Ricky
SkyIsNotGreen
P(doom) <0.001%
AI & ML interests
Independent LLM researcher focused on: long-horizon memory, ternary quantization, LLM forensics & analysis, local-hosting on consumer hardware, and AI portability.
Recent Activity
updated a model 1 day ago
SkyIsNotGreen/Scion-FlashNext-176B-A6B liked a model 3 days ago
unsloth/embeddinggemma-2-GGUFOrganizations
None yet
Independent results for Bonsai-2 PQ2_0 (GSM8K / MATH / HumanEval) with caveats
#87 opened 2 days ago
by SkyIsNotGreen
What level of performance does it achieve?
11
#3 opened 8 days ago
by 
jian2023
mtp on A3B ternary model
1
#1 opened 10 days ago
by 
MultivariatePerspective777
Ternary Training
3
#2 opened 12 days ago
by MultivariatePerspective777
maybe I miss something ...
1
#1 opened 13 days ago
by 
RegisteredWednesday
Ternary-based 35B-A3B I made, using this distill.
👍 1
1
#8 opened 13 days ago
by SkyIsNotGreen
I took Bonsai 2 27B apart: the format is public, the last 8% is trained
👀❤️ 7
10
#44 opened 20 days ago
by SkyIsNotGreen
I took Bonsai 2 27B apart: the format is public, the last 8% is trained
👀❤️ 7
10
#44 opened 20 days ago
by SkyIsNotGreen
I took Bonsai 2 27B apart: the format is public, the last 8% is trained
👀❤️ 7
10
#44 opened 20 days ago
by SkyIsNotGreen