k-l-lambda
/

DeepSeek-V3.1-FP4

8-bit precision

Model card Files Files and versions

DeepSeek-V3.1-FP4

Commit History

config.json: removed fp8 quantization config.

4ad8f19

k-l-lambda commited on Sep 8

chat_template.jinja: workaround error of TensorRT-LLM.

4ae587b

k-l-lambda commited on Aug 26

enhanced chat_template for function-call.

fea23a2

k-l-lambda commited on Aug 26

initial commit

e44c3f8

k-l-lambda commited on Aug 22

initial commit

1c2108b
verified

k-l-lambda commited on Aug 22