meta-llama/Llama-3.2-3B-Instruct
Text Generation • 3B • Updated • 1.97M • • 2.16k
Vasyl Dykun
SpyFox
AI & ML interests
Deep learning
Recent Activity
liked a model 8 days ago
meta-llama/Llama-3.2-3B-Instruct upvoted an article 15 days ago
Unlocking asynchronicity in continuous batching upvoted an article 17 days ago
EMO: Pretraining mixture of experts for emergent modularityOrganizations
liked a
model 8 days ago
upvoted an article 15 days ago
Article
Unlocking asynchronicity in continuous batching
- +1
ror, pcuenq, ariG23498
• • 55 upvoted an article 17 days ago
Article
EMO: Pretraining mixture of experts for emergent modularity
allenai
• • 38 reacted to DedeProGames's post with 🔥 24 days ago
Post
8577
GRaPE 2 Pro is now available.
SL-AI/GRaPE-2-Pro
This is the flagship model of the GRaPE 2 family and the largest model I have trained to date, sitting at 27B parameters. It is built on Qwen3.5-27B and trained on a closed-source proprietary dataset, with roughly half of post-training focused on code and the rest split between STEAM subjects and structured logical reasoning. It punches seriously above its weight class.
GRaPE 2 Pro supports multimodal input (image + text) and features 6 thinking modes via the
It also runs on consumer hardware. You can get it going with as low as 12GB of VRAM on a quantized build.
If you want to try it out and give feedback, that would be really appreciated. Email us at
SL-AI/GRaPE-2-Pro
This is the flagship model of the GRaPE 2 family and the largest model I have trained to date, sitting at 27B parameters. It is built on Qwen3.5-27B and trained on a closed-source proprietary dataset, with roughly half of post-training focused on code and the rest split between STEAM subjects and structured logical reasoning. It punches seriously above its weight class.
GRaPE 2 Pro supports multimodal input (image + text) and features 6 thinking modes via the
minimal, all the way up to xtra-Hi for deep, extended thought on hard problems. For most agentic use, auto or low is the move to keep things snappy.It also runs on consumer hardware. You can get it going with as low as 12GB of VRAM on a quantized build.
If you want to try it out and give feedback, that would be really appreciated. Email us at
contact@skinnertopia.com 
- 1 reply
liked a
Space 28 days ago
upvoted 3
articles 29 days ago
Article
How to build scalable web apps with OpenAI's Privacy Filter
- +1
ysharma, freddyaboulton, abidlabs
• • 13 Article
Introducing NVIDIA Nemotron 3 Nano Omni: Long-Context Multimodal Intelligence for Documents, Audio and Video Agents
nvidia
• • 60 Article
Granite 4.1 LLMs: How They’re Built
ibm-granite
• • 76 liked 2
models 29 days ago
upvoted 5
articles about 1 month ago
Article
Multimodal Embedding & Reranker Models with Sentence Transformers
tomaarsen
• • 60 Article
Training and Finetuning Multimodal Embedding & Reranker Models with Sentence Transformers
tomaarsen
• • 71 Article
The PR you would have opened yourself
pcuenq, awni
• • 72 Article
AI and the Future of Cybersecurity: Why Openness Matters
- +1
meg, yjernite, clem
• • 38 Article
Waypoint-1.5: Higher-Fidelity Interactive Worlds for Everyday GPUs
- +3
lapp0, LouisCastricato, ScottieFox, shahbuland, xAesthetics
• • 30 liked a
dataset about 1 month ago
upvoted an article about 1 month ago
Article
Inside VAKRA: Reasoning, Tool Use, and Failure Modes of Agents
ibm-research
• • 28 upvoted 3
articles about 2 months ago
Article
Welcome Gemma 4: Frontier multimodal intelligence on device
- +5
merve, pcuenq, sergiopaniego, burtenshaw, Steveeeeeeen, alvarobartt, SaylorTwift
• • 902 Article
Holo3: Breaking the Computer Use Frontier
Hcompany
• • 46 Article
TRL v1.0: Post-Training Library Built to Move with the Field
- +2
qgallouedec, stevhliu, pcuenq, sergiopaniego
• • 53