Discussions

• 2 You must be logged in to vote

  🙏

  How does one convert alpaca Llama for use with this repo?

  arijoon asked Mar 22, 2023 in Q&A · Answered

  

  

  

  

  6
• 1 You must be logged in to vote

  💬

  What should be the generation speed on RTX 3060?

  ray2022 started Mar 22, 2023 in General

  

  

  1
• 1 You must be logged in to vote

  🙏

  Rephrase text?

  mindcz asked Mar 24, 2023 in Q&A · Unanswered

  

  

  0
• 3 You must be logged in to vote

  🙏

  Does 4bit support offloading yet?

  ye7iaserag asked Mar 17, 2023 in Q&A · Answered

  

  

  2
• 1 You must be logged in to vote

  🙏

  Connecting text gen to a Telegram bot

  KirillRepinArt asked Mar 23, 2023 in Q&A · Unanswered

  

  

  0
• 1 You must be logged in to vote

  🙏

  Error extracting package: remove_all

  Akh0r asked Mar 22, 2023 in Q&A · Unanswered

  

  

  0
• 3 You must be logged in to vote

  🙏

  Any existing Alpaca models out there?

  JustinHinh asked Mar 22, 2023 in Q&A · Unanswered

  

  

  

  

  5
• 9 You must be logged in to vote

  💡

  Any wish to implement llama.cpp (llama with CPU only) ?

  BadisG started Mar 14, 2023 in Ideas

  

  

  

  

  5
• 1 You must be logged in to vote

  💬

  Erebus for Google Colab

  SoftwareLogico started Mar 20, 2023 in General · Closed

  

  

  1
• 2 You must be logged in to vote

  💬

  It's time for me to dive head first into this.

  aifartist started Mar 20, 2023 in General

  

  

  1
• 5 You must be logged in to vote

  🙏

  Does the generation use a random seed?

  pbosh asked Mar 11, 2023 in Q&A · Unanswered

  

  

  

  

  7
• 2 You must be logged in to vote

  💬

  Why was RWKV package removed?

  ye7iaserag started Mar 18, 2023 in General

  

  

  1
• 3 You must be logged in to vote

  💬

  New chat finetuned model - togethercomputer/GPT-NeoXT-Chat-Base-20B

  wywywywy started Mar 12, 2023 in General

  

  

  

  

  9
• 2 You must be logged in to vote

  💬

  Can someone create a 4 dummies WSL install?

  bbecausereasonss started Mar 17, 2023 in General

  

  

  

  

  9
• 2 You must be logged in to vote

  🙏

  GPTQ 4-bit models seem significantly worse (atleast for the 7B version)

  athu16 asked Mar 18, 2023 in Q&A · Unanswered

  

  

  4
• 2 You must be logged in to vote

  💬

  What can be the different use cases for this?

  sid8491 started Mar 18, 2023 in General

  

  

  0
• 2 You must be logged in to vote

  🙏

  What does "do_sample" do?

  AndreyRGW asked Mar 18, 2023 in Q&A · Closed · Unanswered

  

  

  0
• 2 You must be logged in to vote

  💡

  Implimenting Time Awareness

  olihough86 started Mar 18, 2023 in Ideas

  

  

  0
• 1 You must be logged in to vote

  🙏

  Character Persona not working?

  patrickmros asked Mar 16, 2023 in Q&A · Unanswered

  

  

  3
• 1 You must be logged in to vote

  🙏

  Converting model in order to use it with flexgen

  Wolvensdale asked Mar 11, 2023 in Q&A · Unanswered

  

  

  2
• 1 You must be logged in to vote

  🙏

  Torch not compiled with CUDA enabled

  aimartyr asked Mar 16, 2023 in Q&A · Closed · Answered

  

  

  1
• 1 You must be logged in to vote

  🙏

  Seeing Winsock connection reset errors

  mynumu asked Mar 15, 2023 in Q&A · Unanswered

  

  

  0
• 1 You must be logged in to vote

  🙏

  "Cannot import name 'llama' from partially initialized module 'transformers.models' (most likely due to a circular import)" Error message

  tnginako asked Mar 15, 2023 in Q&A · Unanswered

  

  

  0
• 1 You must be logged in to vote

  💡

  Add an option to choose the path when using the Windows Installer

  mynumu started Mar 14, 2023 in Ideas

  

  

  0
• 2 You must be logged in to vote

  💡

  Threw together a really slapdash continuously built semi-pre-installed/compiled Docker Image for running 4bit GPTQ Llama on a provider like vast.ai, runpod.io, etc.

  nelsonjchen started Mar 14, 2023 in Ideas

  

  

  0