Upload videollama3_baseline checkpoint

.gitattributes

@@ -34,3 +34,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 wheels/flash_attn-2.7.3+cu11torch2.4cxx11abiFALSE-cp310-cp310-linux_x86_64.whl filter=lfs diff=lfs merge=lfs -text
+ckpt/videollama3_baseline/tokenizer.json filter=lfs diff=lfs merge=lfs -text

ckpt/videollama3_baseline/added_tokens.json

@@ -0,0 +1,27 @@
+{
+  "</tool_call>": 151658,
+  "<image>": 151665,
+  "<tool_call>": 151657,
+  "<|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,
+  "<|stream_end|>": 151667,
+  "<|stream_start|>": 151666,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

ckpt/videollama3_baseline/config.json

@@ -0,0 +1,165 @@
+{
+    "vocab_size": 152064,
+    "max_position_embeddings": 32768,
+    "hidden_size": 3584,
+    "intermediate_size": 18944,
+    "num_hidden_layers": 28,
+    "num_attention_heads": 28,
+    "use_sliding_window": false,
+    "sliding_window": null,
+    "max_window_layers": 28,
+    "num_key_value_heads": 4,
+    "hidden_act": "silu",
+    "initializer_range": 0.02,
+    "rms_norm_eps": 1e-06,
+    "use_cache": true,
+    "rope_theta": 1000000.0,
+    "rope_scaling": null,
+    "attention_dropout": 0.0,
+    "return_dict": true,
+    "output_hidden_states": false,
+    "output_attentions": false,
+    "torchscript": false,
+    "torch_dtype": "bfloat16",
+    "use_bfloat16": false,
+    "tf_legacy_loss": false,
+    "pruned_heads": {},
+    "tie_word_embeddings": false,
+    "chunk_size_feed_forward": 0,
+    "is_encoder_decoder": false,
+    "is_decoder": false,
+    "cross_attention_hidden_size": null,
+    "add_cross_attention": false,
+    "tie_encoder_decoder": false,
+    "max_length": 20,
+    "min_length": 0,
+    "do_sample": false,
+    "early_stopping": false,
+    "num_beams": 1,
+    "num_beam_groups": 1,
+    "diversity_penalty": 0.0,
+    "temperature": 1.0,
+    "top_k": 50,
+    "top_p": 1.0,
+    "typical_p": 1.0,
+    "repetition_penalty": 1.0,
+    "length_penalty": 1.0,
+    "no_repeat_ngram_size": 0,
+    "encoder_no_repeat_ngram_size": 0,
+    "bad_words_ids": null,
+    "num_return_sequences": 1,
+    "output_scores": false,
+    "return_dict_in_generate": false,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "remove_invalid_values": false,
+    "exponential_decay_length_penalty": null,
+    "suppress_tokens": null,
+    "begin_suppress_tokens": null,
+    "architectures": [
+        "Videollama3Qwen2ForCausalLM"
+    ],
+    "finetuning_task": null,
+    "id2label": {
+        "0": "LABEL_0",
+        "1": "LABEL_1"
+    },
+    "label2id": {
+        "LABEL_0": 0,
+        "LABEL_1": 1
+    },
+    "tokenizer_class": null,
+    "prefix": null,
+    "bos_token_id": 151643,
+    "pad_token_id": null,
+    "eos_token_id": 151645,
+    "sep_token_id": null,
+    "decoder_start_token_id": null,
+    "task_specific_params": null,
+    "problem_type": null,
+    "_name_or_path": "/home/kaidi/VideoLLaMA3/HF_model",
+    "_attn_implementation_autoset": true,
+    "transformers_version": "4.46.3",
+    "auto_map": {
+        "AutoConfig": "configuration_videollama3.Videollama3Qwen2Config",
+        "AutoModelForCausalLM": "modeling_videollama3.Videollama3Qwen2ForCausalLM"
+    },
+    "model_type": "videollama3_qwen2",
+    "vision_encoder": "DAMO-NLP-SG/SigLIP-NaViT",
+    "vision_encoder_config": {
+        "return_dict": true,
+        "output_hidden_states": false,
+        "output_attentions": false,
+        "torchscript": false,
+        "torch_dtype": null,
+        "use_bfloat16": false,
+        "tf_legacy_loss": false,
+        "pruned_heads": {},
+        "tie_word_embeddings": true,
+        "chunk_size_feed_forward": 0,
+        "is_encoder_decoder": false,
+        "is_decoder": false,
+        "cross_attention_hidden_size": null,
+        "add_cross_attention": false,
+        "tie_encoder_decoder": false,
+        "max_length": 20,
+        "min_length": 0,
+        "do_sample": false,
+        "early_stopping": false,
+        "num_beams": 1,
+        "num_beam_groups": 1,
+        "diversity_penalty": 0.0,
+        "temperature": 1.0,
+        "top_k": 50,
+        "top_p": 1.0,
+        "typical_p": 1.0,
+        "repetition_penalty": 1.0,
+        "length_penalty": 1.0,
+        "no_repeat_ngram_size": 0,
+        "encoder_no_repeat_ngram_size": 0,
+        "bad_words_ids": null,
+        "num_return_sequences": 1,
+        "output_scores": false,
+        "return_dict_in_generate": false,
+        "forced_bos_token_id": null,
+        "forced_eos_token_id": null,
+        "remove_invalid_values": false,
+        "exponential_decay_length_penalty": null,
+        "suppress_tokens": null,
+        "begin_suppress_tokens": null,
+        "architectures": null,
+        "finetuning_task": null,
+        "id2label": {
+            "0": "LABEL_0",
+            "1": "LABEL_1"
+        },
+        "label2id": {
+            "LABEL_0": 0,
+            "LABEL_1": 1
+        },
+        "tokenizer_class": null,
+        "prefix": null,
+        "bos_token_id": null,
+        "pad_token_id": null,
+        "eos_token_id": null,
+        "sep_token_id": null,
+        "decoder_start_token_id": null,
+        "task_specific_params": null,
+        "problem_type": null,
+        "_name_or_path": "",
+        "_attn_implementation_autoset": false,
+        "model_type": "videollama3_vision_encoder",
+        "hidden_size": 1152,
+        "intermediate_size": 4304,
+        "num_hidden_layers": 27,
+        "num_attention_heads": 16,
+        "num_channels": 3,
+        "patch_size": 14,
+        "attention_dropout": 0.0,
+        "layer_norm_eps": 1e-06,
+        "hidden_act": "gelu_pytorch_tanh"
+    },
+    "mm_projector_type": "mlp2x_gelu",
+    "use_token_compression": true,
+    "image_token_index": 151665
+}

ckpt/videollama3_baseline/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19d30a50a736919a8d1b998a3512a7c48f31fede1bd8178fddb790e25204f657
+size 32179254342

ckpt/videollama3_baseline/special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

ckpt/videollama3_baseline/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6bb63ceb1524412064763cffa446ec94ca752b2be438213ddf3242c36a6152a1
+size 11422458

ckpt/videollama3_baseline/tokenizer_config.json

@@ -0,0 +1,236 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<image>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151666": {
+      "content": "<|stream_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151667": {
+      "content": "<|stream_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "auto_map": {
+    "AutoProcessor": "/home/kaidi/VideoLLaMA3/HF_model--processing_videollama3.Videollama3Qwen2Processor"
+  },
+  "bos_token": null,
+  "chat_template": "\n{%- set identifier = 'im' %}\n{% for message in messages %}\n    {% if add_system_prompt and loop.first and message['role'] != 'system' %}\n        {{- '<|im_start|>system\nYou are VideoLLaMA3 created by Alibaba DAMO Academy, a helpful assistant to help people understand images and videos.<|im_end|>\n' -}}\n    {% endif %}\n    {% if message['role'] == 'stream' %}\n        {% set identifier = 'stream' %}\n    {% else %}\n        {% set identifier = 'im' %}\n    {% endif %}\n    {{- '<|' + identifier + '_start|>' + message['role'] + '\n' -}}\n    {% if message['content'] is string %}\n        {{- message['content'] + '<|' + identifier + '_end|>\n' -}}\n    {% else %}\n        {% for content in message['content'] %}\n            {% if content is string %}\n                {{- content -}}\n            {% elif content['type'] == 'text' or 'text' in content %}\n                {{- content['text'] -}}\n            {% elif content['type'] == 'image' or 'image' in content %}\n                {% if 'timestamp' in content %}\n                    {{- 'Time ' + content['timestamp'] | round(1) | string + 's: ' -}}\n                {% endif %}\n                {{- image_token + '\n' -}}\n            {% elif content['type'] == 'video' or 'video' in content %}\n                {% for i in range(content['num_frames']) %}\n                    {% if 'timestamps' in content %}\n                        {{- 'Time ' + content['timestamps'][i] | round(1) | string + 's:' -}}\n                    {% endif %}\n                    {% if i < content['num_frames'] - 1 %}\n                        {{- image_token + ',' -}}\n                    {% else %}\n                        {{- image_token + '\n' -}}\n                    {% endif %}\n                {% endfor %}\n            {% endif %}\n        {% endfor %}\n        {% if identifier == 'stream' %}\n            {{- '<|' + identifier + '_end|>' -}}\n        {% else %}\n            {{- '<|' + identifier + '_end|>\n' -}}\n        {% endif %}\n    {% endif %}\n{% endfor %}\n{% if add_generation_prompt %}\n    {{- '<|im_start|>assistant\n' -}}\n{% endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "processor_class": "Videollama3Qwen2Processor",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}