Update tiny models for Lfm2VlModel

chat_template.jinja

@@ -0,0 +1,4 @@
+{{bos_token}}{% for message in messages %}{{'<|im_start|>' + message['role'] + '
+'}}{% if message['content'] is string %}{{ message['content'] }}{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' %}{{ '<image>' }}{% elif content['type'] == 'text' %}{{ content['text'] }}{% endif %}{% endfor %}{% endif %}{{'<|im_end|>
+'}}{% endfor %}{% if add_generation_prompt %}{{'<|im_start|>assistant
+' }}{% endif %}

config.json

@@ -0,0 +1,61 @@
+{
+  "architectures": [
+    "Lfm2VlModel"
+  ],
+  "downsample_factor": 4,
+  "dtype": "float32",
+  "image_token_id": 4,
+  "model_type": "lfm2_vl",
+  "projector_bias": true,
+  "projector_hidden_act": "gelu",
+  "projector_hidden_size": 32,
+  "projector_use_layernorm": true,
+  "text_config": {
+    "block_auto_adjust_ff_dim": true,
+    "block_ffn_dim_multiplier": 1.0,
+    "block_multiple_of": 2,
+    "bos_token_id": 1,
+    "conv_L_cache": 3,
+    "conv_bias": false,
+    "eos_token_id": 7,
+    "full_attn_idxs": [
+      0
+    ],
+    "hidden_size": 32,
+    "initializer_range": 0.02,
+    "intermediate_size": 37,
+    "layer_types": [
+      "full_attention",
+      "conv"
+    ],
+    "max_position_embeddings": 200,
+    "model_type": "lfm2",
+    "norm_eps": 1e-05,
+    "num_attention_heads": 4,
+    "num_hidden_layers": 2,
+    "num_key_value_heads": 2,
+    "pad_token_id": 0,
+    "rope_parameters": {
+      "rope_theta": 1000000.0,
+      "rope_type": "default"
+    },
+    "tie_word_embeddings": true,
+    "use_cache": true,
+    "vocab_size": 64400
+  },
+  "tie_word_embeddings": true,
+  "transformers_version": "5.16.0.dev0",
+  "vision_config": {
+    "attention_dropout": 0.0,
+    "hidden_act": "gelu_pytorch_tanh",
+    "hidden_size": 32,
+    "intermediate_size": 37,
+    "layer_norm_eps": 1e-06,
+    "model_type": "siglip2_vision_model",
+    "num_attention_heads": 2,
+    "num_channels": 3,
+    "num_hidden_layers": 2,
+    "num_patches": 16,
+    "patch_size": 4
+  }
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:599188a1710606d3b8817fa45a30233422882c0cc3d4c882fa971e71c23aeeba
+size 8463612

preprocessor_config.json

@@ -0,0 +1,38 @@
+{
+  "data_format": "channels_first",
+  "default_to_square": true,
+  "do_image_splitting": true,
+  "do_normalize": true,
+  "do_pad": true,
+  "do_rescale": true,
+  "do_resize": false,
+  "downsample_factor": 2,
+  "encoder_patch_size": 16,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "Lfm2VlImageProcessor",
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "max_image_tokens": 256,
+  "max_num_patches": 1024,
+  "max_pixels_tolerance": 2.0,
+  "max_tiles": 10,
+  "min_image_tokens": 64,
+  "min_tiles": 2,
+  "patch_size": 16,
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "return_row_col_info": true,
+  "size": {
+    "height": 512,
+    "width": 512
+  },
+  "tile_size": 512,
+  "use_thumbnail": true
+}

tokenizer_config.json

@@ -0,0 +1,30 @@
+{
+  "auto_map": {
+    "AutoProcessor": "processing_lfm2_vl.Lfm2VlProcessor"
+  },
+  "backend": "tokenizers",
+  "bos_token": "<|startoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|im_end|>",
+  "image_end_token": "<|image_end|>",
+  "image_start_token": "<|image_start|>",
+  "image_thumbnail": "<|img_thumbnail|>",
+  "image_token": "<image>",
+  "is_local": true,
+  "legacy": false,
+  "local_files_only": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "model_specific_special_tokens": {
+    "image_end_token": "<|image_end|>",
+    "image_start_token": "<|image_start|>",
+    "image_token": "<image>"
+  },
+  "pad_token": "<|pad|>",
+  "processor_class": "Lfm2VlProcessor",
+  "return_token_type_ids": false,
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "TokenizersBackend",
+  "use_default_system_prompt": false,
+  "use_fast": true
+}