IntelligentEstate/Cabbi_7B-Qwn2.6-Q4_K_M-GGUF
Updated
Intelligent Estate
community
AI & ML interests
Connecting individuals with innovation: Emancipating and Truly Federalizing Private Intelligence and other Open Source Tech
Recent Activity
View all activity
IntelligentEstate's activity
fuzzy-mittenz
updated
a
model
about 1 hour ago
fuzzy-mittenz
published
a
model
about 1 hour ago
suayptalha
posted
an
update
about 5 hours ago
Post
125
I've just distilled Llama-3.2-3B-Instruct with
deepseek-ai/DeepSeek-R1 on
ServiceNow-AI/R1-Distill-SFT dataset. 🐋🦙
Here is the model:
suayptalha/DeepSeek-R1-Distill-Llama-3B
Here is the model:
suayptalha/DeepSeek-R1-Distill-Llama-3B
fuzzy-mittenz
updated
a
model
1 day ago
fuzzy-mittenz
updated
a
Space
3 days ago
fuzzy-mittenz
updated
a
model
3 days ago
fuzzy-mittenz
updated
a
collection
4 days ago
fuzzy-mittenz
published
a
model
6 days ago
fuzzy-mittenz
updated
a
model
6 days ago
fuzzy-mittenz
updated
a
collection
8 days ago
fuzzy-mittenz
updated
a
model
8 days ago
fuzzy-mittenz
published
a
model
8 days ago
csabakecskemeti
posted
an
update
9 days ago
Post
1584
I found if we apply the reasoning system prompt (that has been published on the
NousResearch/DeepHermes-3-Llama-3-8B-Preview model card) other models are also react to it and start mimicking reasoning. Some better some worse. I've seen internal monologue and self questioning.
Here's a blogpost about it:
http://devquasar.com/ai/reasoning-system-prompt/
Here's a blogpost about it:
http://devquasar.com/ai/reasoning-system-prompt/
fuzzy-mittenz
updated
a
collection
10 days ago
fuzzy-mittenz
posted
an
update
11 days ago
Post
626
So frustrated with "Reasoning" Models.
Sure, introducing RAG into the mix, or giving it an interpreter to math with helps, but never as much as a model that has good instructions.
Even if it's just to repeat the information before answering, a normal model will usually out "Think" it's reasoning counterpart.
Not sure if it's my frustrations but the best answers I've received (from a reasoner), so far, are from the simple instructions to, "Do better!"
Figured I would share the special sauce.
Using 10-100x Compute just to heat the office can't be environmentally friendly, and It still has no Idea where my keys are.
Sure, introducing RAG into the mix, or giving it an interpreter to math with helps, but never as much as a model that has good instructions.
Even if it's just to repeat the information before answering, a normal model will usually out "Think" it's reasoning counterpart.
Not sure if it's my frustrations but the best answers I've received (from a reasoner), so far, are from the simple instructions to, "Do better!"
Figured I would share the special sauce.
Using 10-100x Compute just to heat the office can't be environmentally friendly, and It still has no Idea where my keys are.
fuzzy-mittenz
updated
2
models
11 days ago
fuzzy-mittenz
updated
a
collection
11 days ago