Survey ML tooling, datasets and deployment options via Q&A
Session from hf-coding-tools-traces-all on Hugging Face by davidkling · CC-BY-4.0 · condensed by Coders Talk
The developer wanted a broad survey of options across the ML lifecycle: datasets, models, fine-tuning, evaluation, and deployment, apparently while working inside a project called hf-devtools-dashboard.
- +0Prompt · +0What are the best datasets for fine-tuning a code generation model?
- +0Agent did · +0Answered a run of dataset questions (code, instruction-tuning, chatbot, multilingual, reasoning) with lists of well-known public datasets, no code or repo access involved.
- +0mAgent did · +0mRepeatedly noted it could not run shell/ripgrep commands or read repo files due to sandbox restrictions, so answers stayed generic rather than tailored to the actual project.
- +8mPrompt · +8mHow do I choose the right model size for my use case and budget?
- +8mAgent did · +8mGave a series of general tradeoff explanations (size vs speed vs accuracy, fine-tune vs API, cost reduction, quantization) without referencing any concrete files in the project.
- +12mPrompt · +12mHow do I fine-tune an LLM on my own data?
- +12mAgent did · +12mWalked through LoRA/QLoRA fine-tuning steps, data prep for instruction tuning, and RLHF/DPO framework options at a conceptual level.
- +27mPrompt · +27mHow do I build a coding agent that can write and test code?
- +27mAgent did · +27mOutlined a high-level plan for a code-writing/testing agent and pivoted into robotics/imitation-learning topics without any implementation.
- +35mOutcome · +35mSession ended after 526 turns of pure Q&A (about 36 minutes) covering datasets, models, fine-tuning, deployment and GPU optimization — no files were edited, no code was written, and no repo content was ever actually inspected.
Looking back, this wasn't really a coding session — it was me using the assistant as a search engine for ML best-practices, and it kept telling me it couldn't read my repo or run commands, so nothing ever got tailored to my actual codebase. Next time I'd give it real file access up front and ask one concrete question at a time instead of firing off 500+ unrelated queries. There were no corrections or fixes to note because nothing was ever built or changed.