openai/gpt-oss-20b · Discussions

Genuine User Reviews and Questions on Repo openai/gpt-oss-20b

#161 opened 8 days ago by

DeepNLP

Tool Calling in Chat Template

#160 opened 10 days ago by

aashkaaa

Update README.md

#159 opened 14 days ago by

sufian7755

Miss

#158 opened 14 days ago by

liuhuangsu1990

deploying finetuned model on triton using vllm backend

#157 opened 18 days ago by

Prabhjot410

gpt

#156 opened 18 days ago by

Alice1288

Missing torchvision==0.24.0.dev20250804+cu128 required by vllm+gptoss installation

➕ 1

1

#155 opened 22 days ago by

BanderaTar

Request: DOI

#154 opened 25 days ago by

SuurajK

Reinforcement Learning example

#153 opened 25 days ago by

danielhanchen

is the model support TGI?

#152 opened about 1 month ago by

AminSharif

Tokenizer vocab size doesn't match model vocab size

👍 1

1

#151 opened about 1 month ago by

frreiss

Request: DOI

#150 opened about 1 month ago by

Moidan4

Cannot retrieve streamed reasoning output from openai/gpt-oss-20b with vLLM and LangChain

1

#149 opened about 1 month ago by

JSchaffauser

Database Intelligent Query System Implemented Using the GPT-OSS-20B Model

#148 opened about 2 months ago by

allengjj

Inference engines that actually use OSS to full extent? (responses, harmony)

#147 opened about 2 months ago by

Howaboua

Create requirements.txt

#146 opened about 2 months ago by

skminhajuddin20

Create app.py

#145 opened about 2 months ago by

skminhajuddin20

KeyError: 'model.layers.17.mlp.experts.gate_up_proj'

2

#144 opened about 2 months ago by

pnaik24

Update Readme.md add multilingual language tag

#143 opened about 2 months ago by

TahirC

"Karen from HR has called... she wants her LLM back."

👀 2

#142 opened 2 months ago by

builderofworlds

Speculative Decoders?

🔥 4

#141 opened 2 months ago by

Ano-Nimus

Privacy moment.

2

#138 opened 2 months ago by

Maria99934

test

➕ 🤗 5

1

#137 opened 2 months ago by

vcn44

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

5

#136 opened 2 months ago by

yjban

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

#135 opened 2 months ago by

findhao

myllm

#134 opened 2 months ago by

arvind

zzsm

#132 opened 3 months ago by

lilisa2099

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

2

#131 opened 3 months ago by

DeepakParameswar

1111

1

#130 opened 3 months ago by

cher0511

Update README.md

#129 opened 3 months ago by

cher0511

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

🤯 👀 3

2

#127 opened 3 months ago by

Yvaine

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

#126 opened 3 months ago by

daohanlu

Upload medical_diagnosis_manual-1.pdf

1

#125 opened 3 months ago by

Lorriea73

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

3

#124 opened 3 months ago by

saiadityavzure

20B Parameters vs ChatGPT 4

13

#123 opened 3 months ago by

Maria99934

68.4 on Aider Polyglot with reasoning_effort: high

👍 1

5

#122 opened 3 months ago by

Fernanda24

MXFP4 utilization over NVFP4

👍 2

1

#121 opened 3 months ago by

pprovins

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

👍 2

#120 opened 3 months ago by

Brayanb

The output of `gpt_oss.generate` is meaningless

#119 opened 3 months ago by

Yi30

running gpt-oss-20B on Intel Arc iGPU

1

#117 opened 3 months ago by

quyendo00

Update chat_template.jinja to correctly parse types nested in arrays

#116 opened 3 months ago by

daohanlu

Model removed from openrouter.ai

#115 opened 3 months ago by

shhhman

Performance gains on low-end hardware

3

#114 opened 3 months ago by

dsprag

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

1

#112 opened 3 months ago by

xiaotianyu2025

Unable to Structured output

8

#111 opened 3 months ago by

Arnab07

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

3

#110 opened 3 months ago by

Biiigstone

With openai harmony response, I cannot generate response.

1

#108 opened 3 months ago by

Noah0627

safe_serialization

#105 opened 3 months ago by

cuongdk253

NVIDIA L40S GPU's for MXFP4 quantization

2

#100 opened 3 months ago by

lordim

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

2

#99 opened 3 months ago by

sumeetm