feat(model-ports): add phi3_mini, minicpm3_4b, bitnet_2b - #205
Open
DarthCeltic wants to merge 4 commits into
Open
feat(model-ports): add phi3_mini, minicpm3_4b, bitnet_2b#205DarthCeltic wants to merge 4 commits into
DarthCeltic wants to merge 4 commits into
Conversation
Same compliant claim shape as the rest of this campaign. All 3 confirmed as genuinely distinct GGUF-reported execution families: arch=phi3 (distinct from phi2), arch=minicpm3 (distinct from minicpm), arch=bitnet-b1.58 (unique in this campaign -- native ternary-weight model, not a quantization of a higher-precision one). bitnet_2b's GGUF used a raw tensor dtype (i2_s, id 36) the installed `gguf` PyPI package's enum doesn't recognize yet -- worked around with a minimal custom KV-only parser rather than fighting the library version. Its recipe is the most honestly hedged in this campaign: real risk that the ET backend's MUL_MAT doesn't support ternary block matmul at all, genuinely unconfirmed either way, not assumed to work. minicpm3_4b similarly flags its MLA-style compressed attention as unconfirmed against ET sysemu, not just a formality caveat. Verification bar is GGUF-metadata-level for all 3 (file hash + architecture confirmed), not full ET sysemu load, consistent with the rest of this batch.
github-actions
Bot
added
track: model-ports
…b claim Backfills PR Checklist item 2 (framework registration) for phi3_mini and minicpm3_4b, and replaces their "GGUF-metadata-level only" verification with real host reference: built a plain CPU-only (GGML_ET=OFF) llama-perplexity from the same vendored source, ran it against the board-pinned WikiText-2 corpus. Both load and score cleanly: phi3 9.4850, minicpm3 11.8752 (confirms MLA-style compressed attention works on ggml-cpu). bitnet_2b's claim is withdrawn -- confirmed, not speculative: the model fails to even load with this repo's vendored llama.cpp-et. Tensor type id 36 collides between BitNet's native ternary format and a now-removed legacy type (TYPE_IQ4_NL_4_4) this fork's version still uses that id for. Recipe rewritten as a documented negative result, same category as this campaign's RWKV-6/PLaMo-2 findings -- a real incompatibility, not a hedge.
…b, phi3_mini Each claim's benchmark_config must exactly match the model's "config" pointer in .github/ci/benchmark_config.json per effective_model_config() in model_port_claim.py, not the top-level benchmark_config.json path itself. Fixes a mismatch that would fail eligibility validation.
Member
|
For Phi3-mini and MiniCPM3 credit, please add committed deterministic oracle evidence and successful full-offload ET-SoC1 runs. BitNet currently has only a recipe and lacks a registered benchmark/standalone claim; add those if it is intended to count. Phi3 overlaps #204, so only the first final qualifying merge can receive that family credit. |
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.
Adds phi3_mini and minicpm3_4b model-ports claims and framework registration. bitnet_2b recipe included as a documented negative result (fails to load -- vendored llama.cpp-et tensor-type enum conflict); no claim filed for it.