openai/gpt-oss-20b · Discussions

#64 opened 15 days ago by

Yunxz

information how to get it working on a 3090

👍 4

#63 opened 15 days ago by

TheBigBlockPC

It seems to be censored a bit too much.

🤯 👍 10

#62 opened 15 days ago by

petwoe

MXFP4 only runs on h100 or b100 or later versions,

😔 2

#61 opened 15 days ago by

kishan51

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

#58 opened 15 days ago by

jiayi37u

🔥🔥🔥中文测评视频

#56 opened 15 days ago by

leo009

Report

🤝 1

#55 opened 15 days ago by

Mks1837

Thinking but no solution?

#54 opened 15 days ago by

ZeroWw

transformers + openai_gpt_oss on modal to run 👌🏻

👍 2

#51 opened 15 days ago by

weege007

self_attn.k_proj.bias are all 0 for all layers

#50 opened 15 days ago by

DaleMeng

no able to deploy using vLLM on A10G

#49 opened 15 days ago by

abhisskk

so much censorship

👍 24

#48 opened 15 days ago by

Utochi

How to set reasoning effort in the shown example?

👍 2

10

#47 opened 15 days 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 15 days ago by

CyroPaws

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

🚀 👀 5

4

#45 opened 15 days ago by

CyroPaws

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

#44 opened 15 days ago by

DavidAU

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

👀 👍 5

#43 opened 15 days ago by

study-hjt

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

#42 opened 15 days ago by

alentzy

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

👍 2

#41 opened 15 days ago by

arvis

3090s?

#39 opened 15 days ago by

xiaotianyu2025

Kaggle error

23

#38 opened 15 days ago by

legolasyiu

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

🔥 3

#37 opened 15 days ago by

agam30

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

❤️ 6

16

#35 opened 15 days ago by

ahmedsaoudi

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

😔 3

#34 opened 15 days ago by

pskmattegunta

Finetune GPT-OSS models 🔥

🔥 11

4

#33 opened 15 days ago by

hiyouga

Float16 ?

👍 1

#32 opened 15 days ago by

horbane

ONNX Format

5

#30 opened 15 days ago by

Aguazzz

REASONING SETTING GUIDE 📚

😔 👍 3

25

#28 opened 15 days ago by

xbruce22

Is CPU offloading possible?

➕ 2

#26 opened 15 days ago by

SpaghettiM

Reasoning settings in Ollama?

➕ 1

#25 opened 15 days ago by

Lynrayy

Scored 67.86 🔥 on MMLU Pro single shot benchmark

#24 opened 15 days ago by

xbruce22

how to make determinstic output?

#23 opened 15 days ago by

junma

Unusual Training metrics

#22 opened 15 days ago by

shadowlilac

Running on apple silicon giving quantization error

❤️ ➕ 9

#21 opened 15 days ago by

aditagar

Content Policy Obsessed Model at Expense of Intelligence and Context Following

👍 18

23

#20 opened 15 days ago by

jalder1989

memory allocation exceeded error

🚀 4

#19 opened 15 days ago by

aditya-shinde

EXO support.

#18 opened 15 days ago by

JohnP1

Gran trabajo. Los amo.

#17 opened 15 days ago by

Chipiri

Promise kept, excellent work. Thank you

🔥 3

#16 opened 15 days ago by

TestregX

This model is unbelievably ignorant.

➕ 👍 40

14

#14 opened 15 days ago by

phil111

so its a bit confusing .. is the model on hugging faces an moe version or a dense version?

#13 opened 15 days ago by

aatri2021

getting error on vllm

👍 3

#12 opened 15 days ago by

maroahma

Reasoning setting examples

➕ 5

#10 opened 15 days ago by

ndurkee

Android?

#9 opened 15 days ago by

TRXJ

It is super great compared to other open source models

🚀 2

#8 opened 15 days ago by

Pamudu

Works Pretty good!

#7 opened 15 days ago by

davvveee

Latest vLLM docker image doesn't yet support gpt-oss

🔥 1

4

#6 opened 15 days ago by

ht7770

Model size 12B

#5 opened 15 days ago by

amine-khelif

OpenAI is finally open.

🤗 👍 12