cais/hle
Viewer
•
Updated
•
3k
•
406
•
49
Mitko Vasilev
mitkox
AI & ML interests
Make sure you own your AI. AI in the cloud is not aligned with you; it's aligned with the company that owns it.
Recent Activity
liked
a dataset
about 19 hours ago
cais/hle
posted
an
update
1 day ago
Stargate to the west of me
DeepSeek to the east
Here I am
Stuck in the middle with the EU
It will likely be a matter of sparkle to get export control on frontier research and models on both sides, leaving us in a vacuum.
Decentralized training infrastructure and on device inferencing are the future.
Organizations
mitkox's activity
liked
a
dataset
about 19 hours ago
posted
an
update
1 day ago
Post
325
Stargate to the west of me
DeepSeek to the east
Here I am
Stuck in the middle with the EU
It will likely be a matter of sparkle to get export control on frontier research and models on both sides, leaving us in a vacuum.
Decentralized training infrastructure and on device inferencing are the future.
DeepSeek to the east
Here I am
Stuck in the middle with the EU
It will likely be a matter of sparkle to get export control on frontier research and models on both sides, leaving us in a vacuum.
Decentralized training infrastructure and on device inferencing are the future.
posted
an
update
4 days ago
Post
467
On device AI reasoning ODA-R using speculative decoding with draft model DeepSeek-R1-Distill-Qwen-1.5B and DeepSeek-R1-Distill-Qwen-32B. DSPy compiler for reasoning prompts in math, engineering, code...
updated
a
model
4 days ago
published
a
model
4 days ago
liked
2
models
4 days ago
posted
an
update
8 days ago
Post
1381
Training a model to reason in the continuous latent space based on Meta's Coconut.
If it all works will apply it on the MiniCPM-o SVD-LR.
Endgame is a multimodal, adaptive, and efficient foundational on device AI model.
If it all works will apply it on the MiniCPM-o SVD-LR.
Endgame is a multimodal, adaptive, and efficient foundational on device AI model.
- 2 replies
replied to
their
post
16 days ago
DDR5 on HP Z8 G5
replied to
their
post
16 days ago
exactly Q2 med with ~190GB RAM
posted
an
update
16 days ago
Post
2430
Can it run DeepSeek V3 671B is the new 'can it run Doom'.
How minimalistic can I go with on device AI with behemoth models - here I'm running DeepSeek V3 MoE on a single A6000 GPU.
Not great, not terrible, for this minimalistic setup. I love the Mixture of Experts architectures. Typically I'm running my core LLM distributed over the 4 GPUs.
Make sure you own your AI. AI in the cloud is not aligned with you; it's aligned with the company that owns it.
How minimalistic can I go with on device AI with behemoth models - here I'm running DeepSeek V3 MoE on a single A6000 GPU.
Not great, not terrible, for this minimalistic setup. I love the Mixture of Experts architectures. Typically I'm running my core LLM distributed over the 4 GPUs.
Make sure you own your AI. AI in the cloud is not aligned with you; it's aligned with the company that owns it.
-
- 5 replies
liked
a
Space
about 1 month ago
Bye Apple and hi NVIDIA
4
#6 opened 2 months ago
by
mitkox
liked
a
model
4 months ago
updated
a
model
4 months ago
Upload folder using huggingface_hub
2
#1 opened 4 months ago
by
mitkox
updated
a
model
4 months ago
liked
3
Spaces
4 months ago