Historique des commits

Auteur SHA1 Message Date
  oobabooga 49c10c5570 Add support for the latest GPTQ models with group-size (#530) il y a 2 ans
  oobabooga c5ebcc5f7e Change the default names (#518) il y a 2 ans
  oobabooga 7618f3fe8c Add -gptq-preload for 4-bit offloading (#460) il y a 2 ans
  oobabooga ddb62470e9 --no-cache and --gpu-memory in MiB for fine VRAM control il y a 2 ans
  oobabooga a78b6508fc Make custom LoRAs work by default #385 il y a 2 ans
  oobabooga c753261338 Disable stop_at_newline by default il y a 2 ans
  oobabooga 29fe7b1c74 Remove LoRA tab, move it into the Parameters menu il y a 2 ans
  oobabooga 214dc6868e Several QoL changes related to LoRA il y a 2 ans
  oobabooga 104293f411 Add LoRA support il y a 2 ans
  oobabooga 4d64a57092 Add Interface mode tab il y a 2 ans
  oobabooga 265ba384b7 Rename a file, add deprecation warning for --load-in-4bit il y a 2 ans
  oobabooga 3da73e409f Merge branch 'main' into Zerogoki00-opt4-bit il y a 2 ans
  oobabooga 3fb8196e16 Implement "*Is recording a voice message...*" for TTS #303 il y a 2 ans
  Ayanami Rei b6c5c57f2e remove default value from argument il y a 2 ans
  Ayanami Rei 1b99ed61bc add argument --gptq-model-type and remove duplicate arguments il y a 2 ans
  oobabooga 66b6971b61 Update README il y a 2 ans
  oobabooga ddea518e0f Document --auto-launch il y a 2 ans
  oobabooga 1ddcd4d0ba Clean up silero_tts il y a 2 ans
  oobabooga d8bea766d7 Merge pull request #192 from xanthousm/main il y a 2 ans
  oobabooga f3b00dd165 Merge pull request #224 from ItsLogic/llama-bits il y a 2 ans
  oobabooga 65dda28c9d Rename --llama-bits to --gptq-bits il y a 2 ans
  oobabooga 0ac562bdba Add a default prompt for OpenAssistant oasst-sft-1-pythia-12b #253 il y a 2 ans
  Xan b3e10e47c0 Fix merge conflict in text_generation il y a 2 ans
  Xan 96c51973f9 --auto-launch and "Is typing..." il y a 2 ans
  Xan 33df4bd91f Merge remote-tracking branch 'upstream/main' il y a 2 ans
  draff 28fd4fc970 Change wording to be consistent with other args il y a 2 ans
  draff 804486214b Re-implement --load-in-4bit and update --llama-bits arg description il y a 2 ans
  draff e6c631aea4 Replace --load-in-4bit with --llama-bits il y a 2 ans
  oobabooga 026d60bd34 Remove default preset that didn't do anything il y a 2 ans
  oobabooga 828a524f9a Add LLaMA 4-bit support il y a 2 ans