Upload folder using huggingface_hub

added_tokens.json

@@ -0,0 +1,40 @@
+{
+  "</bbox>": 151677,
+  "</char>": 151673,
+  "</obj>": 151675,
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<bbox>": 151676,
+  "<char>": 151672,
+  "<delim>": 151678,
+  "<gro>": 151670,
+  "<image>": 151679,
+  "<obj>": 151674,
+  "<ocr>": 151671,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<video>": 151680,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652,
+  "[UNK]": 151669
+}

chat_template.jinja

@@ -1 +1,10 @@
-{% if messages[0]['role'] == 'system' %}{{'<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n'}}{% else %}{{'<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n'}}{% endif %}{% for message in messages %}{% if message['role'] == 'user' or message['role'] == 'system' and not loop.first or message['role'] == 'assistant' %}{{'<|im_start|>' + message['role'] + '\n'}}{# Render all images first #}{% for content in message['content'] | selectattr('type', 'equalto', 'image') %}{{ '<image>\n' }}{% endfor %}{# Render all video then #}{% for content in message['content'] | selectattr('type', 'equalto', 'video') %}{{ '<video>\n' }}{% endfor %}{# Render all text next #}{% if message['role'] != 'assistant' %}{% for content in message['content'] | selectattr('type', 'equalto', 'text') %}{{ content['text'] }}{% endfor %}{% else %}{% for content in message['content'] | selectattr('type', 'equalto', 'text') %}{% generation %}{{ content['text'] }}{% endgeneration %}{% endfor %}{% endif %}{{'<|im_end|>' + '\n'}}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}
+{% if messages[0]['role'] == 'system' %}{{'<|im_start|>system
+' + messages[0]['content'] + '<|im_end|>
+'}}{% else %}{{'<|im_start|>system
+You are VARCO-VISION, created by NC AI. You are a helpful assistant.<|im_end|>
+'}}{% endif %}{% for message in messages %}{% if message['role'] == 'user' or message['role'] == 'system' and not loop.first or message['role'] == 'assistant' %}{{'<|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') %}{{ content['text'] }}{% endfor %}{% else %}{% for content in message['content'] | selectattr('type', 'equalto', 'text') %}{% generation %}{{ content['text'] }}{% endgeneration %}{% endfor %}{% endif %}{{'<|im_end|>' + '
+'}}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
+' }}{% endif %}

generation_config.json

@@ -2,6 +2,5 @@
   "_from_model_config": true,
   "bos_token_id": 151643,
   "eos_token_id": 151645,
-  "transformers_version": "4.52.4",
-  "use_cache": false
+  "transformers_version": "4.53.1"
 }

model-00001-of-00007.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a940e57cae456a0bac7b3190b98a26bc9dd1645fb314a9216edd137815932b34
-size 4972969200
+oid sha256:ce55d54e06c4c745b6ca7b48a13ce1af630e8303e11ef1fe25befe94db7b2a1a
+size 4877307920

model-00002-of-00007.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81eb0fc125f253200a5bfab214528a8cabde4db56326da27ce1ede44a43cdefe
-size 4917989656
+oid sha256:005b8436d9b7c57fef79eefbac03e945d9afd2ca4a7b8c63fff4ba33ab52dd8d
+size 4928486224

model-00003-of-00007.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:21317351c7fb2118fa8f7cb3c6a1f2fe3cdd0a37b3def5e3fd99b04baa2d6631
-size 4991389856
+oid sha256:e9ea2dc9fe8f114859e1aac3f2b1478df97bc8199e3001f9c2d564859ea78951
+size 4980893216

model-00004-of-00007.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a0667c87945df19afac5a810536d63b8703a60dc13996809df75a5dc0b80aee6
-size 4917989648
+oid sha256:9873132aed98e8846be9eeef755ab0e37d09ce4f9d941f1145da66450f696427
+size 4928486304

model-00005-of-00007.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ad8d93739b2f42ec501cd251c15daf478afac0e02fc7d088a914e48ca72b2f0
-size 4991389864
+oid sha256:7dd09186aa7a17806409117686f804e8b99a20ff5eb00f95c536259446de937c
+size 4980893216

model-00006-of-00007.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:449903cafa5ee84ba85a7ede77e2e438a3e772e59fd6af8da5a828d2fddac755
-size 4999901720
+oid sha256:13ff9bae2e0c4db6167461eb9bd46c8b409c5d11f61eac3be284c0267be59aae
+size 4142040936

model-00007-of-00007.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7570475431596713193ac2affde6f7e3ccac654abe02582b761783ea0005a5da
-size 599690752
+oid sha256:1faa9c4b807b278b13c14ea8202bc0d248dcb0cc7df2f7f00664170867088bab
+size 1553213584

tokenizer_config.json

@@ -289,6 +289,22 @@
       "rstrip": false,
       "single_word": false,
       "special": true
+    },
+    "151679": {
+      "content": "<image>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151680": {
+      "content": "<video>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
     }
   },
   "additional_special_tokens": [
@@ -307,9 +323,10 @@
   "eos_token": "<|im_end|>",
   "errors": "replace",
   "extra_special_tokens": {},
-  "model_max_length": 9216,
+  "model_max_length": 16384,
   "pad_token": "[UNK]",
   "padding_side": "right",
+  "processor_class": "LlavaOnevisionProcessor",
   "split_special_tokens": false,
   "tokenizer_class": "Qwen2Tokenizer",
   "unk_token": "[UNK]"