openai/gpt-oss-20b · Discussions

#138 opened 5 days ago by

Maria99934

test

➕ 🤗 4

#137 opened 7 days ago by

vcn44

Unable to load gpt-oss-20b on dual L40 (48GB) GPUs with vLLM

#136 opened 8 days ago by

yjban

int32 overflow detected for operation add in `_keyed_add` kernel under TRITON_DEBUG=1

#135 opened 9 days ago by

findhao

myllm

#134 opened 10 days ago by

arvind

zzsm

#132 opened 12 days ago by

lilisa2099

Getting Error when calling openai/gpt-oss-20b from HuggingFaceEndpoint

#131 opened 12 days ago by

DeepakParameswar

1111

#130 opened 12 days ago by

cher0511

Update README.md

#129 opened 12 days ago by

cher0511

My friend and I asked the exact same question but why was his approved but mine refused?

🤯 👀 2

#127 opened 12 days ago by

Yvaine

Wrap assistant messages inside "{% generation %}" markers in chat_template.jinja

#126 opened 13 days ago by

daohanlu

Upload medical_diagnosis_manual-1.pdf

#125 opened 13 days ago by

Lorriea73

Not able to deploy gpt-oss-20b model in A100s

#124 opened 13 days ago by

saiadityavzure

20B Parameters vs ChatGPT 4

13

#123 opened 13 days ago by

Maria99934

68.4 on Aider Polyglot with reasoning_effort: high

👍 1

#122 opened 13 days ago by

Fernanda24

MXFP4 utilization over NVFP4

👍 1

#121 opened 14 days ago by

pprovins

gpt-oss-20b Nvdidia A10G error deploy Attention Sinks

👍 2

#120 opened 14 days ago by

Brayanb

The output of `gpt_oss.generate` is meaningless

#119 opened 14 days ago by

Yi30

running gpt-oss-20B on Intel Arc iGPU

#117 opened 14 days ago by

quyendo00

Update chat_template.jinja to correctly parse types nested in arrays

#116 opened 14 days ago by

daohanlu

Model removed from openrouter.ai

#115 opened 15 days ago by

shhhman

Performance gains on low-end hardware

#114 opened 16 days ago by

dsprag

Is it mandatory to install flash-attention for GPT-OSS?

#112 opened 16 days ago by

xiaotianyu2025

Unable to Structured output

#111 opened 16 days ago by

Arnab07

Running gpt-oss-20b on an RTX 4070 Ti (12GB) using Transformers

#110 opened 16 days ago by

Biiigstone

With openai harmony response, I cannot generate response.

#108 opened 16 days ago by

Noah0627

safe_serialization

#105 opened 17 days ago by

cuongdk253

NVIDIA L40S GPU's for MXFP4 quantization

#100 opened 17 days ago by

lordim

CUDA out of memory issues when running gptoss model on colab T4

#99 opened 18 days ago by

sumeetm

model quality issues

#92 opened 19 days ago by

TheBigBlockPC

The Abliterated version is the version we deserved.

😔 1

#91 opened 19 days ago by

Koitenshin

The censorship here is just... amazing.

👀 👍 6

#90 opened 19 days ago by

smokeofc

Does transformers utilize PyTorch SDPA's flash_attention for openai/gpt-oss-20b?

#89 opened 19 days ago by

NooBaymax

Quick Results: Testing Multilingual Capabilities via Code Generation from Ukrainian Competitive Programming Tasks

🚀 4

#87 opened 19 days ago by

anon-researcher-ua

How to turn off thinking mode

👍 🔥 6

#86 opened 19 days ago by

Gierry

I haven't seen a more useful model than this one.

#85 opened 19 days ago by

Maria99934

How to run it on macOS

❤️ 1

7

#84 opened 20 days ago by

kopyl

There is no spark.. only darkness

#83 opened 20 days ago by

JFE

tool calling not working as expected?

👍 2

9

#80 opened 20 days ago by

Spider-Jerusalem

SVG problem

#79 opened 20 days ago by

Alkohole

Honest Review of the Model

😎 👍 50

#78 opened 20 days ago by

MarinaraSpaghetti

behavior between GptOssExperts and Mxfp4GptOssExperts

#77 opened 20 days ago by

DaleMeng

'accelerate' missing in the model card.

#76 opened 20 days ago by

Ina-Developer

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

👀 2

#75 opened 20 days ago by

yousef1727

triton_kernels and multiprocessing

#74 opened 20 days ago by

piotrm0

Thanks for the great model

👍 👀 4

#73 opened 20 days ago by

deniiiiiij

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

#72 opened 20 days ago by

shinho0902

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

#71 opened 20 days ago by

lokesher

how to ignore the quantization

❤️ 👍 4

#70 opened 20 days ago by

zzbysd

Is there no usable PyTorch for Python 3.12?