transformers + openai_gpt_oss on modal to run
#51 opened 5 minutes ago
by
weege007

self_attn.k_proj.bias are all 0 for all layers
#50 opened 25 minutes ago
by
DaleMeng
no able to deploy using vLLM on A10G
2
#49 opened about 1 hour ago
by
abhisskk
so much censorship
#48 opened about 2 hours ago
by
Utochi
How to set reasoning effort in the shown example?
👍
1
2
#47 opened about 2 hours 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.
😔
2
#46 opened about 2 hours ago
by
CyroPaws
It's incredibly easy to get the model to spread false information defending conversion therapy for transgender people.
👀
1
#45 opened about 2 hours ago
by
CyroPaws
GGUFs of This model, tested, and conforms to tensor sizes - IQ4NL, Q5_1, MXFP4_MOE.gguf
#44 opened about 3 hours ago
by
DavidAU

🚀[Fine-tuning] LoRA 微调 openai/gpt-oss-20b 👋
👀
👍
5
#43 opened about 3 hours ago
by
study-hjt

Can't Run The Demo FT Code? "Cannot copy out of meta tensor"
#42 opened about 5 hours ago
by
alentzy
RTX 5000 can't not use this model...
👍
1
1
#41 opened about 6 hours ago
by
arvis
3090s?
3
#39 opened about 8 hours ago
by
xiaotianyu2025

Kaggle error
#38 opened about 8 hours ago
by
legolasyiu
Deploy gpt-oss models in your own AWS account using vLLM and Tensorfuse
🔥
3
1
#37 opened about 10 hours ago
by
agam30

If you have issues running gpt-oss-*20b in google's colab notebooks, this might be useful to know
❤️
4
4
#35 opened about 11 hours ago
by
ahmedsaoudi
Open AI open source models not able to run ...
😔
2
#34 opened about 11 hours ago
by
pskmattegunta
Finetune GPT-OSS models 🔥
🔥
6
#33 opened about 11 hours ago
by
hiyouga

Float16 ?
👍
1
#32 opened about 12 hours ago
by
horbane
ONNX Format
2
#30 opened about 13 hours ago
by
Aguazzz

REASONING SETTING GUIDE 📚
👍
😔
2
23
#28 opened about 13 hours ago
by
xbruce22

Is CPU offloading possible?
➕
2
2
#26 opened about 13 hours ago
by
SpaghettiM
Reasoning settings in Ollama?
➕
1
1
#25 opened about 13 hours ago
by
Lynrayy

Scored 67.86 🔥 on MMLU Pro single shot benchmark
1
#24 opened about 13 hours ago
by
xbruce22

how to make determinstic output?
1
#23 opened about 14 hours ago
by
junma
Unusual Training metrics
1
#22 opened about 14 hours ago
by
shadowlilac

Running on apple silicon giving quantization error
➕
7
3
#21 opened about 14 hours ago
by
aditagar

Content Policy Obsessed Model at Expense of Intelligence and Context Following
👍
12
2
#20 opened about 14 hours ago
by
jalder1989

memory allocation exceeded error
🚀
4
2
#19 opened about 14 hours ago
by
aditya-shinde

EXO support.
#18 opened about 14 hours ago
by
JohnP1

Gran trabajo. Los amo.
#17 opened about 14 hours ago
by
Chipiri
Promise kept, excellent work. Thank you
🔥
2
#16 opened about 14 hours ago
by
TestregX

This model is unbelievably ignorant.
➕
👍
32
3
#14 opened about 15 hours ago
by
phil111
so its a bit confusing .. is the model on hugging faces an moe version or a dense version?
4
#13 opened about 15 hours ago
by
aatri2021
getting error on vllm
👍
2
6
#12 opened about 15 hours ago
by
maroahma

Reasoning setting examples
➕
4
1
#10 opened about 15 hours ago
by
ndurkee
Android?
1
#9 opened about 15 hours ago
by
TRXJ
It is super great compared to other open source models
🚀
2
#8 opened about 15 hours ago
by
Pamudu
Works Pretty good!
1
#7 opened about 16 hours ago
by
davvveee
Latest vLLM docker image doesn't yet support gpt-oss
🔥
1
3
#6 opened about 16 hours ago
by
ht7770
Model size 12B
5
#5 opened about 16 hours ago
by
amine-khelif
OpenAI is finally open.
🤗
👍
12
1
#3 opened about 16 hours ago
by
anupbhat
Congrats on the full release!
❤️
🚀
11
#1 opened about 16 hours ago
by
johnpaulbin