Claude/qwen claude reverse eng v hu hv - #76
Merged
Conversation
Release v0.1.0-bgz-data now has 43 assets: 41 × Qwen3.5 models (685 MB) 1 × reader-lm-1.5b.bgz7 (26 MB) — HTML→Markdown structure 1 × bge-m3-f16.bgz7 (7.3 MB) — multilingual embeddings Total: 718 MB bgz7 from ~210 GB original weights. manifest.json updated with SHA256 for both new models. https://claude.ai/code/session_01M3at4EuHVvQ8S95mSnKgtK
…1-indexed Release assets: shard-01..shard-11 (1-indexed, from indexing pipeline) Manifest/local: shard-00..shard-10 (0-indexed, matching bgz7_path()) Fix: download URL uses shard+1, local storage stays shard. Without this fix, hydrate --download tries to fetch shard-00 which doesn't exist in the release, causing 404 on every model. https://claude.ai/code/session_01M3at4EuHVvQ8S95mSnKgtK
Endpoints: POST /v1/chat/completions — all 7 models (qwen35-opus46/45, 9b, reader-lm, bge-m3, llama4-scout, openchat-3.5) POST /v1/embeddings — Base17 fingerprints as 17-dim OpenAI embedding format GET /v1/models — 7 models with descriptions and bgz7 sizes GET /health — ok Fixes: - Model validation: unknown models → 404 with available list - Model descriptions include bgz7 size and purpose Latency: 7ms per request. Tested with 10-test curl suite. https://claude.ai/code/session_01M3at4EuHVvQ8S95mSnKgtK
bge-m3: XLM-RoBERTa forward pass (24 layers, GELU, mean pool, L2 norm) + SentencePiece tokenizer stub + embed_to_base17() projection reader-lm: Qwen2 forward pass (28 layers, GQA 12:2, RoPE, SwiGLU) + BPE tokenizer stub + generate() + html_to_markdown() Both fall back to deterministic hash when no weights loaded. Key finding: bgz7 dims have σ=0.5, range=[-2,+2], L1 μ=2.9 σ=1.8 → SimilarityTable σ-buckets needed for discrimination (not absolute threshold) https://claude.ai/code/session_01M3at4EuHVvQ8S95mSnKgtK
bgz7_to_batch(): Base17 fingerprints → Arrow FixedSizeList[i16,17] compute_heel(): column-wise bundle of all rows → HEEL vector hydrate_bgz7(): read bgz7 file → RecordBatch (ready for Dataset::write) 4 tests passing. Schema: tensor_name, row_idx, base17[17], palette_s/p/o. HEEL test confirms non-zero for asymmetric data. https://claude.ai/code/session_01M3at4EuHVvQ8S95mSnKgtK
|
You have reached your Codex usage limits for code reviews. You can see your limits in the Codex usage dashboard. |
AdaWorldAPI
pushed a commit
that referenced
this pull request
Sep 5, 2026
…epo reachability law Operator correction: a zero-local-callsite result is not a production verdict for a deliberately cross-repo substrate (the error lance-graph-java #76 corrected for WideFieldMask, repeated one layer up). Struck: - 'try_advance_phase has no production entry point' — bardioc substrate-b is a binary over MailboxSoA<32> gating every move on the contract's KanbanColumn::can_transition_to; KanbanShaderSink tags by phase - 'ogar-loco has one live consumer' — blockly-rs is a first-class consumer - 'ogar-r2il is probe-only' — it is the R2IL->loco bridge over r2sleigh's live IR; lance-graph-java lineage consumes R2IL via ruff_r2il RBAC zero-caller verdict rescoped to the nine scanned repos. Ruling A is sharpened: DataFusion policy is grace-period archaeology beside an already-production successor. Law recorded in plan §2 and the epiphany. Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01DCfrD5y19cvFc4AoyydXYv
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
2 participants
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.
No description provided.