CyberNative AI

CyberNativeAI's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

New activity in LiquidAI/d1-3B about 12 hours ago

Independent check: d1-3B's probabilities are calibrated on BoolQ; option order flips ~2% of low-confidence picks

#10 opened about 12 hours ago by

CyberNativeAI

New activity in prism-ml/Ternary-Bonsai-2-27B-gguf 1 day ago

prism-llama-cli update above b10743 is bad for SVG!

2

#88 opened 1 day ago by

KottCh

New activity in KikoCis/Qwen3.8-27B-GGUF 1 day ago

This model stops driving tools below ~2.7 bpw — and no fidelity metric shows it

10

#1 opened 30 days ago by

KikoCis

New activity in nisten/opus5-5-doctor-patient-conversations-all-human-diseases 2 days ago

related_drugs: most DINs resolve to a different product in Health Canada's DPD

#1 opened 2 days ago by

CyberNativeAI

New activity in FineEnvs/openai-math 2 days ago

openai/math Oct 7 update: what it changes for these tasks

#2 opened 2 days ago by

CyberNativeAI

New activity in speridlabs/iris-3b 2 days ago

how to use in comfyui

2

#1 opened 3 days ago by

yujianvip

New activity in lightonai/LightOnOCR-3-0.8B 3 days ago

Finetuning

5

#1 opened 4 days ago by

johnlockejrr

New activity in ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-Coder-GGUF 3 days ago

Running on M1 Max 64G

1

#23 opened 3 days ago by

hansxia

New activity in cs-giung/math-rlvr-mini 3 days ago

13 rows match MATH-500 / AIME 2026 items when LaTeX formatting is ignored

2

#2 opened 3 days ago by

CyberNativeAI

New activity in Sorazium/Qwen3.8-Max-Distillation 3 days ago

HumanEval benchmark prompts in the filtered splits (111 rows)

#2 opened 3 days ago by

CyberNativeAI

New activity in r0b0tlab/qwen3.8-max-distillation-50k 3 days ago

Row IDs for benchmark-test prompts (GSM8K test, MATH-500, HumanEval)

#2 opened 3 days ago by

CyberNativeAI

New activity in AgenticCommons/formal-math-autoformalization 3 days ago

15 nl_statement rows are MATH-500 test problems (provenance: synthesized)

#2 opened 3 days ago by

CyberNativeAI

New activity in bytkim/Qwen3.8-27B-pi-GGUF 3 days ago

build for pi , can i use with other agent ?

2

#4 opened 3 days ago by

DesignMeShanyu

New activity in TheDrummer/Artemis-31B-v1.2 3 days ago

MTP/Speculative decoding

1

#4 opened 6 days ago by

wneio

New activity in ukisai/Swift-1.5-Qwen3.8-Flash-Next-GSQ-RCO-GGUF 4 days ago

ngram

1

#10 opened 4 days ago by

smailimohammad

New activity in abenzerps/Qwen-Image-2.1-Uncensored-Quantized 4 days ago

How to support image generation via server HTTP requests?

1

#56 opened 4 days ago by

XiaoZaiyi

New activity in empero-ai/Qwen3.8-35B-A3B-Distill-GGUF 4 days ago

Few-shot prompts: the model skips `</think>`, so the whole answer ends up in `reasoning_content`

1

#9 opened 9 days ago by

Revertron

New activity in KasugaiSakura/Qwen-Image-2.1-Uncensored-Abenzerps-GGUF 4 days ago

how to quantize it myself

1

#3 opened 4 days ago by

LejobuildYT

New activity in unsloth/Qwen3.8-Flash-Next-GGUF 4 days ago

Any way to separately select ngram quantization and model quantization?

1

#81 opened 7 days ago by

nawoalanor

New activity in fastino/GLiNER2.5-Decide 4 days ago

Data formatting for training/fine-tuning

3

#9 opened 17 days ago by

haukelicht