openai/gpt-oss-20b · Discussions

#78 opened about 2 months ago by

MarinaraSpaghetti

behavior between GptOssExperts and Mxfp4GptOssExperts

#77 opened about 2 months ago by

DaleMeng

'accelerate' missing in the model card.

#76 opened about 2 months ago by

Ina-Developer

Qwen3 beat gpt-oss with just 0.6B with good quality enough to be usable

👀 2

#75 opened about 2 months ago by

yousef1727

triton_kernels and multiprocessing

#74 opened about 2 months ago by

piotrm0

Thanks for the great model

👍 👀 4

#73 opened about 2 months ago by

deniiiiiij

Running gpt-oss Without FlashAttention 3 – Any Alternatives to Ollama?

#72 opened about 2 months ago by

shinho0902

getting curernt Date template issue with OLLAMA_ORIGINS="chrome-extension://*" OLLAMA_DEBUG=1 ollama serve

#71 opened about 2 months ago by

lokesher

how to ignore the quantization

❤️ 👍 4

#70 opened about 2 months ago by

zzbysd

Is there no usable PyTorch for Python 3.12?

#69 opened about 2 months ago by

xiaotianyu2025

This is by far the worst model out there... Won't be using this. 🚮🗑️

🤯 ➕ 7

#67 opened about 2 months ago by

UniversalLove333

question: setting reasoning effort

5

#66 opened about 2 months ago by

TheBigBlockPC

🚀 Best Practices for Evaluating GPT-OSS Models: Speed & Benchmark Testing Guide

👍 🔥 10

#64 opened about 2 months ago by

Yunxz

information how to get it working on a 3090

👍 4

11

#63 opened about 2 months ago by

TheBigBlockPC

It seems to be censored a bit too much.

🤯 👍 10

7

#62 opened about 2 months ago by

petwoe

MXFP4 only runs on h100 or b100 or later versions,

😔 2

12

#61 opened about 2 months ago by

kishan51

AIME 25 Accuracy Discrepancy for GPT-OSS-20B (Reasoning Effort=High)

#58 opened about 2 months ago by

jiayi37u

🔥🔥🔥中文测评视频

#56 opened about 2 months ago by

leo009

Report

🤝 1

#55 opened about 2 months ago by

Mks1837

Thinking but no solution?

#54 opened about 2 months ago by

ZeroWw

transformers + openai_gpt_oss on modal to run 👌🏻

👍 2

#51 opened about 2 months ago by

weege007

self_attn.k_proj.bias are all 0 for all layers

#50 opened about 2 months ago by

DaleMeng

no able to deploy using vLLM on A10G

#49 opened about 2 months ago by

abhisskk

so much censorship

👍 24

6

#48 opened about 2 months ago by

Utochi

How to set reasoning effort in the shown example?

👍 3

12

#47 opened about 2 months ago by

TianheWu

When asked for a story with a gay dog character having a crush on a cat, the model only tells stories with straight characters, and cannot seem to correct itself.

😔 4

#46 opened about 2 months ago by

CyroPaws

It's incredibly easy to get the model to spread false information defending conversion therapy for transgender people.

❤️ 👀 5

#45 opened about 2 months ago by

CyroPaws

GGUFs of This model, tested, and conforms to tensor sizes - IQ4NL, Q5_1, MXFP4_MOE.gguf

#44 opened about 2 months ago by

DavidAU

🚀[Fine-tuning] LoRA fine-tuning openai/gpt-oss-20b 👋

👀 👍 7

#43 opened about 2 months ago by

study-hjt

Can't Run The Demo FT Code? "Cannot copy out of meta tensor"

#42 opened about 2 months ago by

alentzy

RTX 5000 can't not use this model...

👍 2

#41 opened about 2 months ago by

arvis

3090s?

#39 opened about 2 months ago by

xiaotianyu2025

Kaggle error

23

#38 opened about 2 months ago by

legolasyiu

Deploy gpt-oss models in your own AWS account using vLLM and Tensorfuse

🔥 3

#37 opened about 2 months ago by

agam30

If you have issues running gpt-oss-*20b in google's colab notebooks, this might be useful to know

❤️ 6

17

#35 opened about 2 months ago by

ahmedsaoudi

Open AI open source models not able to run ...

😔 3

#34 opened about 2 months ago by

pskmattegunta

Finetune GPT-OSS models 🔥

🔥 11

#33 opened about 2 months ago by

hiyouga

Float16 ?

👍 1

#32 opened about 2 months ago by

horbane

ONNX Format

7

#30 opened about 2 months ago by

Aguazzz

REASONING SETTING GUIDE 📚

😔 👍 4

25

#28 opened about 2 months ago by

xbruce22

Is CPU offloading possible?

➕ 3

#26 opened about 2 months ago by

SpaghettiM

Reasoning settings in Ollama?

➕ 1

#25 opened about 2 months ago by

Lynrayy

Scored 67.86 🔥 on MMLU Pro single shot benchmark

#24 opened about 2 months ago by

xbruce22

how to make determinstic output?

#23 opened about 2 months ago by

junma

Unusual Training metrics

#22 opened about 2 months ago by

shadowlilac

Running on apple silicon giving quantization error

❤️ ➕ 10

11

#21 opened about 2 months ago by

aditagar

Content Policy Obsessed Model at Expense of Intelligence and Context Following

👍 19

31

#20 opened about 2 months ago by

jalder1989

memory allocation exceeded error

🚀 4