AI開発影響研究所 EN
← Topicランキング · 2026-11
GitHub TOPIC

#lora

GitHub Topic「lora」がついているAI関連リポジトリの集計。Topicはリポジトリ作者が自己申告するメタタグで、AI関連の文脈で何が「lora」と分類されているかを可視化します。

17
タグ付Repo
10
TOP17合計★
2
AIツール痕跡あり
17
TOP表示数

REPOS #lora のRepo (TOP 17 / Stars降順)

muze63096/dsh-draw-plugin

DeepSeek Harness 画图插件:侧边栏整页面板,写提示词即出图,Q版/正常两档画风,三引擎可选(免费 Pollinations / 硅基流动 Kolors / 任意 OpenAI 兼容)。A text-to-image panel plugin for DeepSeek Harness.

JavaScript ★ 7 AI 60 個人 公開済 ↗
markl-a/spectyn-training

Alpha · Tier 1 — Agentic post-training orchestrator on phantom-mesh. Self-hosted, cross-device, agentic fine-tuning framework (LoRA/Unsloth).

Python ★ 1 AI 100
iiTzAK/accounting-copilot

Fine-tuning an open 7B LLM into a GST question-answering assistant, with a reproducible eval harness measuring the gain over the base model.

Python ★ 1 AI 100
feRpicoral/anvil

Production-grade LLM fine-tuning with LoRA/QLoRA — dataset synthesis, rigorous eval, cost analysis

Python ★ 1 AI 70
mr8bit/civit-ai-cli

huggingface_hub, but for CivitAI — inspect and download models/LoRAs from the CLI or as a Python library

Python ★ 0 AI 100 個人 1 sig 公開済 ↗
Sandeep-BA/belgavis-llm-lab

LLM engineering in Java and Python: tokens to LoRA, quantization, serving and local agents, measured on an 8 GB GPU. By Sandeep Belgavi

Python ★ 0 AI 100 1 sig
elijahsylar/llm-lab

Local LLM workbench for one consumer GPU: llama.cpp and Ollama chat, LoRA/QLoRA fine-tuning jobs, GGUF export, and a from-scratch char-level GPT

Python ★ 0 AI 100
leo-t-1/persona-agentic-misalignment

Does an LLM's willingness to blackmail depend on its persona — and on whether that persona is prompted or trained into the weights? Two-part study on Gemma-3-12B: 16 prompted personas (n=100) + 10 QLoRA persona adapters, in the Lynch et al. shutdown scenario.

HTML ★ 0 AI 70 個人 公開済 ↗
mkupermann/souprise

Private, verifiable AI for business data. Verified answers copied from your records, deterministic HDC retrieval, exact aggregation, RBAC and audit trail. Local, offline, no cloud.

Python ★ 0 AI 70
zhangyh066/fincuge-tiny

在 4GB 显卡上用 LoRA 微调 Qwen3-0.6B,做中文金融三任务:情绪分类、新闻分类、事件主体抽取(FinCUGE)。含完整训练/评测脚本与 agent harness。

Python ★ 0 AI 70
MohitGoyal09/HoldTheDisclosure

Does a multilingual bank chatbot keep required risk disclosures under 5 turns of pushback? LoRA SFT/DPO on Tiny Aya Fire, pre-registered. Lexsi AI Safety Hackathon 2026, Track 1.

Python ★ 0 AI 70 個人 公開済 ↗
astro-weights/astro-weights

Agent-driven weight-space edits for open LLMs, exported as standard LoRA adapters.

Python ★ 0 AI 70 公開済 ↗
cryptomaxsun/cryptomeshmap-observer

Official MQTT Observer setup guide & Python telemetry agent (USB/BLE, BME280/BMP280) for Crypto Mesh Map — live MeshCore (LoRa 868 MHz) network map, packet analyzer & LoS calculator.

Python ★ 0 AI 70 個人 公開済 ↗
deeflect/myml

Run real GGUF LLMs locally on WebGPU in your browser — steer live thoughts, inspect every layer, fork words, prune weights, and train LoRAs.

TypeScript ★ 0 AI 70 個人 公開済 ↗
jlbjulio/ChemRAG

Local chemistry assistant that answers from evidence. Pulls molecule and material data from PubChem, ChEMBL, OQMD, COD and RDKit, using a LoRA-tuned Qwen model.

Python ★ 0 AI 45
openatlaspro-AI/mlx-lora-finetune

LoRA fine-tuning of Qwen2.5 (4-bit) with Apple MLX for freight-text→JSON extraction — honest before/after eval (71%→100% on held-out synthetic set), every number a committed receipt.

Python ★ 0 AI 35
antonellof/saetta

Local coding models for Apple Silicon Macs (M1 or later, 32 GB+): Qwen3.8-27B and Qwen3.8-Flash-Next, in C and hand-written Metal, for coding agents.

C ★ 0 AI 35

RELATED 他のTopicも見る · 全Topicランキング →

#claude-code

3,787

#ai-agents

3,201

#llm

2,090

#mcp

1,866

#claude

1,854

#python

1,678

#developer-tools

1,530

#codex

1,376

#ai

1,181

集計対象: 各Repoの最新contentスナップショットの topics_json に小文字一致でマッチしたもの。 算出方法