wallnavigatorhook/fine-tuning-llm-lora-qlora-unsloth: Fine-tuning LLM — lora, qlora, unsloth, fine tune tutorial.
Fine-tuning LLM — lora, qlora, unsloth, fine tune tutorial.
#Fine-Tuning
174 articles tagged with Fine-Tuning
On the Scaling of PEFT: Towards Million Personal Models of Trillion Parameters
Parameter-efficient fine-tuning (PEFT) is usually treated as a cheaper alternative to full fine-tuning. We study a broader role: small trainable adapters as persistent local state ...
LayerRoute: Input-Conditioned Adaptive Layer Skipping via LoRA Fine-Tuning for Agentic Language Models
Agentic language model systems alternate between two structurally distinct step types: structured tool calls (short, deterministic, low perplexity) and open-ended planning/reasonin...
Trajectory has released a concurrent multi-LoRA training stack for continual learning, built with UC Berkeley Sky Lab an...
Trajectory has released a concurrent multi-LoRA training stack for continual learning, built with UC Berkeley Sky Lab and Anyscale. Each experiment maps to a dedicated LoRA adapter...
Platforma Krea uruchamia zaawansowany system trenowania modeli LoRA, pozwalający tworzyć powtarzalne style i postaci z p...
Platforma Krea uruchamia zaawansowany system trenowania modeli LoRA, pozwalający tworzyć powtarzalne style i postaci z precyzją dostępną dotąd tylko w rozwiązaniach open-source. #s...
Cerebras (@cerebras)Cerebras Inference에서 Multi-LoRA가 비공개 프리뷰로 제공된다. 하나의 베이스 모델 위에 여러 LoRA 어댑터를 올려 요청마다 전환할 수 있으며, 재로딩이나 ...
Cerebras (@cerebras)Cerebras Inference에서 Multi-LoRA가 비공개 프리뷰로 제공된다. 하나의 베이스 모델 위에 여러 LoRA 어댑터를 올려 요청마다 전환할 수 있으며, 재로딩이나 별도 배포 없이 지연시간 증가도 없다고 한다. 여러 도메인·고객별 어댑터를 운영하는 추론 인프라에 실용적인 ...
How LoRA Remembers? A Parametric Memory Law for LLM Finetuning
Large Language Models (LLMs) must continuously learn and update knowledge to remain effective in dynamic real-world environments. While Low-Rank Adaptation (LoRA) is widely used fo...
Token-Level Generalization in LoRA Adapter Backdoors: Attack Characterization and Behavioral Detection
We show that LoRA adapters, the dominant distribution format for fine-tuned LLMs, can be reliably backdoored through training data poisoning while preserving baseline task performa...
MAAT: Multi-phase Adapter-Aware Targeted Unlearning
Machine unlearning evaluation is structurally skewed: Why-type questions, which probe causal and relational knowledge, comprise less than 0.06% of CounterFact, 0.6% of ZSRE, and le...
QuickCricketCherish/Stable-Diffusion-WebUI-Portable-Full-Pack: Stable Diffusion WebUI Portable with model pack, ControlNet, LoRA library, and extensions—full local AI art studio unlocked.
Stable Diffusion WebUI Portable with model pack, ControlNet, LoRA library, and extensions—full local AI art studio unlocked.
Ingi Erlingsson (@ingi_erlingsson)ComfyUI로 제작한 멀티툴 워크플로를 공유. LTX Model 2.3, FLW LoRA, Alibaba Wan 2.2 I2V/T2V, Florence-...
Ingi Erlingsson (@ingi_erlingsson)ComfyUI로 제작한 멀티툴 워크플로를 공유. LTX Model 2.3, FLW LoRA, Alibaba Wan 2.2 I2V/T2V, Florence-2, Meta Sapiens2, OpenAI GPT Image 2.0, Suno, Adobe AE 등을 조합...
ファインチューニングとLoRAの実践：AIモデル最適化の新たな潮流ファインチューニングとLoRAを使用してAIモデルを最適化する方法論と実践事例を解説します。精度の向上と計算資源の削減をどのように実現するかについて探討します。https:/...
ファインチューニングとLoRAの実践：AIモデル最適化の新たな潮流ファインチューニングとLoRAを使用してAIモデルを最適化する方法論と実践事例を解説します。精度の向上と計算資源の削減をどのように実現するかについて探討します。https://ai-blog-seven-wine.vercel.app/ja/posts/2026-05-27-am-gbf6t#...
PEFT-Arena: Understanding Parameter-Efficient Finetuning from a Stability-Plasticity Perspective
Parameter-efficient finetuning (PEFT) has become the standard approach for adapting large language models, yet evaluations largely emphasize downstream accuracy while overlooking t...
Eric Building... (@outsource_)Unsloth의 QLoRA 구현이 단일 GPU에서 27B급 모델 학습을 실제로 가능하게 만든다는 평가입니다. LLM 파인튜닝 실무에서 메모리 효율과 비용 측면의 ...
Eric Building... (@outsource_)Unsloth의 QLoRA 구현이 단일 GPU에서 27B급 모델 학습을 실제로 가능하게 만든다는 평가입니다. LLM 파인튜닝 실무에서 메모리 효율과 비용 측면의 가치가 큰 도구로 언급됩니다.https://x.com/outsource_/status/205904307253...
CollectionLoRA: Collecting 50 Effects in 1 LoRA via Multi-Teacher On-Policy Distillation
Customized image editing aims to equip pre-trained diffusion models with specific visual effects using limited paired data, typically via Low-Rank Adaptation (LoRA). As the number ...
This somehow feels very very dirty...TLDR for testing; It's a NVidia Tesla V100 SXM2 board, in an PCIe x16 adapter, for ...
This somehow feels very very dirty...TLDR for testing; It's a NVidia Tesla V100 SXM2 board, in an PCIe x16 adapter, for testing in oculink setup#LLM #Selfhosting #homeLab
LoRA lets you save tiny updates, not huge model copies.#ai #lora #llm
LoRA lets you save tiny updates, not huge model copies.#ai #lora #llm
WordPress 7.0 ships the AI Client. The Abilities API and MCP Adapter are what plugin developers should learn first.https...
WordPress 7.0 ships the AI Client. The Abilities API and MCP Adapter are what plugin developers should learn first.https://jorijn.com/en/blog/wordpress-7-0-abilities-mcp-plugin-dev...
Akshay (@akshay_pachaar)TransformerLab이 공개되었습니다. 어떤 클라우드의 GPU든 오케스트레이션해 사용자가 정의한 학습·평가 워크플로를 실행할 수 있는 오픈소스 플랫폼으로, LoRA/D...
Akshay (@akshay_pachaar)TransformerLab이 공개되었습니다. 어떤 클라우드의 GPU든 오케스트레이션해 사용자가 정의한 학습·평가 워크플로를 실행할 수 있는 오픈소스 플랫폼으로, LoRA/DPO/GRPO, MMLU, HellaSwag용 템플릿을 제공합니다. GUI, CLI, 에이전트 스킬로 사용할...
DIY AI Car Diagnostics with a $15 Bluetooth Adapter and Python
A few weeks ago the folding roof on my 2010 Ford Focus CC stopped working. The obvious suspect was...
HaoyuLi-Nova/Diffusion-Zero-to-Hero: Chinese hands-on diffusion models course: DDPM, DDIM, Diffusers, Stable Diffusion, CFG, LoRA, ControlNet, SDXL, DiT, Flow Matching, and video generation.
Chinese hands-on diffusion models course: DDPM, DDIM, Diffusers, Stable Diffusion, CFG, LoRA, ControlNet, SDXL, DiT, Flow Matching, and video generation.
LoRA and Weight Decay (2023)https://irhum.github.io/blog/lorawd/#HackerNews #Tech #MachineLearning
LoRA and Weight Decay (2023)https://irhum.github.io/blog/lorawd/#HackerNews #Tech #MachineLearning
【ロボットビデオ生成のためのLoRA/DoRAを使用したNVIDIA Cosmos Predict 2.5の微調整】https://huggingface.co/blog/nvidia/cosmos-fine-tuning-for-robo...
【ロボットビデオ生成のためのLoRA/DoRAを使用したNVIDIA Cosmos Predict 2.5の微調整】https://huggingface.co/blog/nvidia/cosmos-fine-tuning-for-robot-video-generation※AI生成の自動投稿（見出し＋リンク）#AI #生成AI #LLM #AIGener...
https://www.patreon.com/cw/NamelessdogLabPatreonでサポートしていただけるとWebUIで使用できるキャラクターLoraを公開しております。#ai
https://www.patreon.com/cw/NamelessdogLabPatreonでサポートしていただけるとWebUIで使用できるキャラクターLoraを公開しております。#ai