openai/gpt-oss-120b · Discussions

Rename README.md to README.md, Hello AI, Browser @"Hello World" from https://helloworlddev.in-India by Narasimha Murthy.

#149 opened 6 days ago by

N-HelloWorld

Reinforcement Learning example

#148 opened 17 days ago by

danielhanchen

So much censorship!

👍 2

#147 opened 21 days ago by

mv2woods

An infinitty max input tokenizer token length

👍 2

1

#146 opened 21 days ago by

kdduha

mlp

#145 opened 21 days ago by

Sin2pi

Wrong Formatting in UI?

#144 opened 24 days ago by

matthkarl

Update README.md

#143 opened 29 days ago by

hallisky

gpt-oss-120b

#141 opened about 1 month ago by

cemfcelebi

Issue with tokenizer_config.json

👍 3

#140 opened about 1 month ago by

LucaF

Failed in vllm inference

#139 opened about 2 months ago by

Mqleet

Update README.md

#137 opened about 2 months ago by

lulavc

gpt-oss 120b AMD GPU output problem

👍 1

#136 opened about 2 months ago by

gfatigati

Update Readme.md add multilingual language tag

#135 opened about 2 months ago by

TahirC

Can gpt-oss support local deployment on V100 GPU?

#134 opened about 2 months ago by

SPGZXB

gpt-oss-120b has high possibility to generate response as part of reasoning

#133 opened about 2 months ago by

tonyaw

AIME eval script does not score correctly some answers

👀 2

#132 opened about 2 months ago by

ggerganov

Is it possible to use fine tuning on this model?

1

#131 opened about 2 months ago by

Jameslxz11

assistantfinal, analysis keyword is contained in the huggingface gpt-oss-120 output. Is this intended?

👍 4

3

#130 opened about 2 months ago by

ml345

123

#129 opened 2 months ago by

petermu

Rename README.md to làm đẹp đoạn code của tôi được không ? tôi sẽ dán vào đây

#128 opened 2 months ago by

tranvanbest

How to deploy gpt oss 120B in Openshift AI platform

👍 1

2

#126 opened 2 months ago by

eselvam

how to run gpt-oss-120b by ollama using multi-gpu

1

#125 opened 2 months ago by

ssfyasuo

Is this demo powered by hugging face?

👍 🤗 1

2

#124 opened 2 months ago by

terobox

Very bad censorship

2

#123 opened 2 months ago by

YesIamKurt

how to exclude file in "original" folder while model download

7

#122 opened 2 months ago by

meetzuber

gpt-oss-120b works with OpenRouter + MCP servers, but not with locally hosted setup via LibreChat

#121 opened 2 months ago by

Byrdi

Create ابو الرشد ٢٠٢٥

#120 opened 2 months ago by

Shrif7roshdi

Update README.md

#119 opened 2 months ago by

Lorriea73

new version miss file,can't startup the model gpt-oss

1

#118 opened 2 months ago by

aidenpan0x

Fine tune 120b at 8 H100s getting cuda OOM error

4

#117 opened 2 months ago by

jinxu88

68.4 on Aider Polyglot with reasoning_effort: high

🔥 2

#116 opened 2 months ago by

Fernanda24

fix missing the `{% generation %}` keyword while using tokenizer.apply_chat_template(...return_assistant_tokens_mask=True)

#112 opened 2 months ago by

lllIIIlIlIk

Two clarifications on gpt-oss-120B hardware (fine-tuning vs inference, MoE VRAM)

#110 opened 2 months ago by

GazJ16

gpt-oss is actually good. even on less common benchmark

🤝 👍 6

2

#109 opened 2 months ago by

groupfairnessllm

Please restart openai/gpt-oss-120b endpoint + confirm logprobs support

2

#107 opened 2 months ago by

Melfarser

Model output with FP16

#106 opened 2 months ago by

AnujQCom

BEST open source 120b level model.. ever

❤️ 2

2

#104 opened 2 months ago by

DOFOFFICIAL

Multimodal support missing

#101 opened 2 months ago by

dashesy

LiveCodeBench evaluation

#100 opened 2 months ago by

wasiuddina

How to reproduce the results on hle(Humanity's Last Exam)?

#95 opened 3 months ago by

wenhanli

ImportError: /lib64/libc.so.6: version `GLIBC_2.32' not found

5

#86 opened 3 months ago by

yueqiren

Why is the performance worse on the 20B than on the 120B

➕ 2

2

#84 opened 3 months ago by

megabob

How to turn off thinking mode

2

#82 opened 3 months ago by

Gierry

gpt-oss120b does not actually support 131072 output tokens due to openai policies embedded limiting ouput

8

#81 opened 3 months ago by

Theodophilus

Run GPT-OSS-120B with just Single A100 (80GB)

2

#80 opened 3 months ago by

ghostplant

Please move metal/ and original/ to their own repos

➕ 2

2

#78 opened 3 months ago by

ehartford

gp-oss-120b — Exceptional Reasoning, Not Yet AGI Scale

❤️ 3

#77 opened 3 months ago by

BertrandCabotIDRIS

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

3

#75 opened 3 months ago by

yousef1727

Hallucinates System-promp

2

#74 opened 3 months ago by

Gradois

Can gpt-oss support local vllm deployment on a100 GPU?

10

#73 opened 3 months ago by

Cola-any