Evol-1 T04: local LLM setup on lab Ollama - #83
Merged
Conversation
…raction. Wire a digest-pinned qwen3:8b client (temp 0, JSON schema, retry/abstain) and record a 10-page lab throughput baseline for T05. Co-authored-by: Cursor <cursoragent@cursor.com>
…ntries. Co-authored-by: Cursor <cursoragent@cursor.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
qwen3:8bon lab Ollama (research.neu.edu.vn) with digest check, temperature 0, JSON schema output, retry then abstain.ml/local_llm/client + schema for T05 indicators, ADR-0004 (paper numbers must not use closed narrative APIs), and a 10-page smoke run (~1211 pages/hour wall, 10/10 schema-ok).data/raw/local_llm/with provenance; CI stays mock-only viatests/local_llm.Scratch / docs
docs/evol-1.mdT04 · ADR:docs/adr/0004-local-llm-ollama.mddata/processed/local_llm/run_manifest.json,smoke_run.jsonTest plan
PYTHONPATH=. pytest -q tests/local_llm(16 passed)PYTHONPATH=. python scripts/run_local_llm_smoke.py --fetch-pages(lab live; digest match)PYTHONPATH=. pytest -q(full suite / CI)Checklist
cursor/evol1-task04-local-llm-setup.env, secrets, large raw dumps, or model binariesMade with Cursor