10 Pull requests merged by 6 people

• Update Step-1 PDF-Pre-Processing-Logic.ipynb

  #756 merged Oct 29, 2024

• Quickstart docs: Fix path to location of dict for custom datasets

  #755 merged Oct 29, 2024

• Update hello_llama_cloud.ipynb

  #754 merged Oct 29, 2024

• Added a Gradio UI for multi-modal inferencing using Llama 3.2 Vision/

  #718 merged Oct 28, 2024

• Update hello_llama_cloud.ipynb

  #753 merged Oct 28, 2024

• Fix minor grammatical errors

  #748 merged Oct 28, 2024

• Small notes on next steps

  #746 merged Oct 27, 2024

• Notebook llama

  #739 merged Oct 26, 2024

• Update wordlist.txt

  #745 merged Oct 25, 2024

• Append epoch rather than best val. loss to val_loss

  #744 merged Oct 24, 2024

5 Pull requests opened by 4 people

• add support for ingesting content from websites, audio files, YouTube, etc.

  #750 opened Oct 28, 2024

• Added fix for issue 702 and added code for that as well, added instructions in LLM_finetuning_overview.md as well

  #757 opened Oct 29, 2024

• Update Step-1 PDF-Pre-Processing-Logic.ipynb

  #758 opened Oct 29, 2024

• fix "INPUT_FILE" path and missing variable "processed_text"

  #759 opened Oct 30, 2024

• 1. fixed "INPUT_FILE" path 2. fix create_word_bounded_chunks before read in the text variables 3) processed_text not definedPatch 1

  #760 opened Oct 30, 2024

4 Issues closed by 3 people

• Add how to do inferencing of Llama3.2 Vision after inferencing

  #734 closed Oct 29, 2024

• Not able to save trained model

  #752 closed Oct 28, 2024

• Prompt template for agents with multiple tools and states + Positioning of info in prompts

  #561 closed Oct 23, 2024

• Mismatch in Llama Guard 2 prompt between llama.meta.com and code - `begin_text`

  #617 closed Oct 23, 2024

2 Issues opened by 2 people

• Project license?

  #749 opened Oct 28, 2024

• Project summary should say what it does

  #747 opened Oct 27, 2024

9 Unresolved conversations

Sometimes conversations happen on old items that aren’t yet closed. Here is a list of all the Issues and Pull Requests with unresolved conversations.

• add llama3 support for alpaca dataset

  #742 commented on Oct 30, 2024 • 1 new comment

• The EOS and BOS token setting when contine pretraining Llama3.1

  #648 commented on Oct 23, 2024 • 0 new comments

• Clarification on Evaluation Results for Llama Guard 3

  #633 commented on Oct 23, 2024 • 0 new comments

• FSDP finetuned model inference question

  #634 commented on Oct 24, 2024 • 0 new comments

• llama3.2 fine tuning generates repeated pattern towards the end of one epoch

  #735 commented on Oct 25, 2024 • 0 new comments

• Found two forward recomputation exist in a single backward when using FSDP with activation checkpointing

  #740 commented on Oct 28, 2024 • 0 new comments

• FSDP2 support for training

  #694 commented on Oct 28, 2024 • 0 new comments

• Llama 3.2-11B-vision fully fine-tuned model file question

  #727 commented on Oct 28, 2024 • 0 new comments

• Learning rate scheduler

  #738 commented on Oct 28, 2024 • 0 new comments