alexrozanski/LlamaChat

Issues

• RuntimeError: Internal: could not parse ModelProto from

  #48 opened 3 months ago by tibor
  0

• llama2 7B-chat model works poorly.

  #38 opened 7 months ago by hyeonchang
  0

• Feature Request: Apple Silicone Neural Engine - Core ML model package format support

  #47 opened 8 months ago by qdrddr
  2

• llama3 support

  #46 opened 8 months ago by pentateu
  0

• Support downloadable models

  #6 opened 2 years ago by umaar
  7

• Suggestion add feature to LlamaChat - upload any type of document

  #14 opened 2 years ago by marxo126
  4

• Llamachat is spouting gibberish

  #45 opened a year ago by jdblack
  1

• Broken link in README

  #44 opened a year ago by mdznr
  0

• Ollama support

  #43 opened a year ago by aptonline
  1

• support for amd gpu (macos)

  #42 opened a year ago by sukualam
  0

• Support for Code Llama – Instruct?

  #41 opened a year ago by yashpathack
  0

• [Feature Request] Support InternLM

  #40 opened a year ago by vansinhu
  0

• Error when converting model

  #39 opened a year ago by georgeaidinis
  1

• Error using pth format model

  #36 opened a year ago by realalexsun
  4

• installation environment problem

  #37 opened a year ago by p5ydn0
  1

• Performence on terminal is very different within llamachat

  #24 opened 2 years ago by Darkhell101
  7

• Support ggmlv3

  #34 opened a year ago by jingsam
  2

• Add iOS support ?

  #33 opened a year ago by realcarlos
  1

• Support for Open LLaMa?

  #32 opened 2 years ago by KnowledgeGarden
  1

• Feature Request: detect models in folder (and subfolders)

  #27 opened 2 years ago by mkellerman
  1

• Can the questions not affect each other?

  #25 opened 2 years ago by hunxuewangzi
  5

• I also want to use versions of Mac 13 and below, and I hope to support the use of Mac computers under Mac 13

  #20 opened 2 years ago by MrYangyt
  3

• Support for Falcon

  #31 opened 2 years ago by alelordelo
  1

• Add Metal/GPU support for running model inference

  #30 opened 2 years ago by singularitti
  1

• Build error

  #29 opened 2 years ago by realcarlos
  1

• Syntax Error in ChatModel.swift

  #28 opened 2 years ago by arman-hk
  2

• Feature Request: Add API endpoint

  #26 opened 2 years ago by mkellerman
  3

• Feature request: Automatically stop generation

  #23 opened 2 years ago by TrajansRow
  2

• Failed to load model for eachadea/ggml-vicuna-7b-1.1

  #15 opened 2 years ago by fakechris
  2

• Feature request: custom initial prompt

  #17 opened 2 years ago by juliendargelos
  3

• Selected Model is Unsupported

  #3 opened 2 years ago by xavierallem
  6

• Support configuring whether to load the entire model into memory or use mmap

  #4 opened 2 years ago by xISSAx
  2

• Support closing add source view with dedicated cancel button

  #7 opened 2 years ago by crystoneme
  3

• Add ability to configure runtime and model hyperparameters

  #13 opened 2 years ago by zakkor
  2

• Ensure messages view is scrolled to bottom when new messages are added

  #18 opened 2 years ago by martinverhey
  2

• Unquantized model files aren't cleaned up after conversion

  #10 opened 2 years ago by alexrozanski
  1

• Control answer length?

  #19 opened 2 years ago by SAI-sentinal-ai
  1

• Chinese LLaMA/Alpaca support

  #16 opened 2 years ago by ymcui
  3

• Request for support of official OpenAI API for ChatGPT/GPT4

  #11 opened 2 years ago by sksq96
  1

• Chinese LLaMA/Alpaca is currently working.

  #8 opened 2 years ago by fakechris
  1

• /Users/.../Documents/Llamachat/LlamaChat/ui/sources/convert/ConvertSourceView.swift:189:14 Initializer for conditional binding must have Optional type, not '[ConvertSourceStepViewModel]'

  #5 opened 2 years ago by phoebusg
  2

• [Feature Request] Selectable Text

  #2 opened 2 years ago by luke3butler
  2

• Sources don't persist

  #1 opened 2 years ago by luke3butler
  4