kathywu95
/

deepseek-v3.2-small-random-fp8-64-experts

Model card Files Files and versions

For testing purposes only.

Changes from deepseek-ai/DeepSeek-V3.2:

Number of hidden layers changed to 2
first_k_dense_replace changed to 1
Number of experts changed from 256 to 64

Downloads last month: 11

Safetensors

Model size

6B params

Tensor type

F32

·

BF16

·

F8_E4M3

·

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for kathywu95/deepseek-v3.2-small-random-fp8-64-experts

Base model

deepseek-ai/DeepSeek-V3.2-Exp-Base

Finetuned

deepseek-ai/DeepSeek-V3.2

Quantized

(20)

this model