togethercomputer/MoA

Issues

• seems that MoA does not work on MATH and QA with both weak and strong LLMs

  #41 opened 5 months ago by yananchen1989
  4

• ollama support

  #20 opened 6 months ago by win4r
  2

• add a critique model to the mix to improve the answers

  #23 opened 6 months ago by Aaronminer1
  1

• Evaluation on Objective Benchmarks

  #40 opened 5 months ago by jingmingzhuo
  0

• Could not find where the three "layers" are implemented in the code.

  #34 opened 5 months ago by mikegao2020
  1

• Performance on Large Language Models with Fewer Parameters

  #38 opened 5 months ago by huliang2016
  2

• Error occur after all 805 tests

  #28 opened 6 months ago by URRealHero
  1

• You have been rate limited.

  #27 opened 6 months ago by carrt123
  2

• Does the agent support GPT, Gemini, Claude, etc.

  #16 opened 5 months ago by zsqdx
  1

• --rounds 2 seems broken

  #30 opened 6 months ago by tijszwinkels
  0

• why the implement of `moa.py` isn't consistent with `inject_references_to_messages`

  #26 opened 6 months ago by better629
  0

• How can i use it with close source model. Gpt4o, 1.5 sonnet

  #22 opened 6 months ago by Am0stafa
  1

• how to deploy this locally with ollama UIs like `Open WebUI` and `Lobe Chat` ?

  #14 opened 6 months ago by hemangjoshi37a
  2

• Run locally?

  #10 opened 6 months ago by CHesketh76
  9

• Agents?

  #7 opened 6 months ago by logan-markewich
  3

• Missing AlpacaEval gpt4 reference results - results/gpt4_1106_preview/model_outputs.json

  #21 opened 6 months ago by morganmcg1
  0

• does it support `ollama` ?

  #15 opened 6 months ago by hemangjoshi37a
  4

• questions about the intermediate layers

  #9 opened 6 months ago by yananchen1989
  3