AutoAudit—— the LLM for Cyber Security 网络安全大语言模型
-
Updated
Feb 28, 2025 - HTML
#
qlora
Here are 15 public repositories matching this topic...
Fine-tune your own LLM on an AMD Radeon GPU — the easy, tested way. QLoRA via ROCm on Windows/WSL2 & Linux, a worked Gemma-4 example, a reusable live training dashboard, and a smoke test that proves the loss falls.
-
Updated
Jun 20, 2026 - HTML
🌐 Run GGUF models directly in your web browser using JavaScript and WebAssembly for a seamless and flexible AI experience.
python nlp data machine-learning openai gpt quantization agents fine-tuning multi-agents finetuning langchain instruction-tuning llama-cpp ggml llamaindex qlora deepseek
-
Updated
Jul 1, 2026 - HTML
Claude Code Mastery 2026 – 176 Expert Tips & Cheatsheet from 17 Repositories
developer-tools fine-tuning huggingface ml-engineering hugging-face prompt-engineering qlora ai-coding claude-code subagents claude-code-guide claude-code-subagents claude-md claude-code-plugin claude-code-skills claude-code-tutorial claude-code-best-practices
-
Updated
Jul 1, 2026 - HTML
Hands-on local LLM fine-tuning course (SFT / LoRA / PEFT / DPO / QLoRA) with a browser studio that visualizes loss, tensors, and adapter diffs.
machine-learning tutorial transformers chinese lora study-notes fine-tuning peft finetuning sft dpo huggingface apple-silicon llm qlora chinese-llm
-
Updated
May 6, 2026 - HTML
Technical architecture for an AI-native Operating System. Features a 3-tier agentic hierarchy (Macro, Meso, Micro), Rust-based kernel, distributed error recovery, and nightly QLoRA self-learning loops
rust multi-agent-system mlops apple-silicon fipa-protocols qlora ai-os-agent-safety-developer-tools-architecture scm-magellano
-
Updated
Mar 22, 2026 - HTML
Production LoRA/QLoRA fine-tuning platform for LLMs: Gemma-2, Llama-3.2, Mistral-7B with PEFT, 4-bit quantization, DPO alignment and automated evaluation on custom datasets
-
Updated
Jun 10, 2026 - HTML
QLoRA fine-tuning of a 1.2B model to beat 1T+ baselines on 7x7 grid spatial-design tasks
-
Updated
May 23, 2026 - HTML
Cybersecurity threat intelligence assistant — fine-tuned Llama-3.1-8B on 9,992 NVD CVE records with dual-source RAG grounding (live NVD API + threat actor KB). Zero hallucinations on benchmark. SSE streaming. Two UI themes.
react python streaming llama nvd threat-intelligence cyberse mitre-attack rag fastapi qlora llm-finetuning cve-analysis
-
Updated
May 20, 2026 - HTML
MIN-0 is an alphanumeric constructed language (conlang) spoken by MIN-0, a sentient automaton from the planet RB-0. The language encodes grammatical information - tense, voice, aspect, negation, modality, number, and more directly into alphanumeric symbol sequences using a deterministic rule-based algorithm.
-
Updated
May 9, 2026 - HTML
Run Llama models in your web browser using JavaScript and WebAssembly. Explore light and dark modes easily. 🌐🐱👤
nlp data machine-learning framework ai gpt lora fine-tuning peft large-language-models llm langchain rlhf vllm llamaindex qlora qwen llama3
-
Updated
Jul 1, 2026 - HTML
Project-aware AI architect assistant for the full SDLC. Per-project RAG, domain-adaptive fine-tuning (QLoRA), automated PR review, and a model registry — all self-hosted with Ollama.
java ai spring-boot self-hosted developer-tools code-review sdlc fine-tuning rag llm qlora ollama spring-ai
-
Updated
May 29, 2026 - HTML
Can a small VLM tell you if you can park in SF?
-
Updated
Jun 25, 2026 - HTML
CLI-based AI tool for fine-tuning LLMs using LoRA & QLoRA with an efficient, modular pipeline.
-
Updated
Apr 9, 2026 - HTML
Improve this page
Add a description, image, and links to the qlora topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the qlora topic, visit your repo's landing page and select "manage topics."