Skip to content

Issues: ml-explore/mlx-examples

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

118 Open 457 Closed
118 Open 457 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Issues list

fine-tuned T5 model fails to load after recent change
#1034 opened Oct 12, 2024 by msolo
Architecture Requests for Mamba
#1030 opened Oct 10, 2024 by hg0428
3
T5 tokenizer decoding error with CodeT5+ bug Something isn't working
#1021 opened Oct 9, 2024 by zcbenz
1
Support for Nvidia Nemotron and NVLM 1.0 enhancement New feature or request
#1007 opened Oct 1, 2024 by vlbosch
1
I tried madlad400, but there is a problem with the output if it is float16
#980 opened Sep 7, 2024 by otmb
5
[Feature Request] MLX_lm.cache_prompt | Save cached_prompt as plaintext in the kv-cache-file metadata enhancement New feature or request
#978 opened Sep 6, 2024 by mark-lord
linting / type definitions
#975 opened Sep 4, 2024 by Jonathan-Dobson
It's possible to install mlx-lm with dockerfile?
#968 opened Aug 30, 2024 by NicoNicoNico123
KeyError: 'llama.context_length'
#966 opened Aug 30, 2024 by wuhongsheng
2
[Feature Request] MLX_lm: add support for GLM4 family of language models
#952 opened Aug 25, 2024 by Nekuromento
2
Mlx generate text, by default halusonates more
#947 opened Aug 21, 2024 by kishoretvk
3
[FeatureRequest] Support for prompt fine-tuning
#930 opened Aug 12, 2024 by octavianBordeanu
[FeatureRequest] Support Qwen2-Audio model
#928 opened Aug 10, 2024 by lin72h
Support example for SpeechT5 model?
#921 opened Aug 6, 2024 by yukiarimo
[Model Request] Support DCLM-7B enhancement New feature or request
#908 opened Jul 24, 2024 by Jiaqi0602
2
Support for nanogpt (and gpt-j)
#897 opened Jul 19, 2024 by uogbuji
support for mamba 2 (Codestral mamba) #859
#893 opened Jul 17, 2024 by vovw
1
Support model with mlx - stable video diffusion
#883 opened Jul 10, 2024 by mgierschdev
2
Feature Request - Beam Search Decoder
#846 opened Jun 23, 2024 by r4ghu
iterate_batches in mlx_lm's Lora trainer is discarding the remainder dataset items (modulo batch size) enhancement New feature or request
#843 opened Jun 19, 2024 by chimezie
1
Fusing adapters with llama3 cause bad performances
#832 opened Jun 11, 2024 by Timelessprod
11
Proposal: Add mypy to .pre-commit-config.yml enhancement New feature or request
#829 opened Jun 10, 2024 by wangkuiyi
1
2
[Feature] Export Lora Adapters as GGML
#816 opened Jun 5, 2024 by rmarnold
3
[Feature Request] Add support for logprobs to the mlx_lm server
#791 opened May 21, 2024 by chimezie
3
CLIP Tokenizer unable to take text of unequal length (or token length)
#787 opened May 19, 2024 by kechan
7
ProTip! no:milestone will show everything without a milestone.