Vyber07/cyber-security
Viewer • Updated • 1 • 3.93k • 299
🔄 In a Training Loop
MetrisVailore
Metris
AI & ML interests
Building a new general architecture for LLMs
https://huggingface.co/Dream-W
Recent Activity
liked a dataset about 15 hours ago
Vyber07/cyber-security upvoted a paper about 23 hours ago
Has GPT-6-Astra Achieved Embodied Intelligence? upvoted a paper about 23 hours ago
Player-1: Learning to Play from Synthetic ExperienceOrganizations
liked a
dataset about 15 hours ago
upvoted 6
papers about 23 hours ago
Has GPT-6-Astra Achieved Embodied Intelligence?
Paper • 2610.22471 • Published • 471
Player-1: Learning to Play from Synthetic Experience
Paper • 2610.20584 • Published • 351
VideoJev: System One Model for Video Understanding and Interaction
Paper • 2610.18615 • Published • 341
AgentGarten: Code Worlds for Evolving Agents
Paper • 2610.12374 • Published • 295
DiffusionART: Efficient, Stable and Scalable Reinforcement of Diffusion Models
Paper • 2610.12572 • Published • 328
Any Time, Any Space: A World-State-Centric Framework for Agentic Video Generation
Paper • 2610.20571 • Published • 368
liked a
dataset 1 day ago
liked a
model 1 day ago
reacted to IsValorum's post with 🔥 1 day ago
Post
1,430
Navigating the APEX-I and VAL-APEX Quantization Ecosystem on Hugging Face
As the catalog approaches 400,000 total downloads across 69 releases, all models are now structured into dedicated official collections on Hugging Face.
Our goal remains consistent: eliminate the compromise between memory overflow and cognitive collapse on consumer hardware (especially 16 GB VRAM GPUs like the RTX 4080, RTX 4070 Ti Super, and RX 7800 XT).
Instead of uniform block quantization, all APEX builds use per-tensor mixed precision guided by 4-moment Importance Matrix statistics:
- MiniPlus Tier (approx. 14 to 14.8 GiB): Strict 0% 2-bit policy. All MoE routed experts locked at minimum IQ3_XXS with Q4_K/Q6_K attention. Designed for 24 GB setups or 16 GB setups with moderate context.
- NanoPlus Tier (approx. 11.5 to 12.3 GiB): Strategic use of IQ2_S/IQ2_XXS exclusively in core feedforward blocks, keeping routers and attention high-precision. Leaves ample VRAM for 16k-32k context on 16 GB GPUs.
Explore the active collections:
- MoE Standard (MiniPlus & NanoPlus): IsValorum/apex-i-miniplus-v21-standard-moe-6acfee77961c8c0cf5a083b5
- MoE Abliterated (MiniPlus & NanoPlus): IsValorum/apex-i-miniplus-v21-abliterated-moe-6acfee762fc4a8cf2298c55b
- 27B Dense Hybrids: IsValorum/val-apex-miniplus-standard-27b-6acfec54ca4ce4cf5cd5bdb6
- Apple Silicon (MLX): IsValorum/mlx-apex-abliterated-6abedb1f9d400e984efe4fc6
Full technical article and sizing breakdown: https://huggingface.co/blog/IsValorum
As the catalog approaches 400,000 total downloads across 69 releases, all models are now structured into dedicated official collections on Hugging Face.
Our goal remains consistent: eliminate the compromise between memory overflow and cognitive collapse on consumer hardware (especially 16 GB VRAM GPUs like the RTX 4080, RTX 4070 Ti Super, and RX 7800 XT).
Instead of uniform block quantization, all APEX builds use per-tensor mixed precision guided by 4-moment Importance Matrix statistics:
- MiniPlus Tier (approx. 14 to 14.8 GiB): Strict 0% 2-bit policy. All MoE routed experts locked at minimum IQ3_XXS with Q4_K/Q6_K attention. Designed for 24 GB setups or 16 GB setups with moderate context.
- NanoPlus Tier (approx. 11.5 to 12.3 GiB): Strategic use of IQ2_S/IQ2_XXS exclusively in core feedforward blocks, keeping routers and attention high-precision. Leaves ample VRAM for 16k-32k context on 16 GB GPUs.
Explore the active collections:
- MoE Standard (MiniPlus & NanoPlus): IsValorum/apex-i-miniplus-v21-standard-moe-6acfee77961c8c0cf5a083b5
- MoE Abliterated (MiniPlus & NanoPlus): IsValorum/apex-i-miniplus-v21-abliterated-moe-6acfee762fc4a8cf2298c55b
- 27B Dense Hybrids: IsValorum/val-apex-miniplus-standard-27b-6acfec54ca4ce4cf5cd5bdb6
- Apple Silicon (MLX): IsValorum/mlx-apex-abliterated-6abedb1f9d400e984efe4fc6
Full technical article and sizing breakdown: https://huggingface.co/blog/IsValorum
reacted to yanghaojin's post with 🔥 1 day ago
Post
1,168
Ternary Bonsai 2 27B: 2.7× faster on a Mac, 5.9 GB on DGX Spark ⚡
gbx v0.8.2:
• 114 tok/s on M3 Ultra, 2.7× the official MLX runtime
• 62 tok/s on DGX Spark, 2.1× llama.cpp
• 27B in 5.9 GB of memory
Weights are just −1, 0, +1.
GreenBit Ternary Models, coming soon.
🤗 Model: GreenBitAI/Ternary-Bonsai-2-27B-gbx
⚙️ gbx: https://github.com/GreenBitAI/gbx-lm/releases/tag/v0.8.2
gbx v0.8.2:
• 114 tok/s on M3 Ultra, 2.7× the official MLX runtime
• 62 tok/s on DGX Spark, 2.1× llama.cpp
• 27B in 5.9 GB of memory
Weights are just −1, 0, +1.
GreenBit Ternary Models, coming soon.
🤗 Model: GreenBitAI/Ternary-Bonsai-2-27B-gbx
⚙️ gbx: https://github.com/GreenBitAI/gbx-lm/releases/tag/v0.8.2
upvoted a paper 2 days ago
liked 2
models 3 days ago
updated a
Space 4 days ago
liked a
model 6 days ago
liked 4
models 14 days ago
