Downloads · 30 days
105
3% of all-time downloads
huizimao/gpt-oss-120b-uncensored-mxfp4
gpt-oss-120b-uncensored-mxfp4 is a machine learning model from huizimao. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
This is the MXFP4 PTQ version of huizimao/gpt-oss-120b-uncensored-bf16.
Downloads · 30 days
105
3% of all-time downloads
All-time downloads
3.6K
Public
Parameters
117B
65.3 GB on disk
Likes
7
Public
Click a slice to open those files.
.safetensors65.2 GB · 100%
How the weights are stored.
U8118B · 98%
From the Hugging Face model README
This is the MXFP4 PTQ version of huizimao/gpt-oss-120b-uncensored-bf16.
Finetuning is done on Amazon FalseReject train set with 800 samples.
PTQ is done with NVIDIA ModelOpt
Evaluation results obtained on Amazon FalseReject test set with 300 samples.
| Model Variants | False refusal rate |
|---|---|
| gpt-oss-120b original (MXFP4) | 70% |
| LoRA (BF16) | 6% |
| LoRA + PTQ (MXFP4) - this model | 24% |
Code example, documentation, and further QAT checkpoints will be released soon.