Ecosyste.ms: Issues
An open API service for providing issue and pull request metadata for open source projects.
GitHub / DAMO-NLP-SG/Video-LLaMA issues and pull requests
#172 - 配置文件位置在本地但是还是提示OSError: Can't load tokenizer for 'bert-base-uncased'. If you were trying to load it from 'https://huggingface.co/models', make sure you don't have a local directory with the same name. Otherwise, make sure 'bert-base-uncased' is the correct path to a directory containing all relevant files for a BertTokenizer tokenizer.
Issue -
State: open - Opened by Asmallsoldier 4 days ago
#171 - Do you have plan to release Video-LLaMA checkpoints with LLaMA 3.1?
Issue -
State: open - Opened by ShramanPramanick about 1 month ago
- 1 comment
#166 - modelling_llama.py
Issue -
State: open - Opened by zeroQiaoba 3 months ago
- 1 comment
#143 - Hugging Face demo runtime error
Issue -
State: closed - Opened by sihoseanhan 7 months ago
- 2 comments
#102 - 预训练的参数设置问题
Issue -
State: open - Opened by xmy0916 about 1 year ago
#101 - 运行demo,需要多大的内存
Issue -
State: open - Opened by FyhSky about 1 year ago
- 2 comments
#100 - After completing the fine-tuning of 'visionbranch stage2', what should be its loss value to be considered as having correctly converged?
Issue -
State: open - Opened by joeking11829 about 1 year ago
- 2 comments
#99 - 运行推理脚本python demo_audiovideo.py,如何指定多个gpu进行推理
Issue -
State: closed - Opened by 765144989 about 1 year ago
- 1 comment
#98 - Output Logit
Issue -
State: open - Opened by Anthony6197 about 1 year ago
#97 - Error(s) in loading state_dict for VideoLLAMA
Issue -
State: open - Opened by tiesanguaixia about 1 year ago
- 5 comments
#96 - Maybe some typo in video_llama_eval_only_vl.yaml
Issue -
State: closed - Opened by tiesanguaixia about 1 year ago
- 1 comment
#95 - Do I need to apply convert_llama_weights_to_hf.py to the original 7B LLaMA weight?
Issue -
State: closed - Opened by tiesanguaixia about 1 year ago
- 1 comment
#94 - stage2 webvid数据集问题
Issue -
State: closed - Opened by Dylandtt about 1 year ago
- 3 comments
#93 - 在预训练和fine-tune Video-LLaMA时,使用的数据是否包含一些专门用于Video Captioning任务的数据集呢?比如MSVD, MSR-VTT, VATEX.
Issue -
State: closed - Opened by tiesanguaixia about 1 year ago
- 1 comment
#92 - llama_proj_model not passed to __init__
Issue -
State: closed - Opened by daahuang about 1 year ago
- 1 comment
#91 - 只用video做inference
Issue -
State: closed - Opened by Anthony6197 about 1 year ago
- 1 comment
#90 - visionbranch stage2 finetune with LLaMA-2 13B, A100 80GB is out of GPU memory.
Issue -
State: closed - Opened by joeking11829 about 1 year ago
- 2 comments
#89 - LLaMA2 Video only微调的问题
Issue -
State: closed - Opened by CyrilSterling about 1 year ago
- 1 comment
#88 - Failed to run Billa7B-SFT and error complains wrong shape to reshape position_ids
Issue -
State: open - Opened by dongxiao92 about 1 year ago
#87 - Finetuning each branch
Issue -
State: closed - Opened by liveseongho about 1 year ago
- 1 comment
#86 - visionbranch_stage1预训练webvid数据集问题
Issue -
State: open - Opened by RANYABING about 1 year ago
- 1 comment
#85 - visionbranch stage2收敛问题
Issue -
State: open - Opened by octopusszzy about 1 year ago
#84 - visionbranch stage2 微调问题
Issue -
State: closed - Opened by Givyuscss about 1 year ago
- 14 comments
#83 - [Feature Request] Support InternLM
Issue -
State: closed - Opened by vansinhu about 1 year ago
- 1 comment
#82 - CPU support
Pull Request -
State: open - Opened by esteininger about 1 year ago
- 1 comment
#81 - Training model
Issue -
State: open - Opened by Remosy about 1 year ago
- 2 comments
#80 - def upload_video() in video_llama\conversation\conversation_video.py seems wrong?
Issue -
State: closed - Opened by yjwang346 about 1 year ago
- 1 comment
#79 - About commercial use of weights and code in case of llama2
Issue -
State: closed - Opened by codgas about 1 year ago
- 1 comment
#78 - Facing issue with Internal: src/sentencepiece_processor.cc(1101) [model_proto->ParseFromArray(serialized.data(), serialized.size())]
Issue -
State: closed - Opened by HerculesRay about 1 year ago
- 1 comment
#77 - 可以提供一个infer的脚本吗?非gradio demo的那种
Issue -
State: open - Opened by CaicaiJason about 1 year ago
- 3 comments
#76 - HFValidationError using Video-LLaMA-2-7B-Finetuned
Issue -
State: closed - Opened by amy011872 about 1 year ago
- 3 comments
#75 - cuda issues: docker
Issue -
State: closed - Opened by mtthwryn about 1 year ago
- 1 comment
#74 - demo启动后报错,这个是什么原因嗯?
Issue -
State: closed - Opened by CaicaiJason about 1 year ago
- 4 comments
#73 - RuntimeError: Internal: src/sentencepiece_processor.cc(1101) [model_proto->ParseFromArray(serialized.data(), serialized.size())]
Issue -
State: closed - Opened by mtthwryn about 1 year ago
- 8 comments
#72 - 可以看一下最终的文件树结构吗?
Issue -
State: open - Opened by Dylandtt about 1 year ago
#71 - 考虑加一下deepspeed吗?
Issue -
State: open - Opened by xmy0916 about 1 year ago
- 1 comment
#70 - Do you have plan to release Qwen-7B version
Issue -
State: closed - Opened by FredHuang16 about 1 year ago
- 1 comment
#69 - MiniGPT的作用
Issue -
State: closed - Opened by Ozawakun97 about 1 year ago
- 1 comment
#68 - Errors using LLaMA2 weights
Issue -
State: closed - Opened by amy011872 about 1 year ago
- 1 comment
#67 - demo运行
Issue -
State: open - Opened by luyao-cv about 1 year ago
- 9 comments
#65 - AssertionError: Unknown model type llama_v2
Issue -
State: closed - Opened by alvaro-budria about 1 year ago
- 1 comment
#64 - demo无法正常运行?
Issue -
State: closed - Opened by yingfei1016 about 1 year ago
- 3 comments
#63 - 咨询 13B 的 audio-Language Branch 发布计划
Issue -
State: closed - Opened by DreamCatcher-cai about 1 year ago
- 1 comment
#62 - config相关问题
Issue -
State: closed - Opened by yypurpose about 1 year ago
- 2 comments
#60 - Run Video-LLaMA on A10 24GB
Issue -
State: closed - Opened by alvaro-budria about 1 year ago
- 1 comment
#59 - [Stage2finetune数据集]VideoChat instruction data使用疑问
Issue -
State: closed - Opened by aopolin-lv about 1 year ago
- 3 comments
#58 - Language model is loading really slow.
Issue -
State: closed - Opened by somepago about 1 year ago
- 1 comment
#57 - No place to input in the Demo
Issue -
State: closed - Opened by ChaofanTao about 1 year ago
- 4 comments
#56 - 推理时forward提取audio是在哪里?
Issue -
State: closed - Opened by fanbooo about 1 year ago
- 2 comments
#55 - the ability of sentiment analysis
Issue -
State: closed - Opened by liziming5353 about 1 year ago
- 2 comments
#54 - Any plan to incorporate Llama 2?
Issue -
State: closed - Opened by SushantGautam about 1 year ago
- 1 comment
#53 - finetune-billa7b-zh模型推理错误
Issue -
State: open - Opened by PeterMao11 about 1 year ago
- 2 comments
#52 - 模型输出截断
Issue -
State: closed - Opened by xmy0916 about 1 year ago
- 1 comment
#51 - 是否提供基于ziya的inference code?
Issue -
State: closed - Opened by liu6381810 about 1 year ago
- 1 comment
#50 - Inquiry about “max_epoch” values for pre-training and fine-tuning
Issue -
State: closed - Opened by YasmineXXX about 1 year ago
- 4 comments
#49 - Could you please share the code to generate the instruct data?
Issue -
State: open - Opened by aixiaodewugege about 1 year ago
#48 - 搭建demo返回错误的结果
Issue -
State: closed - Opened by PeterMao11 about 1 year ago
- 6 comments
#47 - imagebind_ckpt_path这个应该如何配置?去哪里下载吗?
Issue -
State: closed - Opened by yaakua about 1 year ago
- 8 comments
#46 - Is is possible to insturct-finetune Video-LLaMA in 8 * 24 GB Nvidia A5000
Issue -
State: closed - Opened by Fr0zenCrane about 1 year ago
- 2 comments
#45 - Can I Instruction Fine-tuning the model with my dataset using 4*3090?
Issue -
State: closed - Opened by aixiaodewugege about 1 year ago
- 4 comments
#44 - why keep "###" before instruct text?
Issue -
State: closed - Opened by Cescfangs about 1 year ago
- 6 comments
#43 - how much data was used in the fine-tuning stage?
Issue -
State: closed - Opened by YasmineXXX about 1 year ago
#42 - Which conference do you submit this paper?
Issue -
State: closed - Opened by jacob-kang about 1 year ago
- 1 comment
#41 - Update README.md
Pull Request -
State: closed - Opened by SushantGautam about 1 year ago
- 2 comments
#40 - key error['API-TOKEN']
Issue -
State: closed - Opened by justinwking about 1 year ago
- 4 comments
#39 - Asking for a simple script to get text and video features
Issue -
State: closed - Opened by ymartin-mw about 1 year ago
- 1 comment
#38 - 虽然git里发布了13b的llama模型,但audio模型还是7b的,这样启动demo程序,会报错,维度不兼容,咋整?
Issue -
State: closed - Opened by willzli about 1 year ago
- 2 comments
#37 - can not install pytorch 1.12.1
Issue -
State: closed - Opened by willzli about 1 year ago
#36 - If i use vicuna7b_audiobranch, Is the model compatible to run vicuna13b-v2 ?
Issue -
State: closed - Opened by willzli about 1 year ago
- 2 comments
#35 - Quantize Video-LLama with SqueezeLLM
Issue -
State: closed - Opened by vegax87 over 1 year ago
- 1 comment
#34 - formats: no handler for file extension `mp4'
Issue -
State: closed - Opened by SushantGautam over 1 year ago
- 5 comments
#33 - Differences in the checkpoint size
Issue -
State: closed - Opened by SushantGautam over 1 year ago
- 1 comment
#32 - how to get the cc3m filter_cap.json data
Issue -
State: closed - Opened by PeterMao11 over 1 year ago
- 1 comment
#31 - video_llama_eval_withaudio.yaml issue
Issue -
State: closed - Opened by imfurkaann over 1 year ago
- 1 comment
#30 - The effect gap is too large
Issue -
State: closed - Opened by DeerEyre over 1 year ago
- 1 comment
#29 - transformers version issue
Issue -
State: closed - Opened by yzxyzh over 1 year ago
- 1 comment
#28 - size mismatch error
Issue -
State: closed - Opened by feymanwang over 1 year ago
- 12 comments
#27 - frame rate and duration of videos
Issue -
State: closed - Opened by amirsafaei over 1 year ago
- 2 comments
#26 - Update video_llama_stage1_pretrain.yaml to prevent AttributeError:
Pull Request -
State: closed - Opened by SushantGautam over 1 year ago
#25 - Explanation about "data" log parameter
Issue -
State: closed - Opened by SushantGautam over 1 year ago
- 3 comments
#24 - which checkpoint should i write?minigpt4?audio.pth or visual.pth?
Issue -
State: closed - Opened by DeerEyre over 1 year ago
- 3 comments
#23 - Update README.md
Pull Request -
State: closed - Opened by IceTheCoder over 1 year ago
- 1 comment
#22 - Update README.md
Pull Request -
State: closed - Opened by eltociear over 1 year ago
- 1 comment
#21 - Prevent variable "atts_img" referred before assignment error on training script on README page.
Pull Request -
State: closed - Opened by SushantGautam over 1 year ago
#20 - Update environment.yml
Pull Request -
State: closed - Opened by Rajathbharadwaj over 1 year ago
- 1 comment
#19 - When the "[06.08] 🚀🚀 Next BIG update is on the way!!" will be available? today is [06, 08]
Issue -
State: closed - Opened by tensorboy over 1 year ago
- 1 comment
#17 - the image size is defined in .yaml files but they are also manually set here and there
Issue -
State: closed - Opened by amirsafaei over 1 year ago
- 2 comments
#16 - Great work!
Issue -
State: closed - Opened by wyzjack over 1 year ago
- 3 comments
#15 - The link for pretrain-vicuna7b is invalid, the weight is missing.
Issue -
State: closed - Opened by AcodeC over 1 year ago
- 1 comment
#14 - what is "The video contains {len(indices)} frames sampled at {sec} seconds. " added in text prompt for?
Issue -
State: closed - Opened by rese1f over 1 year ago
- 1 comment
#13 - miss import
Issue -
State: closed - Opened by rese1f over 1 year ago
- 1 comment
#12 - IndentationError in train_configs/video_llama_stage2_finetune.yaml
Issue -
State: closed - Opened by rese1f over 1 year ago
- 2 comments
#11 - Don't use miniGPT4 to init.
Issue -
State: closed - Opened by chenxianzhao over 1 year ago
#10 - The config of finetuning video-llama with the video instruction data?
Issue -
State: closed - Opened by xuhzyy over 1 year ago
- 1 comment
#9 - The amount of updated parameters during stage1 and stage2 ?
Issue -
State: closed - Opened by cnxupupup over 1 year ago
- 1 comment
#8 - prompts/alignment_video.txt is missing
Issue -
State: closed - Opened by xmy0916 over 1 year ago
- 1 comment
#7 - Paper.pdf is missing.
Issue -
State: closed - Opened by jacob-kang over 1 year ago
- 2 comments
#6 - I'm also training this... I haven't downloaded webvid2.5m yet and then I found that you have done everything I want to do, hahahaha
Issue -
State: closed - Opened by xmy0916 over 1 year ago
- 1 comment
#5 - Great job! Will you release the machine-translated VideoChat instructions data?
Issue -
State: open - Opened by xuhzyy over 1 year ago