Update tiny models for LlavaNextVideoForConditionalGeneration

config.json

@@ -0,0 +1,91 @@
+{
+  "architectures": [
+    "LlavaNextVideoForConditionalGeneration"
+  ],
+  "dtype": "float32",
+  "ignore_index": -100,
+  "image_grid_pinpoints": [
+    [
+      16,
+      16
+    ]
+  ],
+  "image_seq_length": 24,
+  "image_token_index": 0,
+  "model_type": "llava_next_video",
+  "multimodal_projector_bias": true,
+  "projector_hidden_act": "gelu",
+  "spatial_pool_mode": "average",
+  "spatial_pool_stride": 2,
+  "text_config": {
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "attention_probs_dropout_prob": 0.1,
+    "bos_token_id": 1,
+    "eos_token_id": 2,
+    "head_dim": 8,
+    "hidden_act": "gelu",
+    "hidden_dropout_prob": 0.1,
+    "hidden_size": 32,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1",
+      "2": "LABEL_2"
+    },
+    "initializer_range": 0.02,
+    "intermediate_size": 37,
+    "is_training": true,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1,
+      "LABEL_2": 2
+    },
+    "max_position_embeddings": 580,
+    "mlp_bias": false,
+    "model_type": "llama",
+    "num_attention_heads": 4,
+    "num_choices": 4,
+    "num_hidden_layers": 2,
+    "num_key_value_heads": 4,
+    "pad_token_id": 0,
+    "pretraining_tp": 1,
+    "rms_norm_eps": 1e-06,
+    "rope_parameters": {
+      "rope_theta": 10000.0,
+      "rope_type": "default"
+    },
+    "seq_length": 7,
+    "tie_word_embeddings": false,
+    "type_sequence_label_size": 2,
+    "type_vocab_size": 16,
+    "use_cache": true,
+    "use_input_mask": true,
+    "use_labels": true,
+    "use_token_type_ids": false,
+    "vocab_size": 32002
+  },
+  "tie_word_embeddings": false,
+  "transformers_version": "5.16.0.dev0",
+  "video_seq_length": 8,
+  "video_token_index": 1,
+  "vision_config": {
+    "attention_dropout": 0.1,
+    "dropout": 0.1,
+    "hidden_act": "quick_gelu",
+    "hidden_size": 32,
+    "image_size": 8,
+    "initializer_factor": 1.0,
+    "initializer_range": 0.02,
+    "intermediate_size": 37,
+    "is_training": true,
+    "layer_norm_eps": 1e-05,
+    "model_type": "clip_vision_model",
+    "num_attention_heads": 4,
+    "num_channels": 3,
+    "num_hidden_layers": 2,
+    "patch_size": 4,
+    "projection_dim": 32
+  },
+  "vision_feature_layer": -1,
+  "vision_feature_select_strategy": "default"
+}

generation_config.json

@@ -0,0 +1,10 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "output_attentions": false,
+  "output_hidden_states": false,
+  "pad_token_id": 0,
+  "transformers_version": "5.16.0.dev0",
+  "use_cache": true
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc300fe6448f898bda5e30dcc67a718590539e10c612944f4766d623118dfc4c
+size 8332032

preprocessor_config.json

@@ -0,0 +1,51 @@
+{
+  "crop_size": {
+    "longest_edge": 8,
+    "shortest_edge": 8
+  },
+  "do_center_crop": true,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_pad": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_grid_pinpoints": [
+    [
+      336,
+      672
+    ],
+    [
+      672,
+      336
+    ],
+    [
+      672,
+      672
+    ],
+    [
+      1008,
+      336
+    ],
+    [
+      336,
+      1008
+    ]
+  ],
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "LlavaNextImageProcessor",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "longest_edge": 8,
+    "shortest_edge": 8
+  }
+}

tokenizer_config.json

@@ -0,0 +1,27 @@
+{
+  "add_prefix_space": true,
+  "backend": "tokenizers",
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "image_token": "<image>",
+  "is_local": true,
+  "local_files_only": false,
+  "max_length": null,
+  "model_max_length": 10250,
+  "model_specific_special_tokens": {
+    "image_token": "<image>",
+    "video_token": "<video>"
+  },
+  "pad_to_multiple_of": null,
+  "pad_token": "<unk>",
+  "pad_token_type_id": 0,
+  "padding_side": "left",
+  "processor_class": "LlavaNextVideoProcessor",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false,
+  "video_token": "<video>"
+}

video_preprocessor_config.json

@@ -0,0 +1,30 @@
+{
+  "crop_size": {
+    "longest_edge": 8,
+    "shortest_edge": 8
+  },
+  "do_center_crop": true,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "do_sample_frames": false,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "return_metadata": false,
+  "size": {
+    "longest_edge": 8,
+    "shortest_edge": 8
+  },
+  "video_processor_type": "LlavaNextVideoVideoProcessor"
+}