add model

README.md

@@ -1,3 +1,60 @@
----
-license: cc-by-nc-nd-4.0
----
+---
+license: cc-by-nc-nd-4.0
+library_name: peft
+base_model: lmms-lab/LLaVA-Video-7B-Qwen2
+tags:
+  - video-understanding
+  - long-video
+  - visual-question-answering
+  - lora
+  - qwen2
+  - llava
+  - cvpr2026
+datasets:
+  - lmms-lab/LLaVA-Video-178K
+pipeline_tag: video-text-to-text
+---
+
+# QViC-MF-7B
+
+This is the official model for the paper **"Question-guided Visual Compression with Memory Feedback for Long-Term Video Understanding"** (CVPR 2026).
+
+- **Paper:** [arXiv](https://arxiv.org/abs/2603.15167)
+- **Code:** [GitHub](https://github.com/FujitsuResearch/QViC-MF)
+- **Authors:** Sosuke Yamao\*, Natsuki Miyahara\*, Yuankai Qi, Shun Takeuchi
+- **Affiliation:** Fujitsu Research / Macquarie University
+
+## Model Description
+
+QViC-MF-7B is a LoRA adapter trained on top of [LLaVA-Video-7B-Qwen2](https://huggingface.co/lmms-lab/LLaVA-Video-7B-Qwen2) for long-term video understanding. It introduces **Question-guided Multimodal Selective Attention (QMSA)**, which learns to preserve visual information related to the given question from both the current clip and past related frames stored in a context memory. The compressor and memory feedback work iteratively for each clip of the entire video, enabling strong performance on tasks that require understanding complete events (e.g., temporal ordering).
+
+## How to Use
+
+Please refer to the [official code repository](https://github.com/FujitsuResearch/QViC-MF) for inference and evaluation scripts.
+
+## Model Details
+
+| Property | Value |
+|----------|-------|
+| Base Model | [lmms-lab/LLaVA-Video-7B-Qwen2](https://huggingface.co/lmms-lab/LLaVA-Video-7B-Qwen2) |
+| Architecture | LlavaQwenForCausalLM |
+| Vision Encoder | SigLIP-SO400M (google/siglip-so400m-patch14-384) |
+| LLM | Qwen2-7B |
+| Adapter | LoRA (r=64, alpha=16) |
+| Context Memory Length | 256 tokens |
+| Precision | bfloat16 |
+
+## Citation
+
+```bibtex
+@inproceedings{yamao2026qvicmf,
+  title={Question-guided Visual Compression with Memory Feedback for Long-Term Video Understanding},
+  author={Yamao, Sosuke and Miyahara, Natsuki and Qi, Yuankai and Takeuchi, Shun},
+  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
+  year={2026}
+}
+```
+
+## License
+
+This model is released under the [CC-BY-NC-ND-4.0](https://creativecommons.org/licenses/by-nc-nd/4.0/) license.

adapter_config.json

@@ -0,0 +1,18 @@
+{
+  "auto_mapping": null,
+  "base_model_name_or_path": "lmms-lab/LLaVA-Video-7B-Qwen2",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "revision": null,
+  "target_modules": "encoder\\.model\\.layers\\.\\d+\\.(mlp\\.(up_proj|gate_proj|down_proj)|self_attn\\.(q_proj|v_proj|k_proj|o_proj))",
+  "task_type": "CAUSAL_LM"
+}

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db0ec1bfc331941e97ffa0b56491ed1ea7579d7bce005f902a5021f240d5f604
+size 323100714

config.json

@@ -0,0 +1,230 @@
+{
+  "_name_or_path": "lmms-lab/LLaVA-Video-7B-Qwen2",
+  "add_faster_video": false,
+  "add_time_instruction": false,
+  "architectures": [
+    "LlavaQwenForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "context_embed_tokens": 16,
+  "context_memory_length": 256,
+  "ctx_attn_mask_type": "framewise",
+  "eos_token_id": 151645,
+  "faster_token_stride": 10,
+  "force_sample": true,
+  "freeze_mm_mlp_adapter": false,
+  "freeze_mm_vision_resampler": false,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "ignore_index": -100,
+  "image_aspect_ratio": "anyres_max_9",
+  "image_crop_resolution": null,
+  "image_grid_pinpoints": [
+    [
+      384,
+      384
+    ],
+    [
+      384,
+      768
+    ],
+    [
+      384,
+      1152
+    ],
+    [
+      384,
+      1536
+    ],
+    [
+      384,
+      1920
+    ],
+    [
+      384,
+      2304
+    ],
+    [
+      768,
+      384
+    ],
+    [
+      768,
+      768
+    ],
+    [
+      768,
+      1152
+    ],
+    [
+      768,
+      1536
+    ],
+    [
+      768,
+      1920
+    ],
+    [
+      768,
+      2304
+    ],
+    [
+      1152,
+      384
+    ],
+    [
+      1152,
+      768
+    ],
+    [
+      1152,
+      1152
+    ],
+    [
+      1152,
+      1536
+    ],
+    [
+      1152,
+      1920
+    ],
+    [
+      1152,
+      2304
+    ],
+    [
+      1536,
+      384
+    ],
+    [
+      1536,
+      768
+    ],
+    [
+      1536,
+      1152
+    ],
+    [
+      1536,
+      1536
+    ],
+    [
+      1536,
+      1920
+    ],
+    [
+      1536,
+      2304
+    ],
+    [
+      1920,
+      384
+    ],
+    [
+      1920,
+      768
+    ],
+    [
+      1920,
+      1152
+    ],
+    [
+      1920,
+      1536
+    ],
+    [
+      1920,
+      1920
+    ],
+    [
+      1920,
+      2304
+    ],
+    [
+      2304,
+      384
+    ],
+    [
+      2304,
+      768
+    ],
+    [
+      2304,
+      1152
+    ],
+    [
+      2304,
+      1536
+    ],
+    [
+      2304,
+      1920
+    ],
+    [
+      2304,
+      2304
+    ]
+  ],
+  "image_split_resolution": null,
+  "image_token_index": 151646,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "mm_hidden_size": 1152,
+  "mm_newline_position": "grid",
+  "mm_patch_merge_type": "spatial_unpad",
+  "mm_projector_lr": null,
+  "mm_projector_type": "mlp2x_gelu",
+  "mm_resampler_type": null,
+  "mm_spatial_pool_mode": "average",
+  "mm_spatial_pool_stride": 2,
+  "mm_tunable_parts": "mm_vision_tower,mm_mlp_adapter,mm_language_model",
+  "mm_use_im_patch_token": false,
+  "mm_use_im_start_end": false,
+  "mm_vision_select_feature": "patch",
+  "mm_vision_select_layer": -2,
+  "mm_vision_tower": "google/siglip-so400m-patch14-384",
+  "mm_vision_tower_lr": 2e-06,
+  "model_type": "llava",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "pos_skipping_range": 4096,
+  "projector_hidden_act": "gelu",
+  "question_guided_selective_attention": true,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": 131072,
+  "text_config": {
+    "model_type": "llama"
+  },
+  "tie_word_embeddings": false,
+  "tokenizer_model_max_length": 32768,
+  "tokenizer_padding_side": "right",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.40.0.dev0",
+  "tune_mm_mlp_adapter": false,
+  "tune_mm_vision_resampler": false,
+  "unfreeze_mm_vision_tower": false,
+  "use_cache": true,
+  "use_mm_proj": true,
+  "use_pos_skipping": false,
+  "use_sliding_window": false,
+  "vision_config": {
+    "hidden_size": 1024,
+    "image_size": 336,
+    "intermediate_size": 4096,
+    "model_type": "clip_vision_model",
+    "num_attention_heads": 16,
+    "num_hidden_layers": 24,
+    "patch_size": 14,
+    "projection_dim": 768,
+    "vocab_size": 32000
+  },
+  "vision_feature_layer": -2,
+  "vision_feature_select_strategy": "default",
+  "vision_tower_pretrained": null
+}

generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.05,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.40.0.dev0"
+}

non_lora_trainables.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99c0a6d96cafe36e5759091cbcc2826c5442cb85c7f58356989b15a3bd5ffeea
+size 115992