Hugging Face's logo
Josh Bolding's picture

Josh Bolding PRO

BoldingBuilds
6 7
zamrawisami's profile picture TheDcoder's profile picture UruTau01's profile picture
·

AI & ML interests

Independent builder working on local AI, reasoning models, and practical agents. I test models, experiment with small weight edits, and share results, GGUFs, and evaluation tools.

Recent Activity

posted an update about 8 hours ago
I released a one-row weight edit for Qwen3.8 27B and Flash-Next to address a frustrating failure: using the entire output budget thinking, then returning no final answer. The edit changes only the output-layer row that scores </think> and is packaged into ordinary GGUF files. On 200 MATH-500 problems at a 4,096-token output limit: • 27B: 31 empty answers → 0 • Flash-Next: 29 → 0 For comparison, llama.cpp's --reasoning-budget 2048 also eliminated blanks, with similar accuracy. The aim here is to put the control in the model file. The report includes correctness scores, regressions, compatibility checks, evaluation limitations, and links to both models. Report and downloads: https://huggingface.co/spaces/BoldingBuilds/helping-qwen-finish-thinking Built on Qwen's models and Unsloth's GGUF conversions. If you've worked with local reasoning models, I'd like to hear what I got wrong.
published a Space about 8 hours ago
BoldingBuilds/helping-qwen-finish-thinking
published a model about 8 hours ago
BoldingBuilds/Qwen3.8-Flash-Next-Reasoning-Termination-Fix-GGUF
View all activity

Organizations

Flatline's profile picture