You can deploy this model and start earning money today!

OnAnOrange/
LLaDA-8B-Instruct-s1k-sft

Name: LLaDA-8B-Instruct-s1k-sft
Availability: InStock

GSAI-ML/LLaDA-8B-Instruct

Views

No views yet

LLaDA-8B-Instruct-s1k-sft

LLaDA-8B-Instruct-s1k-sft is a diffusion-based instruct model post-trained from LLaDA-8B-Instruct on simplescaling/s1K, using MDLM (masked diffusion) and trained with the dLLM framework.

Model Overview

LLaDA-8B-Instruct-s1k-sft has the following features:

Method: Masked Diffusion Language Modeling (MDLM);
Framework: dLLM
Base model: LLaDA-8B-Instruct
Dataset (SFT): simplescaling/s1K

For broader training and ablation reporting in the dLLM ecosystem, see the dLLM paper.

Eval notes: Metrics use confidence-threshold decoding (alg: confidence_threshold). The primary table is at confidence_threshold = 0.9; full grids sweep confidence_threshold ∈ {0.6, 0.7, 0.8, 0.9} with max_new_tokens ∈ {256, 512}. TPS not recorded for this checkpoint.

Primary results

Benchmark	max_new_tokens=256 _{Acc %}	max_new_tokens=512 _{Acc %}
GSM8K	82.03	82.79
HumanEval	39.63	47.56
MBPP	34.40	23.00
MATH	N/A	41.24

Threshold sweep

Benchmark	τ=0.6 _{Acc %}	τ=0.7 _{Acc %}	τ=0.8 _{Acc %}	τ=0.9 _{Acc %}
GSM8K	73.46	78.62	80.82	82.03
HumanEval	24.39	31.71	39.02	39.63
MBPP	30.20	32.20	33.80	34.40
MATH	N/A	N/A	N/A	N/A

max_new_tokens=256, columns sweep confidence_threshold ∈ {0.6, 0.7, 0.8, 0.9}

Benchmark	τ=0.6 _{Acc %}	τ=0.7 _{Acc %}	τ=0.8 _{Acc %}	τ=0.9 _{Acc %}
GSM8K	75.28	78.92	81.58	82.79
HumanEval	33.54	38.41	45.12	47.56
MBPP	24.40	24.80	23.60	23.00
MATH	34.28	38.34	40.50	41.24

max_new_tokens=512, columns sweep confidence_threshold ∈ {0.6, 0.7, 0.8, 0.9}

OnAnOrange/LLaDA-8B-Instruct-s1k-sft

LLaDA-8B-Instruct-s1k-sft

Model Overview

Primary results

Threshold sweep

OnAnOrange/
LLaDA-8B-Instruct-s1k-sft