feat(model-ports): add falcon_h1_1_5b - #208
Open
DarthCeltic wants to merge 3 commits into
Open
Conversation
…no claim) falcon_h1_1_5b: full compliant shape (claim + framework registration + real host-CPU perplexity). Built a plain CPU-only (GGML_ET=OFF) llama-perplexity from the vendored source, ran against the board-pinned WikiText-2 corpus. Loads and scores cleanly (PPL 11.6708), allocating BOTH a standard transformer KV cache AND a recurrent SSM state cache simultaneously -- direct confirmation of TII's hybrid attention+Mamba architecture, distinct from the plain falcon arch ported earlier. Second data point (after mamba_1_4b) on whether ET-SoC1 supports SSM_CONV/SSM_SCAN. persimmon_8b: confirmed negative result, no claim filed. GGUF parses fine (metadata dump succeeds) but model construction fails with "unknown model architecture: 'persimmon'" -- this repo's vendored llama.cpp-et fork has no persimmon architecture support compiled in at all. Unambiguous, reproducible, different failure mode from both bitnet_2b (quant-type collision) and flan_t5_base (tooling gap).
github-actions
Bot
added
track: model-ports
DarthCeltic
added a commit
to DarthCeltic/hf-hackathon
that referenced
this pull request
Jul 25, 2026
…1_5b 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 Falcon-H1 model-port credit, please add a committed deterministic oracle and successful full-offload ET-SoC1 run. Persimmon currently has only a recipe and no registered benchmark/claim; add those if it is intended to count. Host loading/PPL alone is insufficient. |
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 falcon_h1_1_5b causal-LM port to llama.cpp-et, with a model-ports claim. persimmon_8b recipe included as a documented negative result (this repo's vendored llama.cpp-et has no persimmon architecture support at all); no claim filed for it.