od-dev
/

gpt-oss-120b-mod-merged

Text Generation

8-bit precision

Model card Files Files and versions

gpt-oss-120b Moderation (MXFP4)

Merged LoRA fine-tune of openai/gpt-oss-120b for chat content moderation.

Base model: openai/gpt-oss-120b
Format: MXFP4 (native quantization)
Serving: vLLM with --tensor-parallel-size 4 on 4xH100

Downloads last month: 344

Safetensors

Model size

120B params

Tensor type

BF16

·

U8

·

Model tree for od-dev/gpt-oss-120b-mod-merged

Base model

openai/gpt-oss-120b

Quantized

(95)

this model