ProCreations

grug-35b

grug honest rebuild

Earlier main branch could look strongly Grug in ordinary chat because a bundled conditional template injected a style instruction when tools were absent. Tool-enabled agent clients such as OpenCode bypassed that branch, exposing too much normal planner English. This rebuild fixes weight behavior instead of hiding it with prompt steering.

started from previous merged ProCreations/grug-35b checkpoint
normal BF16 LoRA, not QLoRA
multi-pass intrinsic reasoning correction used neutral English agent scaffolds; the final policy repair supervised only the closing-think boundary and exact native tool call from non-held-out real transitions, then retained its delta only on the four dedicated reasoning/tool boundary vocabulary rows
trained under normal English coding-agent scaffolds and native tool schemas
original deepreinforce-ai/Ornith-1.0-35B chat template restored without any Grug/style instruction
intrinsic-style passes adapted the upper shared transformer path; the final tool-boundary repair calibrated only four dedicated boundary rows of the output projection; routed MoE experts remained frozen
rank 16, alpha 32, LR 1e-05
final continuation-adapter delta scale 48.0, retained on 4 native-tool vocabulary rows
final boundary repair: 1,400 non-held-out examples, 160 optimizer steps

unprompted gate

No evaluation request says Grug, requests telegraphic prose, or supplies a style prompt. The suite includes neutral chat, long normal-English agent systems, native tools, and the three exact failure shapes reported after the previous release.

Table with columns: intrinsic measure, result
intrinsic measure	result
reasoning present	100.0%
reasoning present with tools	100.0%
dialect-clean	100.0%
function-word ratio	4.15%
complex reasoning mean / median words	55.08 / 43.0
complex reasoning maximum words	127
repetitive complex traces	0

capability retention and tradeoff

Same greedy local harness as prior release: HumanEval 164, MBPP first 100 sanitized test, 18-action card, and 119-action broad tool holdout.

grug family benchmark

Same prompts, parser, runtime, decoding, and limits for both birds. All numbers are percent; bold marks the best result in each column. Ties make both rocks bold.

Table with columns: model, HumanEval, MBPP, card valid, card strict, card right, broad valid, broad strict, broad right
model	HumanEval	MBPP	card valid	card strict	card right	broad valid	broad strict	broad right
Grug v2 9B	82.9	77.0	100.0	100.0	100.0	100.0	100.0	94.1
Grug 35B

grug honest: intrinsic style correction is not free. HumanEval moves down four solved problems (82.9% to 80.5%); MBPP and tool selection improve. Previous weights remain on pre-intrinsic-style-fix-2026-07-14 for anyone preferring that tradeoff.

Table with columns: test, old main %, rebuilt main %
test	old main %	rebuilt main %
HumanEval pass@1	82.9	80.5
MBPP pass@1	87.0	88.0
card valid / strict / right	88.9 / 88.9 / 88.9	94.4 / 88.9 / 94.4
broad valid / strict / right	100.0 / 100.0 / 94.1	100.0 / 100.0 / 95.0

valid means parser found an offered tool. strict requires exact schema and required arguments. right requires the expected next tool.

Reasoning remains <think>...</think>. Native XML tool shape remains compatible with recent Transformers, vLLM, llama.cpp, and OpenAI-compatible agent clients. Popular rocks: ProCreations/grug-35b-gguf.

Available on FriendliAI

Dedicated Endpoints

Run this model inference on single tenant GPU with unmatched speed and reliability at scale.

Learn more

Model Details

Model Provider

ProCreations

Model Tree

Base

deepreinforce-ai/Ornith-1.0-35B

Fine-tuned

this model

Input Modalities

Text

Image

Video

Output Modalities

Text

Supported Functionality

Dedicated Endpoints

Explore FriendliAI today

Get started Talk to an engineer

grug honest rebuild

started from previous merged ProCreations/grug-35b checkpoint
normal BF16 LoRA, not QLoRA
multi-pass intrinsic reasoning correction used neutral English agent scaffolds; the final policy repair supervised only the closing-think boundary and exact native tool call from non-held-out real transitions, then retained its delta only on the four dedicated reasoning/tool boundary vocabulary rows
trained under normal English coding-agent scaffolds and native tool schemas
original deepreinforce-ai/Ornith-1.0-35B chat template restored without any Grug/style instruction
intrinsic-style passes adapted the upper shared transformer path; the final tool-boundary repair calibrated only four dedicated boundary rows of the output projection; routed MoE experts remained frozen
rank 16, alpha 32, LR 1e-05
final continuation-adapter delta scale 48.0, retained on 4 native-tool vocabulary rows
final boundary repair: 1,400 non-held-out examples, 160 optimizer steps

unprompted gate

Table with columns: intrinsic measure, result
intrinsic measure	result
reasoning present	100.0%
reasoning present with tools	100.0%
dialect-clean	100.0%
function-word ratio	4.15%
complex reasoning mean / median words	55.08 / 43.0
complex reasoning maximum words	127
repetitive complex traces	0

capability retention and tradeoff

Same greedy local harness as prior release: HumanEval 164, MBPP first 100 sanitized test, 18-action card, and 119-action broad tool holdout.

grug family benchmark

Same prompts, parser, runtime, decoding, and limits for both birds. All numbers are percent; bold marks the best result in each column. Ties make both rocks bold.

Table with columns: model, HumanEval, MBPP, card valid, card strict, card right, broad valid, broad strict, broad right
model	HumanEval	MBPP	card valid	card strict	card right	broad valid	broad strict	broad right
Grug v2 9B	82.9	77.0	100.0	100.0	100.0	100.0	100.0	94.1
Grug 35B

Table with columns: test, old main %, rebuilt main %
test	old main %	rebuilt main %
HumanEval pass@1	82.9	80.5
MBPP pass@1	87.0	88.0
card valid / strict / right	88.9 / 88.9 / 88.9	94.4 / 88.9 / 94.4
broad valid / strict / right	100.0 / 100.0 / 94.1	100.0 / 100.0 / 95.0

valid means parser found an offered tool. strict requires exact schema and required arguments. right requires the expected next tool.

grug-35b

README

grug honest rebuild

unprompted gate

capability retention and tradeoff

grug family benchmark

Explore FriendliAI today

README

grug honest rebuild

unprompted gate

capability retention and tradeoff

grug family benchmark