Sabin Stargem
SabinStargem
AI & ML interests
None yet
Recent Activity
new activity
about 1 month ago
EVA-UNIT-01/EVA-Qwen2.5-72B-v0.2:Request: EVA models suitable for speculative decoding.
new activity
about 1 month ago
mradermacher/model_requests:Mistral-NeMo-Minitron-8B-Base-Minivoc-32k-v0.1a
Organizations
None yet
SabinStargem's activity
Request: EVA models suitable for speculative decoding.
1
#2 opened about 1 month ago
by
SabinStargem
Mistral-NeMo-Minitron-8B-Base-Minivoc-32k-v0.1a
3
#456 opened about 1 month ago
by
SabinStargem
It might be better to use Lumimaid instead of Luminum?
2
#1 opened 4 months ago
by
SabinStargem
70b - Reflection
9
#273 opened 4 months ago
by
SabinStargem
104b Command-R-Plus 08-2024 (v1.5)
12
#258 opened 4 months ago
by
SabinStargem
123b - Mistral Large-2-Instruct-2407
3
#168 opened 6 months ago
by
SabinStargem
Tess v2.5, Qwen2 72b.
1
#92 opened 7 months ago
by
SabinStargem
Dolphin v2.9.2 - Qwen2 72b.
3
#91 opened 7 months ago
by
SabinStargem
160b - Magec4ai-Command-R-Plus
4
#39 opened 9 months ago
by
SabinStargem
Can a AQLM of CommandR+ be converted into a GGUF for LlamaCPP?
5
#34 opened 9 months ago
by
SabinStargem
70b - Llama-3 - Dolphin v2.9
1
#33 opened 9 months ago
by
SabinStargem
"104b" and "CR +X" should be part of the name for SEO purposes.
#31 opened 9 months ago
by
SabinStargem
Invalid split files?
3
#11 opened 9 months ago
by
SabinStargem
104b - Command-R-Plus
7
#19 opened 9 months ago
by
SabinStargem
Airoboros v3.3 and Bagel DPO v0.5
2
#14 opened 9 months ago
by
SabinStargem
Clarification: Is it Yi-34b-200k v2, or v1?
1
#1 opened 9 months ago
by
SabinStargem
Yi-34b-200k v2, in the cards?
2
#2 opened 10 months ago
by
SabinStargem
Q2_XS / Q2_XSS & Q3_XXS are currently unusable on ooba [WIP]
7
#1 opened 11 months ago
by
Undi95
An attempt at determining the INT and WIS of MiquLiz.
#2 opened 11 months ago
by
SabinStargem
A brief comparison of KoboldCPP HI and LO RAM speed of MiquLiz 120b.
#1 opened 11 months ago
by
SabinStargem