Post
19
Good news, llama.cpp seems to be close to supporting MTP on qwen models. Bad news, every single gguf will have to be redone when it is.
Matthew Andrews
BlueNipples
AI & ML interests
None yet
Recent Activity
new activity about 5 hours ago
mistralai/Mistral-Medium-3.5-128B:Finally dense 100b+! liked a model 7 days ago
mistralai/Mistral-Medium-3.5-128BOrganizations
Posts 3
Post
665
I'll never understand why people are merging reasoning models with non-reasoning models. It's worse, every time.
You got to train reasoning on reasoning data, and merge reasoning, with reasoning.
You got to train reasoning on reasoning data, and merge reasoning, with reasoning.
models 11
BlueNipples/combinedsdxl-lora
Text-to-Image • Updated • 39 •
BlueNipples/combined-lora
Text-to-Image • Updated • 60
BlueNipples/SnowLotus-v2-10.7B
Text Generation • 11B • Updated • 122 • 5
BlueNipples/DaringLotus-SnowLotus-10.7b-IQ-GGUF
11B • Updated • 543 • 12
BlueNipples/Fett-uccine_Mini_3B-q2k-imat_GGUF
3B • Updated • 9 • 1
BlueNipples/DaringLotus-v2-10.7b
Text Generation • 11B • Updated • 12 • 2
BlueNipples/Apocrypha-7b
Text Generation • 7B • Updated • 174 • 3
BlueNipples/TimeCrystal-l2-13B-GGUF
13B • Updated • 19 • 1
BlueNipples/TimeCrystal-l2-13B
Text Generation • Updated • 844 • • 16
BlueNipples/Trion-M-7b
Text Generation • Updated • 12 • 4
datasets 0
None public yet