Issues
- 7
Support for Phi-3 models
#58 opened by retteghy - 1
Can you add tinydolphin
#61 opened by EnderRobber101 - 0
Prompt format for Llama 3
#60 opened by iamwillpowers - 11
- 6
Add support for Llama 3
#57 opened by lajlev - 5
Dolphin models problem (modelLoadError)
#38 opened by BlobIsBack - 7
Fine tuning does not work
#24 opened by solidityenthusiast - 1
The version downloaded via git crashes on the physical device iPhone 14 Plus
#54 opened by MortalLien - 6
Sampling stuck in greedy
#42 opened by Maw1979 - 2
Bugs and suggestions
#50 opened by FrostyMisa - 1
Google Gemma 1.1 Support
#56 opened by rahulmanuwas - 1
Why not use the official Phi-3 model
#59 opened by pxz2016 - 15
- 1
- 1
Issue with LLAVA 1.5
#51 opened by ProCreations-Offical - 1
Few bugs with template saving
#23 opened by ShawnFumo - 1
- 1
Image support for multi modal models.
#31 opened by paulwababu - 2
- 3
Few feature requests..
#46 opened by ProCreations-Offical - 0
AWQ support?
#35 opened by achibb - 1
- 2
Apple Model Available
#45 opened by lawyinking - 1
App crashes right away
#48 opened by byjlw - 6
It's so slow
#49 opened by KittenYang - 0
Add list of downloadable models to the app
#32 opened by verhovsky - 2
iOS 15 support
#43 opened by mak448a - 4
Request: user-configurable system prompts
#17 opened by aehlke - 6
- 2
Crash when running with RWKV 5 (Raven)
#41 opened by sammcj - 3
Can the model get information from the outside?
#40 opened by carstenf - 6
The latest code simulator crash
#36 opened by buhe - 5
Multi line input
#13 opened by albertogasparin - 3
How to debug?
#37 opened by buhe - 10
Performance/benchmarks
#14 opened by chen-rn - 2
- 2
Token to string issue FYI
#20 opened by aehlke - 2
Clear chat, edit previous messages
#22 opened by ShawnFumo - 3
Phi-2 does not work
#29 opened by willfaust - 1
Request: Add support for Qwen models
#30 opened by RyutaItabashi - 1
14 Pro Max crashes
#27 opened by merterbak - 0
14 Pro Max crashes
#28 opened by merterbak - 7
stablelm-zephyr-3b-GGUF model fails to load
#25 opened by gblazex - 0
Integrate whisper.cpp
#26 opened by olafgeibig - 1
can't compile in xcode
#19 opened by daystudio - 2
When I send out my first prompt to llm after opening the app, The app will freeze for like 5-10 seconds before llm generate the response.
#15 opened by steveshaoucsb - 10
- 4
Adding support for Mistral
#12 opened by rodas-j - 1
- 2
Crashed on IPad Pro M1 running iPadOS 17 when asking llama 2 to write an 600 word essay
#8 opened by steveshaoucsb