Fine-tuning an LLM to write docs like it's 1995
Hacker News (AI keywords)9 days agoTutorialThe author builds a corpus from old Microsoft manuals, cleans OCR text, generates instruction-style JSONL examples, and fine-tunes Llama 3.1 8B and Qwen 2.5 7B with QLoRA. Tests cover malloc(), a fictional Win32 API, and a deliberately anachronistic REST API prompt. Qwen fine-tunes transfer the period documentation style best, but the experiment also shows hallucination risks, tuning complexity, and why these models augment rather than replace technical writers.
Ideogram 3.0 正式登陸 Replicate：強大的設計、風格遷移與寫實影像生成★ 75
Replicate Blog403 days agoReleaseIdeogram, a standout in the AI image generation space, has launched its latest-generation model Ideogram 3.0, which is now officially available on the AI model…
使用 Wan2.1 進行風格化影片生成：結合 LoRA 實現獨特視覺風格★ 75
Replicate Blog439 days agoTutorialAlibaba's open-source Wan2.1 is a video generation model that has been receiving widespread attention, and Replicate's latest guide focuses on how to use LoRA…