yandex/YaLM-100B issues and pull requests

#34 - gguf / mlx format?

Issue - State: open - Opened by alexander-potemkin 10 months ago

#34 - gguf / mlx format?

Issue - State: open - Opened by alexander-potemkin 10 months ago

#33 - Why usage ssh-agent and openssh-client package in docker

Issue - State: open - Opened by spanarek over 1 year ago

#33 - Why usage ssh-agent and openssh-client package in docker

Issue - State: open - Opened by spanarek over 1 year ago

#32 - Update LICENSE

Pull Request - State: closed - Opened by IgorDuino over 1 year ago

#32 - Update LICENSE

Pull Request - State: closed - Opened by IgorDuino over 1 year ago

#31 - Timeout on 8 x RTX A6000

Issue - State: open - Opened by andrewerf over 1 year ago - 2 comments

#31 - Timeout on 8 x RTX A6000

Issue - State: open - Opened by andrewerf over 1 year ago - 2 comments

#30 - How to use it with LangChain?

Issue - State: open - Opened by tonymacx86PRO over 1 year ago - 2 comments

#30 - How to use it with LangChain?

Issue - State: open - Opened by tonymacx86PRO over 1 year ago - 2 comments

#29 - Request to Open "Russian Pile" Dataset for Public Access

Issue - State: open - Opened by mgrankin over 1 year ago

#28 - Citation bibtex?

Issue - State: closed - Opened by Guitaricet almost 2 years ago - 2 comments

#28 - Citation bibtex?

Issue - State: closed - Opened by Guitaricet almost 2 years ago - 2 comments

#27 - Provide pruned version for weaker hardware

Issue - State: open - Opened by CommanderTvis almost 2 years ago - 2 comments

#27 - Provide pruned version for weaker hardware

Issue - State: open - Opened by CommanderTvis almost 2 years ago - 2 comments

#26 - Has anyone deployed it on 10x 3090 ? Or any similar configuration?

Issue - State: open - Opened by AlexanderKozhevin about 2 years ago - 1 comment

#26 - Has anyone deployed it on 10x 3090 ? Or any similar configuration?

Issue - State: open - Opened by AlexanderKozhevin about 2 years ago - 1 comment

#25 - Is there any plans for making cloud service?

Issue - State: open - Opened by AlexanderKozhevin about 2 years ago - 1 comment

#25 - Is there any plans for making cloud service?

Issue - State: open - Opened by AlexanderKozhevin about 2 years ago - 1 comment

#24 - PCI x1 or PCI x16 for GPU

Issue - State: open - Opened by hostingmydata about 2 years ago

#24 - PCI x1 or PCI x16 for GPU

Issue - State: open - Opened by hostingmydata about 2 years ago

#23 - NCCL error

Issue - State: closed - Opened by ZiqianXie about 2 years ago - 1 comment

#22 - CUDA out of memory

Issue - State: closed - Opened by Aspector1 over 2 years ago - 6 comments

#21 - No mention of `bfloat16` in source, and yet weights are `bfloat16`

Issue - State: open - Opened by lostmsu over 2 years ago

#21 - No mention of `bfloat16` in source, and yet weights are `bfloat16`

Issue - State: open - Opened by lostmsu over 2 years ago

#20 - Would it be possible to run the model on single A100 (40GB) or 2xV100 (32GB) ?

Issue - State: closed - Opened by alkavan over 2 years ago - 2 comments

#20 - Would it be possible to run the model on single A100 (40GB) or 2xV100 (32GB) ?

Issue - State: closed - Opened by alkavan over 2 years ago - 2 comments

#19 - Can it be launched on usual VPS? For example, 6 CPU 16 RAM (usual chips)

Issue - State: open - Opened by CombainerA19 over 2 years ago - 2 comments

#19 - Can it be launched on usual VPS? For example, 6 CPU 16 RAM (usual chips)

Issue - State: open - Opened by CombainerA19 over 2 years ago - 2 comments

#18 - Could you share the md5 value for those checkpoints?

Issue - State: closed - Opened by OleNet over 2 years ago - 2 comments

#18 - Could you share the md5 value for those checkpoints?

Issue - State: closed - Opened by OleNet over 2 years ago - 2 comments

#16 - Fix readme typo

Pull Request - State: closed - Opened by erjanmx over 2 years ago

#16 - Fix readme typo

Pull Request - State: closed - Opened by erjanmx over 2 years ago

#15 - AWS

Issue - State: open - Opened by githubuser100007 over 2 years ago - 1 comment

#15 - AWS

Issue - State: open - Opened by githubuser100007 over 2 years ago - 1 comment

#14 - Run on networked nodes

Issue - State: open - Opened by ExtraE113 over 2 years ago

#14 - Run on networked nodes

Issue - State: open - Opened by ExtraE113 over 2 years ago

#13 - How did you used LAMB optimizer with ZeRO CPU offload?

Issue - State: closed - Opened by ghosthamlet over 2 years ago - 2 comments

#13 - How did you used LAMB optimizer with ZeRO CPU offload?

Issue - State: closed - Opened by ghosthamlet over 2 years ago - 2 comments

#12 - Added a .torrent file for weights

Pull Request - State: open - Opened by lostmsu over 2 years ago - 3 comments

#11 - Привет

Issue - State: closed - Opened by DedP0tap over 2 years ago - 2 comments

#10 - Model dataset irregularity

Issue - State: closed - Opened by joshlk over 2 years ago

#10 - Model dataset irregularity

Issue - State: closed - Opened by joshlk over 2 years ago

#9 - Possible to run on 8 x 24GB 3090?

Issue - State: open - Opened by hobodrifterdavid over 2 years ago - 3 comments

#9 - Possible to run on 8 x 24GB 3090?

Issue - State: open - Opened by hobodrifterdavid over 2 years ago - 3 comments

#8 - [NL] token

Issue - State: closed - Opened by TatianaShavrina over 2 years ago - 2 comments

#8 - [NL] token

Issue - State: closed - Opened by TatianaShavrina over 2 years ago - 2 comments

#7 - ZeRO 3 NVMe Offload?

Issue - State: closed - Opened by Vbansal21 over 2 years ago - 9 comments

#7 - ZeRO 3 NVMe Offload?

Issue - State: closed - Opened by Vbansal21 over 2 years ago - 9 comments

#6 - PowerShell download script

Pull Request - State: open - Opened by lostmsu over 2 years ago

#6 - PowerShell download script

Pull Request - State: open - Opened by lostmsu over 2 years ago

#5 - Dataset information

Issue - State: closed - Opened by finetunej over 2 years ago - 2 comments

#4 - YaLm

Issue - State: closed - Opened by Sigma2398 over 2 years ago - 1 comment

#4 - YaLm

Issue - State: closed - Opened by Sigma2398 over 2 years ago - 1 comment

#3 - Online examples

Issue - State: open - Opened by Slauta over 2 years ago - 9 comments

#3 - Online examples

Issue - State: open - Opened by Slauta over 2 years ago - 9 comments

#2 - Evaluation benchmarks (lm-eval-harness)

Issue - State: open - Opened by justheuristic over 2 years ago

#2 - Evaluation benchmarks (lm-eval-harness)

Issue - State: open - Opened by justheuristic over 2 years ago

#1 - Better seed :)

Pull Request - State: open - Opened by e0xextazy over 2 years ago

#1 - Better seed :)

Pull Request - State: open - Opened by e0xextazy over 2 years ago

GitHub / yandex/YaLM-100B issues and pull requests