Ecosyste.ms: Issues
An open API service for providing issue and pull request metadata for open source projects.
GitHub / LargeWorldModel/LWM issues and pull requests
#83 - Removing Truncation/Padding during Prefix Tokenization
Issue -
State: open - Opened by tsrikris 2 months ago
#82 - Asking to pad but the tokenizer does not have a padding token
Issue -
State: open - Opened by gabeweisz 3 months ago
#81 - checkpoints for run_sample_video.sh
Issue -
State: open - Opened by junsukha 4 months ago
#80 - I wonder if you will release the tokenized dataset.
Issue -
State: open - Opened by lzy-ps 4 months ago
#79 - A question on your implementation of decoder phase of llama
Issue -
State: open - Opened by wangtianxia-sjtu 4 months ago
#78 - Hang in vision_generation.py with newer versions of Jax
Issue -
State: closed - Opened by gabeweisz 5 months ago
- 1 comment
#77 - Error while running bash command: run_sample_video.sh | Error: "TypeError: missing a required argument: 'segment_ids'"
Issue -
State: open - Opened by samitm-123 5 months ago
- 6 comments
#76 - Fix step idx logging and eval frequency
Pull Request -
State: open - Opened by ntoxeg 5 months ago
#75 - Quantize model weights
Issue -
State: open - Opened by befman123 6 months ago
#74 - Any consideration on why use 4 sp & 32 tp?
Issue -
State: open - Opened by ParanoidHW 7 months ago
#74 - Any consideration on why use 4 sp & 32 tp?
Issue -
State: open - Opened by ParanoidHW 7 months ago
#73 - vison-language model training data example for videos
Issue -
State: open - Opened by Minyoung1005 7 months ago
#73 - vison-language model training data example for videos
Issue -
State: open - Opened by Minyoung1005 7 months ago
#72 - fix: check aux length to avoid exception
Pull Request -
State: open - Opened by RealHurrison 7 months ago
#72 - fix: check aux length to avoid exception
Pull Request -
State: open - Opened by RealHurrison 7 months ago
#71 - Question about loading LLaMA-2 7B on the LLM context extension stage
Issue -
State: open - Opened by ImKeTT 7 months ago
#71 - Question about loading LLaMA-2 7B on the LLM context extension stage
Issue -
State: open - Opened by ImKeTT 7 months ago
#70 - Interesting Problems of Accuracy & Inference Speed with run_eval_needle.sh
Issue -
State: open - Opened by Treemann 7 months ago
#70 - Interesting Problems of Accuracy & Inference Speed with run_eval_needle.sh
Issue -
State: open - Opened by Treemann 7 months ago
#69 - what is the "_missing_keys"?
Issue -
State: open - Opened by wangli68 7 months ago
#69 - what is the "_missing_keys"?
Issue -
State: open - Opened by wangli68 7 months ago
#68 - Fix logging issue in llama.py
Pull Request -
State: open - Opened by Treemann 7 months ago
#68 - Fix logging issue in llama.py
Pull Request -
State: open - Opened by Treemann 7 months ago
#67 - vision model initialization
Issue -
State: open - Opened by wangli68 7 months ago
#67 - vision model initialization
Issue -
State: open - Opened by wangli68 7 months ago
#66 - Minimum GPU memory capacity required to run
Issue -
State: closed - Opened by yumianhuli2 7 months ago
- 1 comment
#66 - Minimum GPU memory capacity required to run
Issue -
State: closed - Opened by yumianhuli2 7 months ago
- 1 comment
#65 - Weight conversion scripts
Issue -
State: open - Opened by fmmoret 8 months ago
- 1 comment
#64 - Great work! Any plan for the vision-language models in Pytorch?
Issue -
State: open - Opened by WilTay1 8 months ago
#64 - Great work! Any plan for the vision-language models in Pytorch?
Issue -
State: open - Opened by WilTay1 8 months ago
#63 - Can it be used in the environment H100 ?
Issue -
State: open - Opened by wangli68 8 months ago
#63 - Can it be used in the environment H100 ?
Issue -
State: open - Opened by wangli68 8 months ago
#62 - ValueError: Incompatible shapes for broadcasting: (2, 1, 1, 526464) and requested shape (2, 1, 32768, 32768)
Issue -
State: open - Opened by scsonic 8 months ago
- 2 comments
#62 - ValueError: Incompatible shapes for broadcasting: (2, 1, 1, 526464) and requested shape (2, 1, 32768, 32768)
Issue -
State: open - Opened by scsonic 8 months ago
- 2 comments
#61 - DP FSDP & SP
Issue -
State: open - Opened by wangpengfei1013 8 months ago
#61 - DP FSDP & SP
Issue -
State: open - Opened by wangpengfei1013 8 months ago
#60 - RESOURCE_EXHAUSTED: XLA:TPU compile permanent
Issue -
State: open - Opened by infocodiste 8 months ago
#60 - RESOURCE_EXHAUSTED: XLA:TPU compile permanent
Issue -
State: open - Opened by infocodiste 8 months ago
#59 - AttributeError: module 'jax.numpy' has no attribute 'DeviceArray' when run sample_video.sh
Issue -
State: open - Opened by ersanliqiao 8 months ago
#58 - Request for publicizing the LWM-1K/8K JAX or PyTorch model
Issue -
State: open - Opened by iamlockelightning 8 months ago
#58 - Request for publicizing the LWM-1K/8K JAX or PyTorch model
Issue -
State: open - Opened by iamlockelightning 8 months ago
#57 - Does support text to image and video geneation training ?
Issue -
State: open - Opened by ersanliqiao 8 months ago
#57 - Does support text to image and video geneation training ?
Issue -
State: open - Opened by ersanliqiao 8 months ago
#56 - How to setup conversation with vision chat?
Issue -
State: open - Opened by kylekam 8 months ago
- 1 comment
#56 - How to setup conversation with vision chat?
Issue -
State: open - Opened by kylekam 8 months ago
- 1 comment
#55 - pytorch model & ring attention
Issue -
State: open - Opened by LzhinFdu 8 months ago
- 4 comments
#55 - pytorch model & ring attention
Issue -
State: open - Opened by LzhinFdu 8 months ago
- 4 comments
#54 - run run_sample_video.sh config
Issue -
State: open - Opened by wangli68 8 months ago
#54 - run run_sample_video.sh config
Issue -
State: open - Opened by wangli68 8 months ago
#53 - run run_samle_image.sh error
Issue -
State: open - Opened by wangli68 8 months ago
#52 - Getting memory error while running run_vision.sh
Issue -
State: open - Opened by PraneethKumar126 9 months ago
#52 - Getting memory error while running run_vision.sh
Issue -
State: open - Opened by PraneethKumar126 9 months ago
#51 - When will you support text to video in pytorch?
Issue -
State: open - Opened by 459737087 9 months ago
#51 - When will you support text to video in pytorch?
Issue -
State: open - Opened by 459737087 9 months ago
#50 - `model_max_length` why is it 2048?
Issue -
State: open - Opened by denadai2 9 months ago
- 1 comment
#50 - `model_max_length` why is it 2048?
Issue -
State: open - Opened by denadai2 9 months ago
- 1 comment
#49 - LlamaForCausalLM requires the PyTorch library but it was not found in your environment
Issue -
State: closed - Opened by 459737087 9 months ago
- 1 comment
#49 - LlamaForCausalLM requires the PyTorch library but it was not found in your environment
Issue -
State: closed - Opened by 459737087 9 months ago
- 1 comment
#48 - ValueError: bytes is too large when running scripts/run_train_text.sh
Issue -
State: open - Opened by liu21yd 9 months ago
- 1 comment
#47 - Example Data for vision language training (What is the format?)
Issue -
State: open - Opened by EthanC111 9 months ago
- 1 comment
#47 - Example Data for vision language training (What is the format?)
Issue -
State: open - Opened by EthanC111 9 months ago
- 1 comment
#46 - How to set the input length parameter to support long context window e.g. 256k inputs?
Issue -
State: open - Opened by dzyjjpy 9 months ago
- 1 comment
#46 - How to set the input length parameter to support long context window e.g. 256k inputs?
Issue -
State: open - Opened by dzyjjpy 9 months ago
- 1 comment
#45 - We need API
Issue -
State: open - Opened by lueluelue2006 9 months ago
#45 - We need API
Issue -
State: open - Opened by lueluelue2006 9 months ago
#44 - NCCL Error when running the Jax LWM-Chat-32K-Jax
Issue -
State: closed - Opened by yfb-xieyu 9 months ago
- 1 comment
#44 - NCCL Error when running the Jax LWM-Chat-32K-Jax
Issue -
State: closed - Opened by yfb-xieyu 9 months ago
- 1 comment
#43 - error when run run_sample_img.sh
Issue -
State: closed - Opened by onmygame 9 months ago
- 1 comment
#43 - error when run run_sample_img.sh
Issue -
State: closed - Opened by onmygame 9 months ago
- 1 comment
#42 - NCCL Error when running the Jax LWM-Chat-1M-Jax
Issue -
State: open - Opened by jeffchy 9 months ago
#42 - NCCL Error when running the Jax LWM-Chat-1M-Jax
Issue -
State: open - Opened by jeffchy 9 months ago
#41 - AttributeError: module 'jax.numpy' has no attribute 'DeviceArray'
Issue -
State: closed - Opened by zhongJY1998 9 months ago
- 1 comment
#41 - AttributeError: module 'jax.numpy' has no attribute 'DeviceArray'
Issue -
State: closed - Opened by zhongJY1998 9 months ago
- 1 comment
#40 - TypeError: unsupported operand type(s) for |: 'type' and 'NoneType'
Issue -
State: closed - Opened by dzyjjpy 9 months ago
- 5 comments
#40 - TypeError: unsupported operand type(s) for |: 'type' and 'NoneType'
Issue -
State: closed - Opened by dzyjjpy 9 months ago
- 5 comments
#39 - Mesh dim setting error
Issue -
State: closed - Opened by yfb-xieyu 9 months ago
- 1 comment
#39 - Mesh dim setting error
Issue -
State: closed - Opened by yfb-xieyu 9 months ago
- 1 comment
#38 - Update README.md
Pull Request -
State: open - Opened by I-E-E-E 9 months ago
#37 - out of memory error
Issue -
State: closed - Opened by lucky2046 9 months ago
- 3 comments
#37 - out of memory error
Issue -
State: closed - Opened by lucky2046 9 months ago
- 3 comments
#36 - bash run_vision_chat.sh -- cause flax.errors.ScopeParamNotFoundError: Could not find parameter named "embedding" in scope "/transformer/wte"
Issue -
State: open - Opened by jackyin68 9 months ago
- 6 comments
#36 - bash run_vision_chat.sh -- cause flax.errors.ScopeParamNotFoundError: Could not find parameter named "embedding" in scope "/transformer/wte"
Issue -
State: open - Opened by jackyin68 9 months ago
- 6 comments
#35 - Request for guidance on fine-tuning a model with custom data
Issue -
State: open - Opened by awzhgw 9 months ago
- 2 comments
#35 - Request for guidance on fine-tuning a model with custom data
Issue -
State: open - Opened by awzhgw 9 months ago
- 2 comments
#34 - Great work! Any plan to train a smaller version, e.g. around 3B?
Issue -
State: open - Opened by StarCycle 9 months ago
- 4 comments
#34 - Great work! Any plan to train a smaller version, e.g. around 3B?
Issue -
State: open - Opened by StarCycle 9 months ago
- 4 comments
#33 - Why always use float32 precision in training?
Issue -
State: closed - Opened by cizhenshi 9 months ago
- 2 comments
#33 - Why always use float32 precision in training?
Issue -
State: closed - Opened by cizhenshi 9 months ago
- 2 comments
#32 - Any experiments on reasoning or world modeling ?
Issue -
State: open - Opened by Randolph-zeng 9 months ago
- 1 comment
#32 - Any experiments on reasoning or world modeling ?
Issue -
State: open - Opened by Randolph-zeng 9 months ago
- 1 comment
#31 - can support whole dataset ?
Issue -
State: open - Opened by awzhgw 9 months ago
#31 - can support whole dataset ?
Issue -
State: open - Opened by awzhgw 9 months ago
#30 - can support mixtral 7Bx8 model ?
Issue -
State: closed - Opened by awzhgw 9 months ago
- 1 comment
#30 - can support mixtral 7Bx8 model ?
Issue -
State: closed - Opened by awzhgw 9 months ago
- 1 comment
#29 - is there any schedule for online huggingface demo?
Issue -
State: open - Opened by cyj95 9 months ago
#29 - is there any schedule for online huggingface demo?
Issue -
State: open - Opened by cyj95 9 months ago
#28 - Pytorch version of the vision model
Issue -
State: open - Opened by aamir-gmail 9 months ago
- 4 comments
#28 - Pytorch version of the vision model
Issue -
State: open - Opened by aamir-gmail 9 months ago
- 4 comments
#27 - LWM-Chat-1M PytTorch version and also a gradio demo interface please
Issue -
State: open - Opened by FurkanGozukara 9 months ago
#27 - LWM-Chat-1M PytTorch version and also a gradio demo interface please
Issue -
State: open - Opened by FurkanGozukara 9 months ago