{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/video-llama-an-instruction-tuned-audio-visual","title":"Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding","arxiv_id":"2306.02858","date":"2023-06-05","proceeding":null,"authors":["Hang Zhang","Xin Li","Lidong Bing"],"abstract":"We present Video-LLaMA a multi-modal framework that empowers Large Language Models (LLMs) with the capability of understanding both visual and auditory content in the video. Video-LLaMA bootstraps cross-modal training from the frozen pre-trained visual and audio encoders and the frozen LLMs. Unlike previous works that complement LLMs to process the visual or audio signals only, Video-LLaMA enables video comprehension by tackling two challenges: (1) capturing the temporal changes in visual scenes, (2) integrating audio-visual signals. To counter the first challenge, we propose a Video Q-former to assemble a pre-trained image encoder into our video encoder and introduce a video-to-text generation task to learn video-language correspondence. For the second challenge, we leverage ImageBind, a universal embedding model aligning multiple modalities, as the pre-trained audio encoder and introduce an Audio Q-former on top of ImageBind to learn reasonable auditory query embeddings for the LLM module. To align the output of both visual and audio encoders with LLM's embedding space, we first train Video-LLaMA on massive video/image-caption pairs and then tune our model with visual-instruction datasets of moderate amount but higher quality. We found Video-LLaMA shows the ability to perceive and comprehend video content and generate meaningful responses grounded in the visual and auditory information presented in the videos.","url_abs":"https://arxiv.org/abs/2306.02858v4","url_pdf":"https://arxiv.org/pdf/2306.02858v4.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"video-llama-an-instruction-tuned-audio-visual","repo_url":"https://github.com/damo-nlp-sg/video-llama","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"paper_slug":"video-llama-an-instruction-tuned-audio-visual","repo_url":"https://github.com/damo-nlp-sg/videollama2","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"video-llama-an-instruction-tuned-audio-visual","repo_url":"https://github.com/damo-nlp-sg/videollama3","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"video-llama-an-instruction-tuned-audio-visual","repo_url":"https://github.com/xinding-sys/StreamMind","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"text-generation","task_name":"Text Generation"},{"task_slug":"video-question-answering","task_name":"Video Question Answering"},{"task_slug":"video-understanding","task_name":"Video Understanding"},{"task_slug":"video-text-retrieval","task_name":"Video-Text Retrieval"},{"task_slug":"video-based-generative-performance","task_name":"Video-based Generative Performance Benchmarking"},{"task_slug":"video-based-generative-performance-5","task_name":"Video-based Generative Performance Benchmarking (Consistency)"},{"task_slug":"video-based-generative-performance-3","task_name":"Video-based Generative Performance Benchmarking (Contextual Understanding)"},{"task_slug":"video-based-generative-performance-1","task_name":"Video-based Generative Performance Benchmarking (Correctness of Information)"},{"task_slug":"video-based-generative-performance-2","task_name":"Video-based Generative Performance Benchmarking (Detail Orientation))"},{"task_slug":"video-based-generative-performance-4","task_name":"Video-based Generative Performance Benchmarking (Temporal Understanding)"},{"task_slug":"zeroshot-video-question-answer","task_name":"Zero-Shot Video Question Answer"}],"methods":[{"method_slug":"align","method_name":"ALIGN"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/video-question-answering-on-mvbench","task":"Video Question Answering","dataset":"MVBench","model":"VideoLLaMA","rank_in_archive_order":19,"of":22,"metrics":{"Avg.":"34.1"},"uses_additional_data":false},{"leaderboard":"/sota/video-text-retrieval-on-test-of-time","task":"Video-Text Retrieval","dataset":"Test-of-Time","model":"Video-LLAMA","rank_in_archive_order":1,"of":4,"metrics":{"2-Class Accuracy":"88.33"},"uses_additional_data":true},{"leaderboard":"/sota/video-based-generative-performance","task":"Video-based Generative Performance Benchmarking","dataset":"VideoInstruct","model":"Video LLaMA","rank_in_archive_order":23,"of":23,"metrics":{"Consistency":"1.79","Contextual Understanding":"2.16","Correctness of Information":"1.96","Detail Orientation":"2.18","Temporal Understanding":"1.82","mean":"1.98"},"uses_additional_data":false},{"leaderboard":"/sota/video-based-generative-performance-2","task":"Video-based Generative Performance Benchmarking (Consistency)","dataset":"VideoInstruct","model":"Video LLaMA","rank_in_archive_order":18,"of":18,"metrics":{"gpt-score":"1.79"},"uses_additional_data":false},{"leaderboard":"/sota/video-based-generative-performance-3","task":"Video-based Generative Performance Benchmarking (Contextual Understanding)","dataset":"VideoInstruct","model":"Video LLaMA","rank_in_archive_order":18,"of":18,"metrics":{"gpt-score":"2.16"},"uses_additional_data":false},{"leaderboard":"/sota/video-based-generative-performance-1","task":"Video-based Generative Performance Benchmarking (Correctness of Information)","dataset":"VideoInstruct","model":"Video LLaMA","rank_in_archive_order":18,"of":18,"metrics":{"gpt-score":"1.96"},"uses_additional_data":false},{"leaderboard":"/sota/video-based-generative-performance-4","task":"Video-based Generative Performance Benchmarking (Detail Orientation))","dataset":"VideoInstruct","model":"Video LLaMA","rank_in_archive_order":18,"of":18,"metrics":{"gpt-score":"2.18"},"uses_additional_data":false},{"leaderboard":"/sota/video-based-generative-performance-5","task":"Video-based Generative Performance Benchmarking (Temporal Understanding)","dataset":"VideoInstruct","model":"Video LLaMA","rank_in_archive_order":18,"of":18,"metrics":{"gpt-score":"1.82"},"uses_additional_data":false},{"leaderboard":"/sota/zeroshot-video-question-answer-on-activitynet","task":"Zero-Shot Video Question Answer","dataset":"ActivityNet-QA","model":"Video LLaMA","rank_in_archive_order":28,"of":28,"metrics":{"Accuracy":"12.4","Confidence Score":"1.1"},"uses_additional_data":false},{"leaderboard":"/sota/zeroshot-video-question-answer-on-msrvtt-qa","task":"Zero-Shot Video Question Answer","dataset":"MSRVTT-QA","model":"Video LLaMA-7B","rank_in_archive_order":30,"of":30,"metrics":{"Accuracy":"29.6","Confidence Score":"1.8"},"uses_additional_data":false},{"leaderboard":"/sota/zeroshot-video-question-answer-on-msvd-qa","task":"Zero-Shot Video Question Answer","dataset":"MSVD-QA","model":"Video LLaMA-7B","rank_in_archive_order":27,"of":28,"metrics":{"Accuracy":"51.6","Confidence Score":"2.5"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2306.02858","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.02858"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/damo-nlp-sg/videollama2","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/damo-nlp-sg/video-llama","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/damo-nlp-sg/videollama3","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/xinding-sys/StreamMind","reach":null}],"summary":{"ran":10,"ran_fixture":2,"ran_draft_wrong":5,"ran_violates":1,"unverified":7},"by_repo_kind":{"official":{"samples":9,"ran":7,"repositories":1},"listed":{"samples":16,"ran":11,"repositories":2}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":9,"samples":[{"code_sha256_prefix":"0d7afd7e8c6f79a7","entry":"ClsNet","repo":"xinding-sys/StreamMind","repo_kind":"listed","path":"streammind/model/multimodal_projector/builder.py","file_url":"https://github.com/xinding-sys/StreamMind/blob/HEAD/streammind/model/multimodal_projector/builder.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"0d7afd7e8c6f79a7"}},{"code_sha256_prefix":"034c07582f342e3f","entry":"STCConnector","repo":"xinding-sys/StreamMind","repo_kind":"listed","path":"streammind/model/multimodal_projector/builder.py","file_url":"https://github.com/xinding-sys/StreamMind/blob/HEAD/streammind/model/multimodal_projector/builder.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"034c07582f342e3f"}},{"code_sha256_prefix":"143af1a0e1416655","entry":"STCConnector","repo":"damo-nlp-sg/videollama2","repo_kind":"listed","path":"videollama2/model/videollama2_arch.py","file_url":"https://github.com/damo-nlp-sg/videollama2/blob/HEAD/videollama2/model/videollama2_arch.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"143af1a0e1416655"}},{"code_sha256_prefix":"d25dbb06b89a36bd","entry":"STCConnectorV35","repo":"damo-nlp-sg/videollama2","repo_kind":"listed","path":"videollama2/model/videollama2_arch.py","file_url":"https://github.com/damo-nlp-sg/videollama2/blob/HEAD/videollama2/model/videollama2_arch.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"d25dbb06b89a36bd"}},{"code_sha256_prefix":"a1260df691548981","entry":"STPConnector","repo":"damo-nlp-sg/videollama2","repo_kind":"listed","path":"videollama2/model/videollama2_arch.py","file_url":"https://github.com/damo-nlp-sg/videollama2/blob/HEAD/videollama2/model/videollama2_arch.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"a1260df691548981"}},{"code_sha256_prefix":"75d05c81526b6ca0","entry":"SpatialConv","repo":"damo-nlp-sg/videollama2","repo_kind":"listed","path":"videollama2/model/videollama2_arch.py","file_url":"https://github.com/damo-nlp-sg/videollama2/blob/HEAD/videollama2/model/videollama2_arch.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"75d05c81526b6ca0"}},{"code_sha256_prefix":"27e6bfb755d3e81b","entry":"SpatialPool","repo":"damo-nlp-sg/videollama2","repo_kind":"listed","path":"videollama2/model/videollama2_arch.py","file_url":"https://github.com/damo-nlp-sg/videollama2/blob/HEAD/videollama2/model/videollama2_arch.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"27e6bfb755d3e81b"}},{"code_sha256_prefix":"9b4dff79d5e6102c","entry":"apply_rotary_pos_emb","repo":"damo-nlp-sg/video-llama","repo_kind":"official","path":"video_llama/models/modeling_llama.py","file_url":"https://github.com/damo-nlp-sg/video-llama/blob/HEAD/video_llama/models/modeling_llama.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":false,"mcp_get_code":{"code_sha256":"9b4dff79d5e6102c"}},{"code_sha256_prefix":"d62ac690ebadd7fa","entry":"build_mlp","repo":"xinding-sys/StreamMind","repo_kind":"listed","path":"streammind/model/multimodal_projector/builder.py","file_url":"https://github.com/xinding-sys/StreamMind/blob/HEAD/streammind/model/multimodal_projector/builder.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"d62ac690ebadd7fa"}},{"code_sha256_prefix":"7aa936fbe4f3d6fe","entry":"build_vision_projector","repo":"damo-nlp-sg/videollama2","repo_kind":"listed","path":"videollama2/model/videollama2_arch.py","file_url":"https://github.com/damo-nlp-sg/videollama2/blob/HEAD/videollama2/model/videollama2_arch.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"7aa936fbe4f3d6fe"}},{"code_sha256_prefix":"4cb732f513d69dfd","entry":"disabled_train","repo":"damo-nlp-sg/video-llama","repo_kind":"official","path":"video_llama/models/blip2.py","file_url":"https://github.com/damo-nlp-sg/video-llama/blob/HEAD/video_llama/models/blip2.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":false,"mcp_get_code":{"code_sha256":"4cb732f513d69dfd"}},{"code_sha256_prefix":"7d214655954e2bc6","entry":"getAttMap","repo":"damo-nlp-sg/video-llama","repo_kind":"official","path":"video_llama/common/gradcam.py","file_url":"https://github.com/damo-nlp-sg/video-llama/blob/HEAD/video_llama/common/gradcam.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"BSD-3-Clause","inline_ok":false,"mcp_get_code":{"code_sha256":"7d214655954e2bc6"}},{"code_sha256_prefix":"d8e25fe3aa75d2ce","entry":"load_mm_projector","repo":"damo-nlp-sg/videollama2","repo_kind":"listed","path":"videollama2/model/videollama2_arch.py","file_url":"https://github.com/damo-nlp-sg/videollama2/blob/HEAD/videollama2/model/videollama2_arch.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"d8e25fe3aa75d2ce"}},{"code_sha256_prefix":"98589643273920ba","entry":"main_process","repo":"damo-nlp-sg/video-llama","repo_kind":"official","path":"video_llama/common/dist_utils.py","file_url":"https://github.com/damo-nlp-sg/video-llama/blob/HEAD/video_llama/common/dist_utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":false,"mcp_get_code":{"code_sha256":"98589643273920ba"}},{"code_sha256_prefix":"791c72070c0b1cfb","entry":"node_to_dict","repo":"damo-nlp-sg/video-llama","repo_kind":"official","path":"video_llama/common/config.py","file_url":"https://github.com/damo-nlp-sg/video-llama/blob/HEAD/video_llama/common/config.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":false,"mcp_get_code":{"code_sha256":"791c72070c0b1cfb"}},{"code_sha256_prefix":"04129d1d261c322a","entry":"parse_snapshot_folder","repo":"damo-nlp-sg/videollama2","repo_kind":"listed","path":"videollama2/model/videollama2_arch.py","file_url":"https://github.com/damo-nlp-sg/videollama2/blob/HEAD/videollama2/model/videollama2_arch.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"04129d1d261c322a"}},{"code_sha256_prefix":"b99eea6376d1e212","entry":"rotate_half","repo":"damo-nlp-sg/video-llama","repo_kind":"official","path":"video_llama/models/modeling_llama.py","file_url":"https://github.com/damo-nlp-sg/video-llama/blob/HEAD/video_llama/models/modeling_llama.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"BSD-3-Clause","inline_ok":false,"mcp_get_code":{"code_sha256":"b99eea6376d1e212"}},{"code_sha256_prefix":"cb33571427334815","entry":"tile","repo":"damo-nlp-sg/video-llama","repo_kind":"official","path":"video_llama/models/base_model.py","file_url":"https://github.com/damo-nlp-sg/video-llama/blob/HEAD/video_llama/models/base_model.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"BSD-3-Clause","inline_ok":false,"mcp_get_code":{"code_sha256":"cb33571427334815"}},{"code_sha256_prefix":"351648024debfdef","entry":"CLIPVisionTower","repo":"damo-nlp-sg/videollama2","repo_kind":"listed","path":"videollama2/model/videollama2_arch.py","file_url":"https://github.com/damo-nlp-sg/videollama2/blob/HEAD/videollama2/model/videollama2_arch.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"351648024debfdef"}},{"code_sha256_prefix":"44b8362633634eda","entry":"MistralForCausalLM_cls","repo":"xinding-sys/StreamMind","repo_kind":"listed","path":"streammind/model/multimodal_projector/builder.py","file_url":"https://github.com/xinding-sys/StreamMind/blob/HEAD/streammind/model/multimodal_projector/builder.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"44b8362633634eda"}},{"code_sha256_prefix":"93c7869a74572a70","entry":"SiglipVisionTower","repo":"damo-nlp-sg/videollama2","repo_kind":"listed","path":"videollama2/model/videollama2_arch.py","file_url":"https://github.com/damo-nlp-sg/videollama2/blob/HEAD/videollama2/model/videollama2_arch.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"93c7869a74572a70"}},{"code_sha256_prefix":"e0abf348c09035c4","entry":"Videollama2MetaModel","repo":"damo-nlp-sg/videollama2","repo_kind":"listed","path":"videollama2/model/videollama2_arch.py","file_url":"https://github.com/damo-nlp-sg/videollama2/blob/HEAD/videollama2/model/videollama2_arch.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"e0abf348c09035c4"}},{"code_sha256_prefix":"0ec9fc2025c16f65","entry":"all_gather_with_grad","repo":"damo-nlp-sg/video-llama","repo_kind":"official","path":"video_llama/models/base_model.py","file_url":"https://github.com/damo-nlp-sg/video-llama/blob/HEAD/video_llama/models/base_model.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":false,"mcp_get_code":{"code_sha256":"0ec9fc2025c16f65"}},{"code_sha256_prefix":"f61dd94ea06b9f92","entry":"build_vision_tower","repo":"damo-nlp-sg/videollama2","repo_kind":"listed","path":"videollama2/model/videollama2_arch.py","file_url":"https://github.com/damo-nlp-sg/videollama2/blob/HEAD/videollama2/model/videollama2_arch.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"f61dd94ea06b9f92"}},{"code_sha256_prefix":"643539116e049080","entry":"download_cached_file","repo":"damo-nlp-sg/video-llama","repo_kind":"official","path":"video_llama/common/dist_utils.py","file_url":"https://github.com/damo-nlp-sg/video-llama/blob/HEAD/video_llama/common/dist_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":false,"mcp_get_code":{"code_sha256":"643539116e049080"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}