "content": "<|EXTRA_9_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "<BOS_TOKEN>",
+  "chat_template": "{{ bos_token }}<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|>You are Aya Vision, a brilliant, sophisticated, AI-assistant chatbot trained to assist human users by providing thorough responses. You are a large vision language model built by the Cohere For AI. You are capable of interpreting images, including describing them, answering questions about their contents, extracting textual information, and analyzing visual context.<|END_OF_TURN_TOKEN|>\n{%- for message in messages -%}\n    <|START_OF_TURN_TOKEN|>{{ message.role | replace(\"user\", \"<|USER_TOKEN|>\") | replace(\"assistant\", \"<|CHATBOT_TOKEN|><|START_RESPONSE|>\") | replace(\"system\", \"<|SYSTEM_TOKEN|>\") }}\n    {%- if message.content is defined -%}\n        {%- if message.content is string -%}\n{{ message.content }}\n        {%- else -%}\n            {%- for item in message.content | selectattr('type', 'equalto', 'image') -%}\n<image>\n            {%- endfor -%}\n            {%- for item in message.content | selectattr('type', 'equalto', 'text') -%}\n{{ item.text }}\n            {%- endfor -%}\n        {%- endif -%}\n    {%- elif message.message is defined -%}\n        {%- if message.message is string -%}\n{{ message.message }}\n        {%- else -%}\n            {%- for item in message.message | selectattr('type', 'equalto', 'image') -%}\n<image>\n            {%- endfor -%}\n            {%- for item in message.message | selectattr('type', 'equalto', 'text') -%}\n{{ item.text }}\n            {%- endfor -%}\n        {%- endif -%}\n    {%- endif -%}\n    {%- if message.role == \"assistant\" -%}\n<|END_RESPONSE|>\n    {%- endif -%}\n<|END_OF_TURN_TOKEN|>\n{%- endfor -%}\n{%- if add_generation_prompt -%}\n<|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>\n{%- endif -%}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|END_OF_TURN_TOKEN|>",
+  "extra_special_tokens": {},
+  "legacy": true,
+  "merges_file": null,
+  "model_max_length": 16384,
+  "pad_token": "<PAD>",
+  "padding_side": "left",
+  "processor_class": "AyaVisionProcessor",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "CohereTokenizer",
+  "unk_token": null,
+  "use_default_system_prompt": false,
+  "vocab_file": null
+}