fix(cli): point 7B qwen models to single-file GGUF artifacts and align caches#1891
Closed
noahgift wants to merge 3 commits into
Closed
fix(cli): point 7B qwen models to single-file GGUF artifacts and align caches#1891noahgift wants to merge 3 commits into
noahgift wants to merge 3 commits into
Conversation
- Added qwen2.5-coder-1.5b alias to configs/aliases.yaml to fix apr pull qwen2.5-coder-1.5b - Fixed apr run and apr chat to resolve short name aliases using the same logic as apr pull - Fixed apr run cache checking logic to look in the Pacha streaming cache directory, ensuring apr run uses models successfully fetched by apr pull without attempting to re-download. - Fixed apr serve usage in README.md to apr serve run.
58b07c3 to
014b44e
Compare
- Update configs/aliases.yaml to point qwen2.5 to the Q3_K_M GGUF file and qwen2.5-coder to the Q4_K_M GGUF file. - Prevent apr run from mistaking local file paths containing slashes for Hugging Face repos. - Fix pull logic for selecting the best single-file artifact when shards are mixed in.
014b44e to
75e7341
Compare
Contributor
Author
auto-merge was automatically disabled
May 23, 2026 07:09
Pull request was closed
noahgift
added a commit
that referenced
this pull request
May 23, 2026
PR #1891 wrapped all path_arg through HF alias resolution. For inputs that look like filesystem paths (absolute or starts with ./, ../) and don't exist, the alias resolver was rewriting them as hf:// URIs and returning a mangled path in the FileNotFound error. Fix: short-circuit with the original path_arg in the error BEFORE alias resolution kicks in. Preserves the contract that test_run_file_not_found and test_run_nonexistent_path_without_trace assert. Closes the workspace-test failure on bundle PR #1898.
noahgift
added a commit
that referenced
this pull request
May 23, 2026
, #1896, #1897) (#1898) * docs(spec): SPEC-DISTILL-001 §87 — PMAT-704 post-mortem on Bug B wrong turn (#1880) * chore(distill): Stage D dispatch wrapper with PMAT-701 lessons baked in (#1883) * chore(distill): Phase 5 HumanEval dispatch wrapper (#1886) * chore: bundle PMAT-702..705 distill cascade + clippy fix (#1897) * fix(cli): point 7B qwen models to single-file GGUF artifacts and align caches (#1891) * fix(chat): preserve original path in FileNotFound for filesystem paths PR #1891 wrapped all path_arg through HF alias resolution. For inputs that look like filesystem paths (absolute or starts with ./, ../) and don't exist, the alias resolver was rewriting them as hf:// URIs and returning a mangled path in the FileNotFound error. Fix: short-circuit with the original path_arg in the error BEFORE alias resolution kicks in. Preserves the contract that test_run_file_not_found and test_run_nonexistent_path_without_trace assert. Closes the workspace-test failure on bundle PR #1898.
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.
configs/aliases.yamlto pointqwen2.5toq3_k_m.ggufandqwen2.5-codertoq4_k_m.gguf, utilizing the fast single-file.ggufbypass rather than triggering sharded resolution issues or unsupported quantization types in the inference engine.apr runandapr chatto resolve aliases using the same module asapr pull.apr runqueries the Pacha download directory, eliminating cache misses after a successfulapr pull.apr serveusage inREADME.mdtoapr serve run.