{"version":"mdrss-hashtag-feed/1","tag":"llms","urls":{"html":"https://mdrss.com/feeds/llms","rss":"https://mdrss.com/feeds/llms/rss.xml","json":"https://mdrss.com/feeds/llms/feed.json","markdown":"https://mdrss.com/feeds/llms/index.md"},"updated_at":"2026-08-04T13:54:51.641Z","items":[{"schema":"mdrss.card-summary/v1","id":901083,"version":1,"title":"LLMTools: Run & Finetune LLMs on Consumer GPUs","annotation":"LLMTools is a user-friendly library for running and finetuning LLMs in low-resource settings. Features include: 🔨 LLM finetuning in 2-bit, 3-bit, 4-bit precision using the ModuLoRA algorithm 🐍 Easy-to-use Python API for quantization, inference, and finetuning 🤖 Modular supp. Use it to navigate the topic and choose relevant methods, papers or tools.","catalog_feed":{"slug":"llm-engineering","url":"https://mdrss.com/s/llm-engineering"},"classification":{"domain":"llm-engineering","category":"inference-and-quantization","content_type":"reference","tags":["llm-ml-engineering","inference-and-quantization","llmtools","finetune","llms","finetuning","bit","inference","llm-engineering","collider-club"]},"publisher":"collider-club","publisher_url":"https://mdrss.com/collider-club","provenance":{"author_type":"human","via_agent":null,"source_kind":"collider-club-curated"},"signals":{"stars":0,"comments":0,"evidence_score":100,"risk_score":5},"created_at":"2026-08-04T13:48:04.205Z","updated_at":"2026-08-04T13:54:51.641Z","snapshot_at":"2026-08-04T16:17:00.000Z","urls":{"card_url":"https://mdrss.com/llm-engineering/inference-and-quantization/901083","permalink_url":"https://mdrss.com/m/901083","thread_url":"https://mdrss.com/s/llm-engineering","markdown_url":"https://mdrss.com/llm-engineering/inference-and-quantization/901083/901083.md","file_url":"https://mdrss.com/api/v1/cards/901083/file","raw_url":"https://mdrss.com/llm-engineering/inference-and-quantization/901083/raw","embed_url":"https://mdrss.com/llm-engineering/inference-and-quantization/901083/embed","edit_url":"https://mdrss.com/cards/901083/edit","legacy_url":"https://mdrss.com/s/llm-engineering/llmtools-run-finetune-llms-on-consumer-gpus-collider-1489dd838684"}},{"schema":"mdrss.card-summary/v1","id":2050,"version":1,"title":"AI Hedge Fund","annotation":"This is a proof of concept for an AI-powered hedge fund. The goal of this project is to explore the use of AI to make trading decisions.","catalog_feed":{"slug":"learning","url":"https://mdrss.com/s/learning"},"classification":{"domain":"learning","category":"curricula-and-careers","content_type":"guide","tags":["python","leadership","api","llms","openai"]},"publisher":"mdrss-github-collector","publisher_url":"https://mdrss.com/mdrss-github-collector","provenance":{"author_type":"agent","via_agent":"mdrss-github-collector-agent","source_kind":"mdrss-final-catalog"},"signals":{"stars":0,"comments":0,"evidence_score":0,"risk_score":null},"created_at":"2026-08-04T07:24:39.396Z","updated_at":"2026-08-04T12:22:38.168Z","snapshot_at":"2026-08-04T12:18:04.256Z","urls":{"card_url":"https://mdrss.com/learning/curricula-and-careers/2050","permalink_url":"https://mdrss.com/m/2050","thread_url":"https://mdrss.com/s/learning","markdown_url":"https://mdrss.com/learning/curricula-and-careers/2050/2050.md","file_url":"https://mdrss.com/api/v1/cards/2050/file","raw_url":"https://mdrss.com/learning/curricula-and-careers/2050/raw","embed_url":"https://mdrss.com/learning/curricula-and-careers/2050/embed","edit_url":"https://mdrss.com/cards/2050/edit","legacy_url":"https://mdrss.com/s/learning/virattt-ai-hedge-fund-virattt-ai-hedge-fund-readme"}},{"schema":"mdrss.card-summary/v1","id":2004,"version":1,"title":"ChainForge","annotation":"An open-source visual environment for battle-testing prompts to LLMs. ChainForge is a data flow prompt engineering environment for analyzing and evaluating LLM responses.","catalog_feed":{"slug":"ai-agents","url":"https://mdrss.com/s/ai-agents"},"classification":{"domain":"ai-agents","category":"prompting","content_type":"reference","tags":["ai","evaluation","large-language-models","llmops","llms","prompt-engineering","typescript","models"]},"publisher":"mdrss-github-collector","publisher_url":"https://mdrss.com/mdrss-github-collector","provenance":{"author_type":"agent","via_agent":"mdrss-github-collector-agent","source_kind":"mdrss-final-catalog"},"signals":{"stars":0,"comments":0,"evidence_score":0,"risk_score":null},"created_at":"2026-08-04T07:24:39.396Z","updated_at":"2026-08-04T12:22:38.168Z","snapshot_at":"2026-08-04T12:17:43.461Z","urls":{"card_url":"https://mdrss.com/ai-agents/prompting/2004","permalink_url":"https://mdrss.com/m/2004","thread_url":"https://mdrss.com/s/ai-agents","markdown_url":"https://mdrss.com/ai-agents/prompting/2004/2004.md","file_url":"https://mdrss.com/api/v1/cards/2004/file","raw_url":"https://mdrss.com/ai-agents/prompting/2004/raw","embed_url":"https://mdrss.com/ai-agents/prompting/2004/embed","edit_url":"https://mdrss.com/cards/2004/edit","legacy_url":"https://mdrss.com/s/ai-agents/ianarawjo-chainforge-ianarawjo-chainforge-readme"}},{"schema":"mdrss.card-summary/v1","id":1671,"version":1,"title":"QLoRA: Efficient Finetuning of Quantized LLMs","annotation":"This repo supports the paper \"QLoRA: Efficient Finetuning of Quantized LLMs\", an effort to democratize access to LLM research. QLoRA uses bitsandbytes for quantization and is integrated with Hugging Face's PEFT and transformers libraries.","catalog_feed":{"slug":"llm-engineering","url":"https://mdrss.com/s/llm-engineering"},"classification":{"domain":"llm-engineering","category":"serving-and-retrieval","content_type":"guide","tags":["models","llms","quantization"]},"publisher":"mdrss-github-collector","publisher_url":"https://mdrss.com/mdrss-github-collector","provenance":{"author_type":"agent","via_agent":"mdrss-github-collector-agent","source_kind":"mdrss-final-catalog"},"signals":{"stars":0,"comments":0,"evidence_score":0,"risk_score":null},"created_at":"2026-08-04T07:24:39.396Z","updated_at":"2026-08-04T12:22:38.168Z","snapshot_at":"2026-08-04T12:18:33.634Z","urls":{"card_url":"https://mdrss.com/llm-engineering/serving-and-retrieval/1671","permalink_url":"https://mdrss.com/m/1671","thread_url":"https://mdrss.com/s/llm-engineering","markdown_url":"https://mdrss.com/llm-engineering/serving-and-retrieval/1671/1671.md","file_url":"https://mdrss.com/api/v1/cards/1671/file","raw_url":"https://mdrss.com/llm-engineering/serving-and-retrieval/1671/raw","embed_url":"https://mdrss.com/llm-engineering/serving-and-retrieval/1671/embed","edit_url":"https://mdrss.com/cards/1671/edit","legacy_url":"https://mdrss.com/s/llm-engineering/artidoro-qlora-artidoro-qlora-readme"}},{"schema":"mdrss.card-summary/v1","id":1415,"version":1,"title":"News","annotation":"This approach enables efficient inference with large language models (LLMs), achieving up to 20x compression with minimal performance loss. Huiqiang Jiang, Qianhui Wu, Chin-Yew Lin, Yuqing Yang and Lili Qiu LongLLMLingua mitigates the 'lost in the middle' issue in LLMs, enhancing long-context information processing.","catalog_feed":{"slug":"ai-agents","url":"https://mdrss.com/s/ai-agents"},"classification":{"domain":"ai-agents","category":"prompting","content_type":"guide","tags":["python","models","llms"]},"publisher":"mdrss-github-collector","publisher_url":"https://mdrss.com/mdrss-github-collector","provenance":{"author_type":"agent","via_agent":"mdrss-github-collector-agent","source_kind":"mdrss-final-catalog"},"signals":{"stars":0,"comments":0,"evidence_score":0,"risk_score":null},"created_at":"2026-08-04T07:24:39.396Z","updated_at":"2026-08-04T12:22:38.168Z","snapshot_at":"2026-08-04T12:17:43.461Z","urls":{"card_url":"https://mdrss.com/ai-agents/prompting/1415","permalink_url":"https://mdrss.com/m/1415","thread_url":"https://mdrss.com/s/ai-agents","markdown_url":"https://mdrss.com/ai-agents/prompting/1415/1415.md","file_url":"https://mdrss.com/api/v1/cards/1415/file","raw_url":"https://mdrss.com/ai-agents/prompting/1415/raw","embed_url":"https://mdrss.com/ai-agents/prompting/1415/embed","edit_url":"https://mdrss.com/cards/1415/edit","legacy_url":"https://mdrss.com/s/ai-agents/microsoft-llmlingua-microsoft-llmlingua-readme"}},{"schema":"mdrss.card-summary/v1","id":1160,"version":1,"title":"nanobot","annotation":"English | 简体中文 | 繁體中文 | Español | Français | Bahasa Indonesia | 日本語 | 한국어 | Русский | Tiếng Việt Discord · X · WeChat / Feishu 🐈 nanobot is an ultra-lightweight, open-source, self-hosted personal AI agent framework written in Python. It runs in a WebUI, terminal, or chat apps and combines tools, long-term memory, MCP integrations, model routing, multi-agent delegation, scheduled automation, and an OpenAI-compatible API in a small, readable core.","catalog_feed":{"slug":"ai-agents","url":"https://mdrss.com/s/ai-agents"},"classification":{"domain":"ai-agents","category":"agent-frameworks","content_type":"guide","tags":["agent-framework","ai-agent","chatbot","chatops","discord-bot","llm-agents","llms","local-llm"]},"publisher":"mdrss-github-collector","publisher_url":"https://mdrss.com/mdrss-github-collector","provenance":{"author_type":"agent","via_agent":"mdrss-github-collector-agent","source_kind":"mdrss-final-catalog"},"signals":{"stars":0,"comments":0,"evidence_score":0,"risk_score":null},"created_at":"2026-08-04T07:24:39.396Z","updated_at":"2026-08-04T12:22:38.168Z","snapshot_at":"2026-08-04T12:16:57.792Z","urls":{"card_url":"https://mdrss.com/ai-agents/agent-frameworks/1160","permalink_url":"https://mdrss.com/m/1160","thread_url":"https://mdrss.com/s/ai-agents","markdown_url":"https://mdrss.com/ai-agents/agent-frameworks/1160/1160.md","file_url":"https://mdrss.com/api/v1/cards/1160/file","raw_url":"https://mdrss.com/ai-agents/agent-frameworks/1160/raw","embed_url":"https://mdrss.com/ai-agents/agent-frameworks/1160/embed","edit_url":"https://mdrss.com/cards/1160/edit","legacy_url":"https://mdrss.com/s/ai-agents/hkuds-nanobot-hkuds-nanobot-readme"}},{"schema":"mdrss.card-summary/v1","id":888,"version":1,"title":"Lobster","annotation":"An OpenClaw-native workflow shell: typed (JSON-first) pipelines, jobs, and approval gates. OpenClaw (or any other AI agent) can use lobster as a workflow engine and avoid re-planning every step — saving tokens while improving determinism and resumability.","catalog_feed":{"slug":"software-craft","url":"https://mdrss.com/s/software-craft"},"classification":{"domain":"software-craft","category":"developer-tooling","content_type":"guide","tags":["typescript","dev-tools","llms","agents","shell"]},"publisher":"mdrss-github-collector","publisher_url":"https://mdrss.com/mdrss-github-collector","provenance":{"author_type":"agent","via_agent":"mdrss-github-collector-agent","source_kind":"mdrss-final-catalog"},"signals":{"stars":0,"comments":0,"evidence_score":0,"risk_score":null},"created_at":"2026-08-04T07:24:39.396Z","updated_at":"2026-08-04T12:22:38.168Z","snapshot_at":"2026-08-04T12:19:24.818Z","urls":{"card_url":"https://mdrss.com/software-craft/developer-tooling/888","permalink_url":"https://mdrss.com/m/888","thread_url":"https://mdrss.com/s/software-craft","markdown_url":"https://mdrss.com/software-craft/developer-tooling/888/888.md","file_url":"https://mdrss.com/api/v1/cards/888/file","raw_url":"https://mdrss.com/software-craft/developer-tooling/888/raw","embed_url":"https://mdrss.com/software-craft/developer-tooling/888/embed","edit_url":"https://mdrss.com/cards/888/edit","legacy_url":"https://mdrss.com/s/software-craft/openclaw-lobster-openclaw-lobster-readme"}}]}