docs: repoint the local GGUF probe at ~/.jev-browser/models - #3
Merged
Merged
Conversation
The 0.8B GGUF no longer lives in the repo root; it sits in the shared cache next to the other local backends' blobs (same file: 811,843,840 B, sha256 0ad885ff…). Update the model table, the location note and the llama-server repro command accordingly.
The driver scripts the experiment records told readers to run lived only under /tmp (jev-ceiling, jev-local-smoke, gguf, kev-threshold) and are gone with the cleanup, never committed. Each reference now says so and gives the recreation step from tracked tools: eval/run.mjs + cli.mjs for the 4B per-candidate protocol, lab/fetch.mjs for the download retry, the §7.3 dry-run flow for the smoke probes, and a copy of the tracked journals for the Kev threshold replay.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Follow-up to the local model backends work.
The 0.8B GGUF the probe used no longer lives in the repo root — it sits in the shared model cache next to the other local backends' blobs (same file: 811,843,840 B, sha256
0ad885ffd4bb022fc4f0d33a3308fa108ef8613159d3b3a67e23abca056b7a6c).This updates
docs/local-gguf-probe.mdonly:./Qwen3.5-0.8B-Q8_0.gguf（仓库根目录）→~/.jev-browser/models/Qwen3.5-0.8B-Q8_0.gguf*.ggufis covered by.gitignore-m "$PWD/Qwen3.5-0.8B-Q8_0.gguf"→-m ~/.jev-browser/models/Qwen3.5-0.8B-Q8_0.ggufDocs-only, no behaviour change.