Fine-tuning LLMs with Singular Value Decomposition
•
8
Alberto Cetoli PRO
fractalego
AI & ML interests
Entity/relation extraction, Q&A, Summarisation
Recent Activity
liked
a model
2 days ago
stabilityai/stable-video-diffusion-img2vid-xt
Articles
Organizations
fractalego's activity
liked
a
model
2 days ago
reacted to
mitkox's
post with 🤯🔥➕
3 days ago
Post
2306
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
dataset
8 days ago
liked
a
dataset
9 days ago
updated
a
model
9 days ago
upvoted
3
papers
18 days ago
Critic-V: VLM Critics Help Catch VLM Errors in Multimodal Reasoning
Paper
•
2411.18203
•
Published
•
33
LLaMA-Berry: Pairwise Optimization for O1-like Olympiad-Level Mathematical Reasoning
Paper
•
2410.02884
•
Published
•
53
Accessing GPT-4 level Mathematical Olympiad Solutions via Monte Carlo Tree Self-refine with LLaMa-3 8B
Paper
•
2406.07394
•
Published
•
26
liked
a
model
21 days ago
updated
a
dataset
28 days ago
liked
a
model
about 1 month ago
reacted to
julien-c's
post with 🔥
about 1 month ago
Post
2487
wow 😮
INTELLECT-1 is the first collaboratively trained 10 billion parameter language model trained from scratch on 1 trillion tokens of English text and code.
PrimeIntellect/INTELLECT-1-Instruct
INTELLECT-1 is the first collaboratively trained 10 billion parameter language model trained from scratch on 1 trillion tokens of English text and code.
PrimeIntellect/INTELLECT-1-Instruct
reacted to
merve's
post with ❤️
about 2 months ago
Post
3156
your hugging face profile now has your recent activities 🤗
liked
2
datasets
about 2 months ago
upvoted
a
collection
2 months ago
reacted to
chansung's
post with 👍
2 months ago
Post
4691
Effortlessly stay up-to-date with AI research trends using a new AI tool, "AI Paper Reviewer" !!
It analyzes a list of Hugging Face Daily Papers(w/ @akhaliq ) and turn them into insightful blog posts. This project leverages Gemini models (1.5 Pro, 1.5 Flash, and 1.5 Flash-8B) for content generation and Upstage Document Parse for parsing the layout and contents.
blog link: https://deep-diver.github.io/ai-paper-reviewer/
Also, here is the link of GitHub repository for parsing and generating pipeline. By using this, you can easily build your own GitHub static pages based on any arXiv papers with your own interest!
: https://github.com/deep-diver/paper-reviewer
It analyzes a list of Hugging Face Daily Papers(w/ @akhaliq ) and turn them into insightful blog posts. This project leverages Gemini models (1.5 Pro, 1.5 Flash, and 1.5 Flash-8B) for content generation and Upstage Document Parse for parsing the layout and contents.
blog link: https://deep-diver.github.io/ai-paper-reviewer/
Also, here is the link of GitHub repository for parsing and generating pipeline. By using this, you can easily build your own GitHub static pages based on any arXiv papers with your own interest!
: https://github.com/deep-diver/paper-reviewer
liked
a
dataset
3 months ago