BestHub
Sign in
Fun with Large Models
Fun with Large Models
Apr 1, 2026 · Artificial Intelligence

A Beginner's Deep Dive into Large‑Model Training Parameters with LLaMAFactory

This article walks readers through the three major training methods—full‑parameter, LoRA, and QLoRA—explaining their memory costs, data requirements, and trade‑offs, then provides a line‑by‑line breakdown of LLaMAFactory configuration files, hyper‑parameter tuning guidelines, and the process for merging LoRA adapters into a deployable model.

LLaMAFactoryLoRAQLoRA
0 likes · 27 min read
A Beginner's Deep Dive into Large‑Model Training Parameters with LLaMAFactory
Xiaohongshu Tech REDtech
Xiaohongshu Tech REDtech
Aug 6, 2025 · Artificial Intelligence

dots.vlm1: Open‑Source Multimodal Vision‑Language Model Near SOTA Performance

dots.vlm1, the first open‑source multimodal large model from Xiaohongshu hi‑lab, combines a 1.2‑billion‑parameter NaViT visual encoder with DeepSeek V3 LLM, achieving near‑state‑of‑the‑art visual understanding and reasoning while remaining competitive on text tasks, and is available on GitHub and HuggingFace.

AIVision-Languagedeep-learning
0 likes · 11 min read
dots.vlm1: Open‑Source Multimodal Vision‑Language Model Near SOTA Performance
DataFunSummit
DataFunSummit
Dec 23, 2024 · Artificial Intelligence

Huolala's Large Model Evaluation Framework (LaLaEval) and Application Practices

This article presents Huolala's comprehensive LaLaEval framework for evaluating large language models, detailing the challenges of model deployment, the five‑step assessment process, two real‑world case studies in freight and driver invitation, and future directions toward more automated, product‑driven evaluation.

AIFrameworkLogistics
0 likes · 24 min read
Huolala's Large Model Evaluation Framework (LaLaEval) and Application Practices
DataFunSummit
DataFunSummit
Nov 4, 2024 · Artificial Intelligence

Performance Optimization Techniques for Large Model Inference Frameworks

This article outlines four key optimization areas for large model inference frameworks—quantization, speculative sampling, TTFT/TPOT improvements, and communication optimization—detailing specific techniques, experimental results, and practical benefits such as reduced memory usage, lower latency, and higher throughput.

AIPerformanceSpeculative Sampling
0 likes · 12 min read
Performance Optimization Techniques for Large Model Inference Frameworks