grug-35b-v2

grug-35b-v2

old grug-35b repeat words until cave fall down. grug bury him, study bones, rebuild WHOLE brother from zero with the grug-27b pipeline. v2 different animal: complete retrain, repetition gates, stripped-history training, deep grug reasoning. then v2.1 round on top (long-hunt + deep-think data).

• base: Ornith-1.0-35B (mixture-of-experts) - template keep think in every turn, grug respect that
• method: LoRA on attention + DeltaNet + shared paths (expert FFN and router untouched - grug no poke router), merged bf16, then v2.1 continued round with long agent sessions + deep-think data
• grug think in dense grug-speak inside <think>, answer normal english

number. same harness as grug-27b, all open

MATH-500 special: never touch any grug data pipeline. base got 3x bigger budget and still 32% of base run hit token wall. grug beat base with 33x fewer token. no benchmaxx, just no fat.

grug honest corner: HumanEval -1.8, MBPP -4 vs base. and tool-call PRESENCE 82.4% vs base 98.5 (grug sometimes answer in words when tool call better; when grug DO call, args 100% valid and right tool way more often, 79.4 vs 52.9). old v1 repetition sickness: extinct. zero loops all gauntlets.

v2 -> v2.1 changelog

v2.1 add: stuck-loop escape, sacred no-tool final summary, fresh think every turn, deep-think on hard problems. same medicine as grug-27b v2.1.

how run

vllm serve ProCreations/grug-35b-v2 --max-model-len 32768 --reasoning-parser deepseek_r1

gguf rocks (+ vision mmproj): grug-35b-v2-gguf. sampling temp 0.6-1.0, top_p 0.95, top_k 20. MTP not included (mtp_num_hidden_layers=0); vision tower untouched from base.

grug family

grug-v2-9b | grug-27b | grug-27b-qat-q4-gguf | brain food: v2 data + v2.1 data

grug made by ProCreations. base brain by DeepReinforce.