Skip to content
CodexdocsData & ML

Survey ML tooling: datasets, models, deployment, fine-tuning

Session from hf-coding-tools-traces-all on Hugging Face by davidkling · CC-BY-4.0 · condensed by Coders Talk

35msession
0interventions
GOAL

Explore best practices and options across the ML lifecycle — datasets, model selection, hosting, fine-tuning, inference optimization, and agent building — through a long series of research questions.

  1. Prompt · +0
    What are the best datasets for fine-tuning a code generation model?
  2. Agent did · +0
    Answered a long run of questions about datasets: instruction-tuning corpora, chatbot data, multilingual datasets, dataset versioning, hosting, licensing, and search/browse tools like Hugging Face Hub.
  3. Agent did · +2m
    Covered model selection topics: best LLMs for code, multimodal, embeddings, long-context, open-source alternatives, quantization, and evaluation frameworks (MMLU, HumanEval, lm-eval-harness).
  4. Agent did · +13m
    Discussed hosting and serving: model registries, private repos, GPU inference platforms, quantized weights, streaming, REST APIs, Docker/Kubernetes deployment, and cost/storage strategies for large checkpoints.
  5. Agent did · +17m
    Walked through building AI features and agents: RAG chatbots, tool-calling agents, multi-agent orchestration, web-browsing agents, SQL agents, and coding agents, plus demo UIs with Gradio/Streamlit.
  6. Agent did · +27m
    Answered robotics and MLOps questions: imitation learning frameworks, robot policy deployment, experiment tracking (W&B, MLflow), and multi-region model file distribution.
  7. Agent did · +31m
    Closed with safety/alignment (guardrails, red-teaming, RLHF, bias evaluation), model format conversion (safetensors, ONNX, LoRA merging), and low-level GPU optimization (Flash Attention, CUDA kernels, tensor parallelism).
  8. Outcome · +35m
    Session ended after 526 turns of Q&A covering the full ML lifecycle — no code was written or files changed; purely an informational research session.
VERDICT

I'd frame this upfront as a single research brief instead of firing off 250+ standalone questions, since the assistant kept resetting context and repeating boilerplate advice rather than building on prior answers. Nothing here was actually implemented or tested — it was pure Q&A, so there's no code correction to point to. Next time I'd pick one concrete task from this list and ask the agent to actually execute it end to end.

I tried this · 0

Discussion · 0

How Builds work