Koes Nandar
koesn
AI & ML interests
LLM Quantizing, Fine-Tuning, Law AI, Automation
Recent Activity
liked
a model
10 days ago
shuyuej/gte-Qwen2-7B-instruct-GPTQ
Organizations
None yet
koesn's activity
exl2 quants?
#1 opened 5 months ago
by
koesn
Exl2 quants
5
#1 opened 6 months ago
by
bullerwins
Nice job!
4
#4 opened 6 months ago
by
BigHuggyD
ITS NOT REAL
5
#15 opened 8 months ago
by
rombodawg
What's the VRAM usage?
9
#2 opened 9 months ago
by
CamiloMM
Lines end with "assistant"
1
#1 opened 8 months ago
by
just1moremodel
2.75 bpw high EQ bench
1
#1 opened 8 months ago
by
koesn
Great combo
#7 opened 9 months ago
by
koesn
Would love 5.0bpw
1
#2 opened 9 months ago
by
koesn
Very good on complex prompt
#1 opened 9 months ago
by
koesn
exl2 please
2
#3 opened 10 months ago
by
zypcastles
This model run on 3x3060 at 32k contexts
#1 opened 9 months ago
by
koesn
Updated version
2
#1 opened 9 months ago
by
venkycs
GGUF?
3
#1 opened 10 months ago
by
Goldenblood56
Smart and Cohesive
1
#1 opened 10 months ago
by
koesn
Best for summarizing long context.
#2 opened 11 months ago
by
koesn
Can the yi-34b.Q3_K_S.gguf model be set up on Mac M1 with 16GB of memory?
2
#7 opened about 1 year ago
by
liweixin
Rikues Basis Mistral
1
#1 opened about 1 year ago
by
koesn
Model Q8 File Corrupt
1
#1 opened about 1 year ago
by
koesn
Coherence in Exhaustive Tests on 8k Context
#1 opened about 1 year ago
by
koesn