AGENT SKILL

generation

Routes GPT2-Chinese prompt-based text generation and batch sample export.

License 许可
MIT
最近更新
2026-09-03
Stars
★ 351
Forks
27

01 前言 Front Matter

name
generation
license
MIT
metadata
{ "disco-role": "operating" }
description
Routes GPT2-Chinese prompt-based text generation and batch sample export.
disable-model-invocation
true

02 资源文件 1

03 SKILL.md 正文

Generation

Use this sub-skill when the task is about generating text from a checkpoint with generate.py or generate_texts.py.

Read first

  • ../references/workflows.md for the end-to-end generation flow.
  • ../references/cli-reference.md for the exact flags and output paths.
  • ../references/model-overview.md when you need to match a checkpoint to a vocabulary bundle.
  • ../references/troubleshooting.md and this sub-skill's troubleshooting file for loop, prompt, and sample-saving issues.
  • ../../scripts/check_install.py when you want to confirm the environment can instantiate the model and sample a token sequence.

What belongs here

  • Prompted generation from a checkpoint directory.
  • generate.py for interactive or single-prompt generation.
  • generate_texts.py for batch generation by title list.
  • Sampling controls such as --prefix, --length, --temperature, --topk, --topp, and --repetition_penalty.
  • Sample saving via --save_samples or --save_path.

What does not belong here

  • Corpus preprocessing and checkpoint creation belong in training.
  • Tokenizer or vocabulary creation belongs in tokenization.
  • Generic sampling theory without this repo's CLI behavior belongs elsewhere.

How to route a generation request

  1. Pick the output shape.
    • One prompt, one stream of text: use generate.py.
    • Multiple titles or articles on disk: use generate_texts.py.
  2. Choose the checkpoint and vocab pair.
    • model_path or model_path should point at a saved checkpoint directory.
    • tokenizer_path must match the config and checkpoint vocab size.
  3. Choose the prompt form.
    • The usual checkpoints expect a [CLS]-prefixed prompt.
    • The prompt is tokenized before sampling, so keep the tokenizer mode in mind.
  4. Choose the decoding behavior.
    • --fast_pattern is the preferred smoke path.
    • --topk, --topp, and --temperature shape the sampling distribution.
  5. Choose the save target.
    • --save_samples writes a samples.txt file.
    • generate_texts.py writes one text file per generated article.

Common decision points

  • If the user wants a quick demo, keep --batch_size 1 and use a short length.
  • If the user wants file-based batch output, use the title list interface instead of copy-pasting one prompt at a time.
  • If the user is asking why the same sample repeats, check nsamples versus batch_size first.
  • If the task is really about tokenization quality or vocabulary choice, route back to the tokenization sub-skill.

Output expectations

  • Printed samples on stdout for the interactive path.
  • samples.txt when --save_samples is used.
  • <title-index>-<article-index>.txt files when generate_texts.py is used.

04 同仓库更多 Skills

VectorSpaceLab
VectorSpaceLab/AREX-Skill

passnet-triton-opt

Make a single PassNet Triton kernel fast AND numerically faithful: performance model (when a replacement can win at all), block/grid/warp tuning, autotune policy, launch overhead, and per-op numeric recipes to pass the dtype baseline tolerances. Use when a pass matches and is correct but speedup below expected, or when correctness fails by small numeric margins.

★ 351
VectorSpaceLab
VectorSpaceLab/AREX-Skill

passnet-solve

END-TO-END playbook for solving one PassNet sample: analyze the computation graphs, decide the optimization strategy (what to fuse, what to replace, what to leave alone), drive the iteration loop, and maximize the sample score. This is the ENTRY skill — invoke it first for any PassNet optimization task; it tells you when to use passnet-pattern-fusion, passnet-triton-opt and passnet-feedback.

★ 351
VectorSpaceLab
VectorSpaceLab/AREX-Skill

passnet-skill

PassNet GPU kernel optimization via compiler passes. Design and implement Triton-based optimization passes, create pass files under ./pass_dir/, self-evaluate with pass_evaluator, and iterate to maximize GPU speedup.

★ 351
VectorSpaceLab
VectorSpaceLab/AREX-Skill

passnet-pattern-fusion

Author PassNet pass files: write patterns that actually MATCH the FX graph, pick fusion regions (which ops to absorb into one Triton kernel), and structure multi-pass submissions with the mandatory shared-dispatch architecture. Use when creating or fixing pattern()/replacement_args()/replacement_func() files, when a pass "failed to match", or when deciding how to fuse multiple kernels/ops.

★ 351
VectorSpaceLab
VectorSpaceLab/AREX-Skill

passnet-orchestrate

Round/batch planning and decision support for PassNet graph optimization. Use for multi-sample triage, worker allocation, eval-budget policy, and post-eval keep/revert decisions. For solving one concrete sample end to end, use passnet-solve as the entry skill; consult this skill only when you need broader planning or a specific decision gate.

★ 351
VectorSpaceLab
VectorSpaceLab/AREX-Skill

passnet-feedback

Fast, deterministic feedback for PassNet work: pre-flight pattern/match verification WITHOUT burning a GPU evaluation, per-node bottleneck analysis of a sample's graphs, and eval-log parsing into per-variant status + estimated score + failure classification. Use BEFORE every GPU evaluation (check_pattern), at the START of a sample (analyze_graph), and AFTER every evaluation (parse_eval_log).

★ 351