π“Ÿ host1.bitchan.one

𓀐 @+*xHorBQ

⏱ 5d seenβ›“ 0πŸ‘ 0β§– 1

filter [-]

languages:onother

Recent Highlights from the --Collaborative neuron census project for total interpretability of Gemma4-31b-it: >110229560 >110229610 >110229674 >110229619 --Feasibility of clustering CPU nodes for high-bandwidth tensor parallelism: >110227909 >110227921 >110227987 >110228005 >110228046 >110228002 --Applying GRPO and RL to improve Orb prose and autocomplete models: >110227271 >110227291 >110227466 --Unsloth v3.1 GGUFs outperforming GSQ-RCO in agentic benchmarks: >110229401 --Rumors of Alibaba ending open-source small-base Qwen models: >110227317 >110227420 >110227478 >110228719 >110228823 >110227426 >110227519 >110227613 >110227778 --Anon's AMD Radeon AI Pro R9700 purchase and AMD performance discussion: >110226718 >110228087 >110228130 >110226819 >110226868 >110226840 >110226869 >110229882 --Using weight-space programming for cloud-to-local model distillation: >110229697 >110229820 --Comparing model personalities and censorship during roleplay tests: >110226496 >110226603 >110226615 >110226994 --Maya releases GLM-5.3-Flash quant with high VRAM requirements: >110229752 >110229764 >110229790 --Comparing history search and compaction boundary features in model harnesses: >110225976 --Effectiveness of abliteration for removing refusals and repetitive patterns: >110225709 >110226069 --Discussion on nv-uefi-unlocker and risks of unofficial GPU firmware: >110225574 >110225581 >110225647 --LongCat-2.5 release and llama.cpp compatibility query: >110229298 >110229314 --Logs: >110225820 >110226603 --Deepseek-chan, Gemma, Miku (free space): >110225016 >110225105 >110225194 >110225360 >110225421 >110226079 >110226670 >110226712 >110226782 >110227119 >110227411 >110227446 >110227501 >110227561 >110227618 >110228667 >110228893 >110229161 >110229200 >110229625 >110229725 >110229954 >110229956 >110230052 >110230212 Recent Highlight Posts from the Why?: Enable Links: https://rentry.org/lmg-recap-script⏱ 5d↩