Commits · a346e19df9dd1a9cddde416167732a3edd899d09 · mirrored_repos / MachineLearning / meta-llama / Llama Recipes

This project is mirrored from https://github.com/meta-llama/llama-recipes. Pull mirroring failed 1 month ago.
Repository mirroring has been paused due to too many failed attempts. It can be resumed by a project maintainer or owner.
Last successful update 2 months ago.

Nov 26, 2024
- add 5 together llama notebooks (#798) · a346e19d
  Jeff Tang authored 3 months ago
  
  Unverified
  
  a346e19d
- Add llama 3.2 mmlu, math, gpqa evals to meta_eval harness (#801) · 7ebd68c2
  Kai Wu authored 3 months ago
  
  Unverified
  
  7ebd68c2
- replaced the nba playoff example with The paper Attention Is All You Need in... · 946d73db
  Jeff Tang authored 3 months ago
  
  replaced the nba playoff example with The paper Attention Is All You Need in knowledge_graphs_with_structured_outputs
  946d73db
- path fix · 6dca2157
  Jeff Tang authored 3 months ago
  
  6dca2157
- removed invalid line · 2a710b8a
  Jeff Tang authored 3 months ago
  
  2a710b8a
- typo and link fix · a80440c4
  Jeff Tang authored 3 months ago
  
  a80440c4
- README update · 94682864
  Jeff Tang authored 3 months ago
  
  94682864
- Add gpqa and math evals for instruct models · ab1b1450
  Aidan Do authored 3 months ago
  
  ab1b1450
Nov 23, 2024
- update comment · 6224bd56
  Aidan Do authored 3 months ago
  
  6224bd56
- ensure pretrain_.yaml is udpated · b442625b
  Aidan Do authored 3 months ago
  
  b442625b
- Add mmlu eval for llama 3.2 pretrained models · 4f9050f7
  Aidan Do authored 3 months ago
  
  4f9050f7
Nov 21, 2024
- update descriptions · be983133
  Zain Hasan authored 4 months ago
  
  be983133
- update readme · 8fa428cf
  Zain Hasan authored 4 months ago
  
  8fa428cf
- update readme · 59bc27c0
  Zain Hasan authored 4 months ago
  
  59bc27c0
- add 5 together llama notebooks · 9c2bee07
  Zain Hasan authored 4 months ago
  
  9c2bee07
Nov 20, 2024
- [docs] small typo in eval readme (#796) · 2f72bcec
  Kai Wu authored 4 months ago
  
  Unverified
  
  2f72bcec
- small typo in eval README · 008b8e45
  Jayson Francis authored 4 months ago
  
  008b8e45
- fix typo in auto wrap policy (#793) · de3e32c8
  Kai Wu authored 4 months ago
  
  Unverified
  
  de3e32c8
- All functionality has been consolidated into a single file for... · 7579b61d
  Kai Wu authored 4 months ago
  
  All functionality has been consolidated into a single file for CLI/UI/Checkpointing and Added fix for issue 702 and added code for that as well, added instructions in local_inference /README.md as well (#757)
  Unverified
  
  7579b61d
- add freeze_LLM_only option for mllama finetuning (#791) · e5662e58
  Kai Wu authored 4 months ago
  
  Unverified
  
  e5662e58
- add TogetherNotebookLM recipe (#766) · 39bfabf6
  Jeff Tang authored 4 months ago
  
  Unverified
  
  39bfabf6
- added pydantic to wordlist.txt · d437411c
  Jeff Tang authored 4 months ago
  
  d437411c
Nov 19, 2024
- fix typo in auto wrap policy · a62aff38
  Guanghui Qin authored 4 months ago
  
  Fix a typo. The FSDP wrapper should wrap the `MllamaCrossAttentionDecoderLayer`, which was missing.
  Unverified
  
  a62aff38
- Print model's frozen status after freezing · d31ee18e
  JimChienTW authored 4 months ago
  
  d31ee18e
- added inference instructions in README for easy inferencing · 54269639
  Himanshu Shukla authored 4 months ago
  
  54269639
- shifted the import statement at top · 3ba4b64e
  Himanshu Shukla authored 4 months ago
  
  3ba4b64e
- fixed the issue of everytime login · 2df7d1b6
  Himanshu Shukla authored 4 months ago
  
  2df7d1b6
- Added the huggingface cli feature · db321669
  Himanshu Shukla authored 4 months ago
  
  db321669
- Fix model parameter mismatch by printing parameters before FSDP · d1195a6f
  JimChienTW authored 4 months ago
  
  d1195a6f
- Merge branch 'meta-llama:main' into main · 3e1d9856
  Himanshu Shukla authored 4 months ago
  
  Unverified
  
  3e1d9856
Nov 16, 2024
- colab links fix (#790) · 42504393
  Sanyam Bhutani authored 4 months ago
  
  Unverified
  
  42504393
- update README · f228cb4d
  JimChienTW authored 4 months ago
  
  f228cb4d
- add freeze_LLM_only option for mllama finetuning · 21e8368c
  JimChienTW authored 4 months ago
  
  21e8368c
Nov 15, 2024
- Merge branch 'meta-llama:main' into main · 06ea2a7a
  Himanshu Shukla authored 4 months ago
  
  Unverified
  
  06ea2a7a
- colab links fix · b579bd04
  Jeff Tang authored 4 months ago
  
  b579bd04
Nov 13, 2024
- fix walkthrough.ipynb render (#787) · b9fc1069
  Suraj Subramanian authored 4 months ago
  
  Unverified
  
  b9fc1069
- fix walkthrough.ipynb render · 9c7e1d06
  Suraj Subramanian authored 4 months ago
  
  Unverified
  
  9c7e1d06
Nov 02, 2024
- fixed gradio UI during performing the tests, it is working in this commit · 6b6bb37e
  Himanshu Shukla authored 4 months ago
  
  6b6bb37e
- added working code of CLI/gradio UI/ LoRA weights merge · 20dd4740
  Himanshu Shukla authored 4 months ago
  
  20dd4740
- Renamed file from code-merge-inference.py to multi_modal_infer.py · 24333253
  Himanshu Shukla authored 4 months ago
  
  24333253