Update tiny models for HunYuanVLVisionTransformer

chat_template.jinja

@@ -0,0 +1 @@
+{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% if messages[0]['content'] is string %}{% set system_message = messages[0]['content'] %}{% else %}{% set system_message = messages[0]['content']['text'] %}{% endif %}<｜hy_begin▁of▁sentence｜>{{ system_message }}<｜hy_place▁holder▁no▁3｜>{% else %}{% set loop_messages = messages %}<｜hy_begin▁of▁sentence｜>{% endif %}{% for message in loop_messages %}{% if message['role'] == 'user' %}{% if message['content'] is string %}{{ message['content'] }}{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}<｜hy_place▁holder▁no▁100｜><｜hy_place▁holder▁no▁102｜><｜hy_place▁holder▁no▁101｜>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}{% endif %}<｜hy_User｜>{% elif message['role'] == 'assistant' %}{{ message['content'] }}<｜hy_Assistant｜>{% endif %}{% endfor %}

config.json

@@ -0,0 +1,27 @@
+{
+  "architectures": [
+    "HunYuanVLVisionTransformer"
+  ],
+  "attention_dropout": 0.0,
+  "dtype": "float32",
+  "hidden_act": "silu",
+  "hidden_size": 64,
+  "img_max_token_num": 4096,
+  "intermediate_size": 128,
+  "interpolate_mode": "bilinear",
+  "max_image_size": 64,
+  "max_vit_seq_len": 16,
+  "min_image_size": 64,
+  "model_type": "hunyuan_vl_vision",
+  "num_attention_heads": 4,
+  "num_channels": 3,
+  "num_hidden_layers": 2,
+  "num_key_value_heads": 4,
+  "out_hidden_size": 64,
+  "patch_size": 16,
+  "rms_norm_eps": 1e-05,
+  "spatial_merge_size": 1,
+  "temporal_patch_size": 1,
+  "text_hidden_size": 64,
+  "transformers_version": "5.16.0.dev0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4a4f0d413087e2c6d2ba682b9839a775fdfb4124f264135a5564b3b9eba4fe4
+size 706824

preprocessor_config.json

@@ -0,0 +1,26 @@
+{
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "HunYuanVLImageProcessor",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "merge_size": 2,
+  "patch_size": 16,
+  "resample": 1,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "longest_edge": 16777216,
+    "shortest_edge": 262144
+  },
+  "temporal_patch_size": 1
+}

tokenizer_config.json

@@ -0,0 +1,26 @@
+{
+  "backend": "tokenizers",
+  "bos_token": "<｜hy_begin▁of▁sentence｜>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<｜hy_Assistant｜>",
+  "image_end_token": "<｜hy_place▁holder▁no▁101｜>",
+  "image_start_token": "<｜hy_place▁holder▁no▁100｜>",
+  "image_token": "<｜hy_place▁holder▁no▁102｜>",
+  "is_local": true,
+  "local_files_only": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "model_specific_special_tokens": {
+    "image_end_token": "<｜hy_place▁holder▁no▁101｜>",
+    "image_start_token": "<｜hy_place▁holder▁no▁100｜>",
+    "image_token": "<｜hy_place▁holder▁no▁102｜>",
+    "video_end_token": "<｜hy_place▁holder▁no▁105｜>",
+    "video_start_token": "<｜hy_place▁holder▁no▁104｜>",
+    "video_token": "<｜hy_place▁holder▁no▁665｜>"
+  },
+  "pad_token": "<｜hy_▁pad▁｜>",
+  "processor_class": "HunYuanVLProcessor",
+  "tokenizer_class": "TokenizersBackend",
+  "video_end_token": "<｜hy_place▁holder▁no▁105｜>",
+  "video_start_token": "<｜hy_place▁holder▁no▁104｜>",
+  "video_token": "<｜hy_place▁holder▁no▁665｜>"
+}