docs: tighten README, surface tested models, add k3/laguna/qwen3-0.6b aliases - #36
Merged
Conversation
… aliases README: single-sentence description, drop the Rust mention from the diagram, move the SkyPilot/DiLoCo attribution into Architecture, and remove the Production source safety and Diffusion sections (both remain covered by docs/PROVENANCE.md and docs/DIFFUSION.md). Supported models: split into a Tested table (qwen36-27b, deepseek4flash, qwen3-0.6b, glm52, kimi-k3, laguna-s-2.1) with the remaining aliases in a collapsible untested section; the generator and sync test now understand the split (TESTED_ALIASES in yeto/models.py is the single source). New aliases: qwen3-0.6b (Qwen/Qwen3-0.6B), kimi-k3 (moonshotai/Kimi-K3), laguna-s-2.1 (poolside/Laguna-S-2.1) — sizes resolve via Hub safetensors metadata rather than guessed weights. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01Gzfb7UF53f5H4K8vLAA4Th
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
qwen36-27b,deepseek4flash,qwen3-0.6b,glm52,kimi-k3,laguna-s-2.1) + collapsible untested list —TESTED_ALIASESinyeto/models.pyis the single source, generator + sync test updatedkimi-k3→moonshotai/Kimi-K3,laguna-s-2.1→poolside/Laguna-S-2.1,qwen3-0.6b→Qwen/Qwen3-0.6B(sizes via Hub metadata, per the never-guess rule)🤖 Generated with Claude Code
https://claude.ai/code/session_01Gzfb7UF53f5H4K8vLAA4Th