Add files using upload-large-folder tool

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,12 @@
+# VEFX-Reward Model
+
+Video Editing Quality Reward Model based on Qwen3-VL.
+
+## Dimensions
+- **IF**: Instructional Following (1-4)
+- **RQ**: Render Quality (1-4)
+- **EE**: Edit Exclusivity (1-4)
+
+## Usage
+
+See [VEFX-Leaderboard](https://github.com/YOUR_ORG/VEFX-Leaderboard) for usage.

chat_template.jinja

@@ -0,0 +1,120 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {%- if messages[0].content is string %}
+            {{- messages[0].content }}
+        {%- else %}
+            {%- for content in messages[0].content %}
+                {%- if 'text' in content %}
+                    {{- content.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {{- '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' }}
+        {%- if messages[0].content is string %}
+            {{- messages[0].content }}
+        {%- else %}
+            {%- for content in messages[0].content %}
+                {%- if 'text' in content %}
+                    {{- content.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set image_count = namespace(value=0) %}
+{%- set video_count = namespace(value=0) %}
+{%- for message in messages %}
+    {%- if message.role == "user" %}
+        {{- '<|im_start|>' + message.role + '\n' }}
+        {%- 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 %}
+                    {%- set image_count.value = image_count.value + 1 %}
+                    {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
+                    <|vision_start|><|image_pad|><|vision_end|>
+                {%- elif content.type == 'video' or 'video' in content %}
+                    {%- set video_count.value = video_count.value + 1 %}
+                    {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
+                    <|vision_start|><|video_pad|><|vision_end|>
+                {%- elif 'text' in content %}
+                    {{- content.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role + '\n' }}
+        {%- if message.content is string %}
+            {{- message.content }}
+        {%- else %}
+            {%- for content_item in message.content %}
+                {%- if 'text' in content_item %}
+                    {{- content_item.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and message.content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {%- 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 %}
+                    {%- set image_count.value = image_count.value + 1 %}
+                    {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
+                    <|vision_start|><|image_pad|><|vision_end|>
+                {%- elif content.type == 'video' or 'video' in content %}
+                    {%- set video_count.value = video_count.value + 1 %}
+                    {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
+                    <|vision_start|><|video_pad|><|vision_end|>
+                {%- elif 'text' in content %}
+                    {{- content.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

config.json

@@ -0,0 +1,76 @@
+{
+  "architectures": [
+    "Qwen3VLRewardModelBT"
+  ],
+  "dtype": "bfloat16",
+  "image_token_id": 151655,
+  "model_type": "qwen3_vl",
+  "text_config": {
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "bos_token_id": 151643,
+    "dtype": "bfloat16",
+    "eos_token_id": 151645,
+    "head_dim": 128,
+    "hidden_act": "silu",
+    "hidden_size": 2560,
+    "initializer_range": 0.02,
+    "intermediate_size": 9728,
+    "max_position_embeddings": 262144,
+    "model_type": "qwen3_vl_text",
+    "num_attention_heads": 32,
+    "num_hidden_layers": 36,
+    "num_key_value_heads": 8,
+    "pad_token_id": null,
+    "rms_norm_eps": 1e-06,
+    "rope_parameters": {
+      "mrope_interleaved": true,
+      "mrope_section": [
+        24,
+        20,
+        20
+      ],
+      "rope_theta": 5000000,
+      "rope_type": "default"
+    },
+    "tie_word_embeddings": true,
+    "use_cache": true,
+    "vocab_size": 151675,
+    "rope_scaling": {
+      "mrope_interleaved": true,
+      "mrope_section": [
+        24,
+        20,
+        20
+      ],
+      "rope_type": "default"
+    }
+  },
+  "tie_word_embeddings": true,
+  "transformers_version": "5.4.0",
+  "use_cache": true,
+  "video_token_id": 151656,
+  "vision_config": {
+    "deepstack_visual_indexes": [
+      5,
+      11,
+      17
+    ],
+    "depth": 24,
+    "dtype": "bfloat16",
+    "hidden_act": "gelu_pytorch_tanh",
+    "hidden_size": 1024,
+    "in_channels": 3,
+    "initializer_range": 0.02,
+    "intermediate_size": 4096,
+    "model_type": "qwen3_vl",
+    "num_heads": 16,
+    "num_position_embeddings": 2304,
+    "out_hidden_size": 2560,
+    "patch_size": 16,
+    "spatial_merge_size": 2,
+    "temporal_patch_size": 2
+  },
+  "vision_end_token_id": 151653,
+  "vision_start_token_id": 151652
+}

generation_config.json

@@ -0,0 +1,27 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "num_classes": 4,
+  "output_dim": 3,
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.0,
+  "reward_token": "special",
+  "special_token_ids": [
+    151669,
+    151670,
+    151671,
+    151672,
+    151673,
+    151674
+  ],
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "5.4.0",
+  "use_cache": true,
+  "use_ordinal": true
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3c0d03f770f0a73631206821922213de75413bb517f7d7a2fd9ab1f2c38f59d
+size 8874398544

model_config.json

@@ -0,0 +1,226 @@
+{
+  "data_config": {
+    "max_frame_pixels": 399360,
+    "num_frames": null,
+    "fps": 4.0,
+    "p_shuffle_frames": 0.0,
+    "p_color_jitter": 0.0,
+    "eval_dim": [
+      "IF",
+      "RQ",
+      "EE"
+    ],
+    "prompt_template_type": "editreward_v2_special",
+    "add_noise": false,
+    "sample_type": "uniform",
+    "use_tied_data": true,
+    "pointwise": true
+  },
+  "training_args": {
+    "overwrite_output_dir": false,
+    "do_train": false,
+    "do_eval": true,
+    "do_predict": false,
+    "eval_strategy": "steps",
+    "prediction_loss_only": false,
+    "per_device_train_batch_size": 1,
+    "per_device_eval_batch_size": 1,
+    "per_gpu_train_batch_size": null,
+    "per_gpu_eval_batch_size": null,
+    "gradient_accumulation_steps": 4,
+    "eval_accumulation_steps": null,
+    "eval_delay": 0,
+    "torch_empty_cache_steps": null,
+    "learning_rate": 1e-05,
+    "weight_decay": 0.0,
+    "adam_beta1": 0.9,
+    "adam_beta2": 0.999,
+    "adam_epsilon": 1e-08,
+    "max_grad_norm": 1.0,
+    "num_train_epochs": 30.0,
+    "max_steps": -1,
+    "lr_scheduler_type": "cosine",
+    "lr_scheduler_kwargs": null,
+    "warmup_ratio": 0.0172,
+    "warmup_steps": 0,
+    "log_level": "passive",
+    "log_level_replica": "warning",
+    "log_on_each_node": true,
+    "logging_dir": "/mnt/novita2/xiangbo/Folder/Research/2026/VideoEditedReward/VideoEditReward/VideoAlign/logs/v4/ord_4B_lora_2stage_promptv2_res399k/runs/Mar19_16-20-11_host-10-240-99-115",
+    "logging_strategy": "steps",
+    "logging_first_step": false,
+    "logging_steps": 5,
+    "logging_nan_inf_filter": true,
+    "save_strategy": "steps",
+    "save_steps": 50,
+    "save_total_limit": 4,
+    "save_safetensors": true,
+    "save_on_each_node": false,
+    "save_only_model": false,
+    "restore_callback_states_from_checkpoint": false,
+    "no_cuda": false,
+    "use_cpu": false,
+    "use_mps_device": false,
+    "seed": 42,
+    "data_seed": null,
+    "jit_mode_eval": false,
+    "bf16": true,
+    "fp16": false,
+    "fp16_opt_level": "O1",
+    "half_precision_backend": "auto",
+    "bf16_full_eval": false,
+    "fp16_full_eval": false,
+    "tf32": null,
+    "ddp_backend": null,
+    "tpu_num_cores": null,
+    "tpu_metrics_debug": false,
+    "debug": [],
+    "dataloader_drop_last": false,
+    "eval_steps": 50,
+    "dataloader_num_workers": 6,
+    "dataloader_prefetch_factor": null,
+    "past_index": -1,
+    "run_name": null,
+    "disable_tqdm": false,
+    "remove_unused_columns": false,
+    "label_names": null,
+    "load_best_model_at_end": false,
+    "metric_for_best_model": "eval_loss",
+    "greater_is_better": false,
+    "ignore_data_skip": false,
+    "fsdp": [],
+    "fsdp_min_num_params": 0,
+    "fsdp_config": {
+      "min_num_params": 0,
+      "xla": false,
+      "xla_fsdp_v2": false,
+      "xla_fsdp_grad_ckpt": false
+    },
+    "fsdp_transformer_layer_cls_to_wrap": null,
+    "accelerator_config": {
+      "split_batches": false,
+      "dispatch_batches": null,
+      "even_batches": true,
+      "use_seedable_sampler": true,
+      "non_blocking": false,
+      "gradient_accumulation_kwargs": null,
+      "use_configured_state": false
+    },
+    "parallelism_config": null,
+    "deepspeed": "ds_config/zero0.json",
+    "label_smoothing_factor": 0.0,
+    "optim": "adamw_torch",
+    "optim_args": null,
+    "adafactor": false,
+    "group_by_length": false,
+    "length_column_name": "length",
+    "report_to": [
+      "tensorboard"
+    ],
+    "project": "huggingface",
+    "trackio_space_id": "trackio",
+    "ddp_find_unused_parameters": null,
+    "ddp_bucket_cap_mb": null,
+    "ddp_broadcast_buffers": null,
+    "dataloader_pin_memory": true,
+    "dataloader_persistent_workers": false,
+    "skip_memory_metrics": true,
+    "use_legacy_prediction_loop": false,
+    "push_to_hub": false,
+    "resume_from_checkpoint": null,
+    "hub_model_id": null,
+    "hub_strategy": "every_save",
+    "hub_token": null,
+    "hub_private_repo": null,
+    "hub_always_push": false,
+    "hub_revision": null,
+    "gradient_checkpointing": true,
+    "gradient_checkpointing_kwargs": null,
+    "include_inputs_for_metrics": false,
+    "include_for_metrics": [],
+    "eval_do_concat_batches": true,
+    "fp16_backend": "auto",
+    "push_to_hub_model_id": null,
+    "push_to_hub_organization": null,
+    "push_to_hub_token": null,
+    "mp_parameters": "",
+    "auto_find_batch_size": false,
+    "full_determinism": false,
+    "torchdynamo": null,
+    "ray_scope": "last",
+    "ddp_timeout": 1800,
+    "torch_compile": false,
+    "torch_compile_backend": null,
+    "torch_compile_mode": null,
+    "include_tokens_per_second": false,
+    "include_num_input_tokens_seen": "no",
+    "neftune_noise_alpha": null,
+    "optim_target_modules": null,
+    "batch_eval_metrics": false,
+    "eval_on_start": false,
+    "use_liger_kernel": false,
+    "liger_kernel_config": null,
+    "eval_use_gather_object": false,
+    "average_tokens_across_devices": true,
+    "model_init_kwargs": null,
+    "chat_template_path": null,
+    "disable_dropout": true,
+    "dataset_num_proc": null,
+    "eos_token": null,
+    "pad_token": null,
+    "max_length": 32768,
+    "pad_to_multiple_of": null,
+    "center_rewards_coefficient": null,
+    "activation_offloading": false,
+    "vision_lr": 2e-06,
+    "merger_lr": 1e-05,
+    "special_token_lr": 5e-05,
+    "conduct_eval": true,
+    "load_from_pretrained": null,
+    "load_from_pretrained_step": null,
+    "logging_epochs": null,
+    "eval_epochs": null,
+    "save_epochs": null,
+    "save_full_model": false,
+    "two_stage_align": true,
+    "align_lr": 0.0002,
+    "align_epochs": 1.0,
+    "align_init_embedding": "0.5"
+  },
+  "model_config": {
+    "model_name_or_path": "Qwen/Qwen3-VL-4B-Instruct",
+    "model_revision": "main",
+    "output_dim": 3,
+    "use_ordinal": true,
+    "num_classes": 4,
+    "use_special_tokens": true,
+    "freeze_vision_tower": true,
+    "freeze_llm": false,
+    "tune_merger": true,
+    "torch_dtype": "bfloat16",
+    "trust_remote_code": false,
+    "attn_implementation": null,
+    "load_in_8bit": false,
+    "load_in_4bit": false,
+    "bnb_4bit_quant_type": "nf4",
+    "use_bnb_nested_quant": false,
+    "reward_token": "special",
+    "loss_type": "ord"
+  },
+  "peft_lora_config": {
+    "lora_enable": true,
+    "vision_lora": false,
+    "vision_lora_only": false,
+    "lora_r": 16,
+    "lora_alpha": 32,
+    "lora_dropout": 0.05,
+    "lora_target_modules": null,
+    "lora_namespan_exclude": [
+      "visual"
+    ],
+    "lora_modules_to_save": null,
+    "lora_task_type": "CAUSAL_LM",
+    "use_rslora": false,
+    "num_lora_modules": -1
+  }
+}

processor_config.json

@@ -0,0 +1,60 @@
+{
+  "image_processor": {
+    "do_convert_rgb": true,
+    "do_normalize": true,
+    "do_rescale": true,
+    "do_resize": true,
+    "image_mean": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "image_processor_type": "Qwen2VLImageProcessor",
+    "image_std": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "merge_size": 2,
+    "patch_size": 16,
+    "resample": 3,
+    "rescale_factor": 0.00392156862745098,
+    "size": {
+      "longest_edge": 16777216,
+      "shortest_edge": 65536
+    },
+    "temporal_patch_size": 2
+  },
+  "processor_class": "Qwen3VLProcessor",
+  "video_processor": {
+    "do_convert_rgb": true,
+    "do_normalize": true,
+    "do_rescale": true,
+    "do_resize": true,
+    "do_sample_frames": true,
+    "fps": 2,
+    "image_mean": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "image_std": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "max_frames": 768,
+    "merge_size": 2,
+    "min_frames": 4,
+    "patch_size": 16,
+    "resample": 3,
+    "rescale_factor": 0.00392156862745098,
+    "return_metadata": false,
+    "size": {
+      "longest_edge": 25165824,
+      "shortest_edge": 4096
+    },
+    "temporal_patch_size": 2,
+    "video_processor_type": "Qwen3VLVideoProcessor"
+  }
+}

stage1/adapter_config.json

@@ -0,0 +1,49 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "/mnt/novita2/xiangbo/.cache/huggingface/hub/models--Qwen--Qwen3-VL-4B-Instruct/snapshots/ebb281ec70b05090aa6165b016eac8ec08e71b17",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_proj",
+    "down_proj",
+    "o_proj",
+    "rm_head",
+    "up_proj",
+    "lm_head",
+    "embed_tokens",
+    "k_proj",
+    "gate_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

stage1/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ca4266366a7e98f8a1b72092b6f8100b883944070c1cb0ccd2e41d52b281a8d
+size 1629243584

stage1/non_lora_state_dict.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a617579fefc4742e6e71fe1c984ddcba59fa97a3ab2a8724f6d44c882e354466
+size 776592992

stage2/adapter_config.json

@@ -0,0 +1,49 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "/mnt/novita2/xiangbo/.cache/huggingface/hub/models--Qwen--Qwen3-VL-4B-Instruct/snapshots/ebb281ec70b05090aa6165b016eac8ec08e71b17",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_proj",
+    "down_proj",
+    "o_proj",
+    "rm_head",
+    "up_proj",
+    "lm_head",
+    "embed_tokens",
+    "k_proj",
+    "gate_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

stage2/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a10bb1a1a429e7dbdf6c0b4b44397cec04e7cd9d0f0833cde3e89729b6c6f09
+size 1629243584

stage2/non_lora_state_dict.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9daff7dd904a57927c51bd0322d62b4c183fcd42268c752f35512e12e607f73a
+size 831138256

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14b00451fa975cf85805f0a7a15dee0ae5049d5f0b50046f432dd6d9a95b095a
+size 11423790

tokenizer_config.json

@@ -0,0 +1,16 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "is_local": true,
+  "model_max_length": 262144,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "processor_class": "Qwen3VLProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

vefx_config.json

@@ -0,0 +1,14 @@
+{
+  "output_dim": 3,
+  "use_ordinal": true,
+  "num_classes": 4,
+  "reward_token": "special",
+  "fps": 4.0,
+  "max_frame_pixels": 399360,
+  "eval_dim": [
+    "IF",
+    "RQ",
+    "EE"
+  ],
+  "prompt_template_type": "editreward_v2_special"
+}