feat(model-ports): add smollm3_3b, nemotron_mini_4b, apertus_8b, glm4_9b - #206
Open
DarthCeltic wants to merge 3 commits into
Open
feat(model-ports): add smollm3_3b, nemotron_mini_4b, apertus_8b, glm4_9b#206DarthCeltic wants to merge 3 commits into
DarthCeltic wants to merge 3 commits into
Conversation
Full compliant shape from the start: model-ports claim (new standalone root + submissions/model_ports/<model>.json), ordinary framework registration (artifacts.json, benchmarks/<model>.json, benchmark_config.json entry), and real host-CPU perplexity for all 4. Built a plain CPU-only (GGML_ET=OFF) llama-perplexity from the same vendored llama.cpp-et source (the ET-linked build hard-depends on /opt/et/lib/esperanto-fw sysemu firmware not present outside the real hackathon runner) and ran each GGUF against the board-pinned WikiText-2 corpus with the board's own ctx/batch/chunks params. All 4 load and score cleanly: smollm3 12.3653, nemotron 10.5717, apertus 7.8747, glm4 12.2894. All 4 confirmed as genuinely distinct GGUF-reported execution families (arch=smollm3/nemotron/apertus/glm4), none seed, none colliding with each other or prior claims in this campaign. glm4_9b's GGUF was quantized under the source's former THUDM namespace (now zai-org); the pinned revision is re-fetched from the current zai-org repo, not guessed.
github-actions
Bot
added
track: model-ports
DarthCeltic
added a commit
to DarthCeltic/hf-hackathon
that referenced
this pull request
Jul 25, 2026
…4b, apertus_8b, glm4_9b (real measured PPL, see PR aifoundry-org#206)
…, glm4_9b, nemotron_mini_4b, smollm3_3b 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 SmolLM3, Nemotron-mini, Apertus and GLM4 model-port credit, please add committed deterministic oracle evidence and successful full-offload ET-SoC1 runs for each claimed model. Host loading/PPL alone is insufficient. The protected tracker still needs maintainer-owned identities/contracts and approval of the |
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 smollm3_3b, nemotron_mini_4b, apertus_8b, and glm4_9b causal-LM ports to llama.cpp-et, with model-ports claims for each.