openai/gpt-oss-120b · Discussions

can i load the local model without internet?

#164 opened 5 months ago by

jcasjcj

Add Artificial Analysis evaluations for gpt-oss-120b

#162 opened 5 months ago by

SeasonalFall84

Please move metal/ and original/ folder in a separate branch

👍 4

2

#160 opened 5 months ago by

mratsim

How many graphics cards are needed to train OSS-120B using GRPO?

1

#158 opened 5 months ago by

wanghongyu1111

gpt-weights

#157 opened 5 months ago by

airawat123

Suggesting an open-weight Gpt-Oss LLM between the 20B and 120B parameters

#156 opened 5 months ago by

rtzurtz

Trouble using GPT-OSS 120B via MCP (repro + logs inside)

🤯🔥 3

#155 opened 5 months ago by

abdelhafidmrh

Small changes in readme for Vllm serve

2

#154 opened 6 months ago by

Navanit-AI

RuntimeError: expected scalar type Float but found BFloat16 during activation capture

#153 opened 6 months ago by

ojas03

An error occurred when generating a response.

#152 opened 6 months ago by

pauls123

Parallel Tool Calling not working in latest commit

👍 1

19

#151 opened 6 months ago by

mirzads

GPT-OSS 120B

#150 opened 6 months ago by

elly99

Reinforcement Learning example

#148 opened 7 months ago by

danielhanchen

So much censorship!

👍 7

1

#147 opened 7 months ago by

mv2woods

An infinitty max input tokenizer token length

👍 2

1

#146 opened 7 months ago by

kdduha

mlp

#145 opened 7 months ago by

Sin2pi

Update README.md

#143 opened 7 months ago by

hallisky

gpt-oss-120b

#141 opened 7 months ago by

cemfcelebi

Issue with tokenizer_config.json

👍 3

#140 opened 8 months ago by

LucaF

Failed in vllm inference

1

#139 opened 8 months ago by

Mqleet

Update README.md

#137 opened 8 months ago by

lulavc

gpt-oss 120b AMD GPU output problem

👍 1

#136 opened 8 months ago by

gfatigati

Update Readme.md add multilingual language tag

#135 opened 8 months ago by

TahirC

Can gpt-oss support local deployment on V100 GPU?

#134 opened 8 months ago by

SPGZXB

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

#133 opened 8 months ago by

tonyaw

AIME eval script does not score correctly some answers

👀 2

#132 opened 8 months ago by

ggerganov

Is it possible to use fine tuning on this model?

1

#131 opened 8 months ago by

Jameslxz11

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

👍 4

4

#130 opened 8 months ago by

ml345

123

#129 opened 8 months ago by

petermu

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

#128 opened 8 months ago by

tranvanbest

How to deploy gpt oss 120B in Openshift AI platform

👍 1

2

#126 opened 8 months ago by

eselvam

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

1

#125 opened 8 months ago by

ssfyasuo

Is this demo powered by hugging face?

👍🤗 1

2

#124 opened 8 months ago by

terobox

Very bad censorship

👍 2

2

#123 opened 8 months ago by

YesIamKurt

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

7

#122 opened 8 months ago by

meetzuber

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

➕ 2

#121 opened 8 months ago by

Byrdi

Create ابو الرشد ٢٠٢٥

#120 opened 8 months ago by

Shrif7roshdi

Update README.md

#119 opened 8 months ago by

Lorriea73

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

1

#118 opened 8 months ago by

aidenpan0x

Fine tune 120b at 8 H100s getting cuda OOM error

👀 1

6

#117 opened 8 months ago by

jinxu88

68.4 on Aider Polyglot with reasoning_effort: high

🔥 2

#116 opened 8 months ago by

Fernanda24

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

#112 opened 8 months ago by

lllIIIlIlIk

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

#110 opened 8 months ago by

GazJ16

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

🤝👍 7

2

#109 opened 8 months ago by

groupfairnessllm

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

2

#107 opened 8 months ago by

Melfarser

Model output with FP16

#106 opened 8 months ago by

AnujQCom

BEST open source 120b level model.. ever

❤️ 2

2

#104 opened 9 months ago by

DOFOFFICIAL

Multimodal support missing

#101 opened 9 months ago by

dashesy

LiveCodeBench evaluation

❤️👀 2

1

#100 opened 9 months ago by

wasiuddina

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

#95 opened 9 months ago by

wenhanli