feat(model-ports): add smallthinker_4ba0_6b - #218
Open
DarthCeltic wants to merge 2 commits into
Open
Conversation
github-actions
Bot
added
track: model-ports
Member
|
SmallThinker still needs a real full-offload ET-SoC1 execution and a committed deterministic oracle/expected output with an explicit comparison threshold. Host loading and CPU PPL alone are insufficient. Please also ensure the hosted GGUF is pinned by immutable revision + verified SHA256/size/license. Maintainers will then review/adopt the identity/contract and runner policy. |
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
PowerInfer/SmallThinker-4BA0.6B-Instruct(Apache-2.0, 4B-total/0.6B-active MoE) as a new model-port claim, introducing the SmallThinker execution family — an architecture purpose-built for on-device local deployment.Self-converted GGUF (no pre-made quant existed), hosted on Hugging Face (
darthceltic85/smallthinker-4ba0.6b-gguf) since the 4.55GB file exceeds GitHub's 2GB release-asset limit. Locally verified: arch=smallthinker loads cleanly (32 experts, 4 active/token), clean 1640-node compute graph, real PPL = 14.2763 +/- 2.93 against WikiText-2.Full provenance in
ported_models/smallthinker_4ba0_6b/docs/RECIPE.md.