dleemiller/WordLlama

Issues

• How to extract the Token Embedding

  #37 opened 2 months ago by biniyoni
  4

• Something is wrong in versions accessible by PIP

  #38 opened 2 months ago by tumikosha
  2

• Fedora Linux: Illegal instruction (core dumped)

  #10 opened 2 months ago by russellballestrini
  7

• Word Splitting

  #29 opened 2 months ago by chapmanjacobd
  2

• Doubts about utility to multilingual models

  #30 opened 3 months ago by TheMrguiller
  4

• Matryoshka Representations Evaluation

  #32 opened 3 months ago by KyleSmith19091
  2

• Feature / Add Semantic Splitting

  #19 opened 3 months ago by dleemiller
  3

• tokenizer = Tokenizer.from_file(str(tokenizer_path)) Exception: data did not match any variant of untagged enum PyNormalizerTypeWrapper at line 49 column 3

  #16 opened 3 months ago by gfkdliucheng
  2

• A example of using WordLlama for a RAG pipeline

  #25 opened 3 months ago by dinhanhx
  4

• wl.embed, wl.cluster high RAM usage

  #17 opened 3 months ago by chapmanjacobd
  8

• How do you really create WordLlama model?

  #20 opened 3 months ago by dinhanhx
  3

• The example does not work

  #21 opened 3 months ago by tumikosha
  1

• Gradio Demo

  #12 opened 3 months ago by amrrs
  4

• Need detailed example on how to extract the embedding model from LLM

  #14 opened 3 months ago by harshitv804
  3

• ModuleNotFoundError: No module named 'wordllama.algorithms.kmeans_helpers'

  #13 opened 3 months ago by chapmanjacobd
  2

• First README example fails

  #9 opened 3 months ago by cpa
  3