jan
jan copied to clipboard
janhq
Jan is an open source alternative to ChatGPT that runs 100% offline on your computer. Multiple engine support (llama.cpp, TensorRT-LLM)
## **1. Release scope:** #### :truck: Important changes: - **Jan app important changes** [Please use this filter for Jan app important changes](https://github.com/janhq/jan/issues?q=label%3A"Release+Comms"+milestone%3A"v0.4.13+🌾%C2%A0Broken+Rice") #### ⏫ Enhancement: - Command-r https://github.com/janhq/jan/pull/2868 #### ✏️...
**Pages** Folder to your models -> default -/> choose specified. **Success Criteria** Thiss will show people where are models stored, to create links or manage it. **Additional context** Right now,...
**Describe the bug** The nitro-extension, which runs the nitro engine within the application, currently defines the core number as equal to the number of physical cores to avoid resource hogging....
**Problem** For some users want to use 104B model via API **Success Criteria** Run CommandR+ in Jan with ease **Additional context** https://docs.cohere.com/reference/about
The list of threads gets too long very fast if I try the same prompt with several different models. A possibility to group threads in folders (similarly to bookmarks in...
**Describe the bug** A clear and concise description of what the bug is. Upon running `docker compose --profile gpu-fs up`, I can proceed to localhost:3000, but as soon as i...
When launchin a model (each model), i got this error: `2024-04-12T16:15:13.762Z [NITRO]::Debug: [1712938513] [C:\actions-runner\_work\nitro\nitro\controllers\llamaCPP.h: 1585][llama_server_context::update_slots] slot 0 released (53 tokens in cache) 2024-04-12T16:15:14.769Z [NITRO]::Debug: 20240412 16:15:13.763000 UTC 13672 INFO reached...
hello, I can't start any model. {"timestamp":1712753736,"level":"INFO","function":"loadModelImpl","line":642,"message":"system info","n_threads":25,"total_threads":48,"system_info":"AVX = 1 | AVX_VNNI = 0 | AVX2 = 1 | AVX512 = 0 | AVX512_VBMI = 0 | AVX512_VNNI = 0...
