Patrick Devaney

patrickbdevaney

·

AI & ML interests

mamba s4, mixtral 8x-7b, candle, pytorch

Recent Activity

reacted to onekq's post with 👀 2 minutes ago

My takes on Jev 1. Very likely a small model. You can certainly pretrain, but I would grab an existing base model, say Qwen 3 class 2. The new RL method is a breakthrough, classification doesn't need to align with human preferences 3. The new output is an overstatement. It's just a new LM head. Of course autoregressive decoding can be used for classification: it takes just a few tokens to express the output. Think twice: are you sure classification doesn't need few-shot, CoT, or reasoning? All of these depend on auto-regressiveness 4. It carves out a market already existing, which is now served by oversized LLMs (hence overpaid), e.g. LLM as judge, labeling 5. Jevons effect will kick in, promoting more modeling efforts for small budget teams. It might even accelerate RSI

reacted to eaddario's post with 🔥 5 days ago

Experimental global target bits‑per‑weight quantization of openbmb/MiniCPM5-1B and openbmb/MiniCPM5-2B. Unlike standard llama.cpp quantization that rely on fixed type heuristics (e.g., Q4_K_M), the Target BPW approach automatically optimizes per-tensor precision where it matters the most, and produces high quality models that meet a precise global size target. Key Advantages: - VRAM Maximization: Can generate high quality models sized exactly to fit hardware constraints (e.g., fitting the model into exactly 24GB VRAM). - Data-Driven Precision: Quantization mix is determined by actual weight error sensitivity rather than hardcoded rules, often yielding better PPL/KLD size trade-offs. Full benchmarks (PPL, KLD, ARC, GPQA, MMLU, etc.) and methodology in the model's card. https://huggingface.co/eaddario/MiniCPM5-1B-GGUF https://huggingface.co/eaddario/MiniCPM5-2B-GGUF

liked a model 11 days ago

PixelML/Qwen3.8-Flash-Next-NVFP4-DFlash

View all activity

Organizations

patrickbdevaney 's models 33

patrickbdevaney/WizardLM-1b-GGUF

Text Generation • 1B • Updated Feb 27, 2024 • 58

patrickbdevaney/biomistral-gguf

7B • Updated Feb 27, 2024 • 42

patrickbdevaney/solidity

Text Generation • 7B • Updated Feb 27, 2024 • 63