Skip to content

Pull requests: OpenAccess-AI-Collective/axolotl

New pull request New
Clear current search query, filters, and sorts
6 Open 393 Closed
6 Open 393 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
Reviews
Filter by reviews
No reviews Review required Approved review Changes requested
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

Allow "weight: 0" in messages to mask them
#1703 by DavidFarago was merged Jun 20, 2024 Loading…
5
improve Pre-Tokenized Dataset docs
#1684 by josharian was merged Jun 26, 2024 Loading…
1
Fix the broken link in README
#1678 by saeedesmaili was merged Jun 3, 2024 Loading…
Fix README quick start example usage model dirs
#1668 by abevoelker was merged May 28, 2024 Loading…
1
Correct name of MixtralBlockSparseTop2MLP (L -> l)
#1667 by seungduk-yanolja was merged May 28, 2024 Loading…
Fix Google Colab notebook 2024-05 ready to merge
#1662 by maciejgryka was merged May 28, 2024 Loading…
Generalizing the chat_template prompt strategy
#1660 by fozziethebeat was merged May 28, 2024 Loading…
1 task done
1
4
Fix Lora config error for Llama3 ready to merge
#1659 by oaishi was merged May 28, 2024 Loading…
1
Fix: ensure correct handling of val_set_size as float or int ready to merge
#1655 by davidecaroselli was merged May 28, 2024 Loading…
1
document how to use share_strategy="no"
#1653 by charlesfrye was merged May 24, 2024 Loading…
1 task done
Enable LoRA+ setting for dpo trainer
#1646 by thepowerfuldeez was merged May 22, 2024 Loading…
Add KTO support
#1640 by benredmond was merged May 20, 2024 Loading…
5
Update tiny-llama qlora.yml addressing eval packing error
#1638 by jaydeepthik was merged May 22, 2024 Loading…
Fix llama3 chat_template (extra <|eot_id|> on last turn)
#1635 by lhl was merged May 21, 2024 Loading…
3
add save_only_model option
#1634 by jquesnelle was merged May 17, 2024 Loading…
add dstack section ready to merge
#1612 by deep-diver was merged May 14, 2024 Loading…
Gradio configuration parameters
#1591 by marijnfs was merged May 6, 2024 Loading…
3
improve tool handling roles
#1587 by winglian was merged May 7, 2024 Loading…
3
FIX: max_length and max_prompt_length was not being sent to ORPOTrainer
#1584 by ali-mosavian was merged May 14, 2024 Loading…
2
FIX: TRL trainer preprocessing step was running in one process
#1583 by ali-mosavian was merged May 3, 2024 Loading…
2
Phi-3 conversation format, example training script and perplexity metric
#1582 by brianfitzgerald was merged Jun 4, 2024 Loading…
9
Pass weakref to model in the SIGINT handler to free up model post train function ready to merge
#1581 by chiragjn was merged May 3, 2024 Loading…
3
feat: exclude mamba blocks for jamba when load8bit ready to merge
#1578 by NanoCode012 was merged May 7, 2024 Loading…
1
2
docs(config.qmd): add loraplus example
#1577 by tpoisonooo was merged May 6, 2024 Loading…
3
Pass deepspeed and fsdp as None explicitly when merging adapters to allow custom device_map
#1575 by chiragjn was merged May 7, 2024 Loading…
6
ProTip! no:milestone will show everything without a milestone.