LnL-AI
/

dbrx-base-converted-v2-4bit-gptq-gptq

Text Generation

Inference Endpoints

text-generation-inference

4-bit precision

Model card Files Files and versions Community

dbrx-base-converted-v2-4bit-gptq-gptq / combine_tensors.sh

Qubitium's picture

Create combine_tensors.sh

b485353 verified 3 months ago

raw history blame contribute delete

No virus

92 Bytes

	# combine the two files into one
	cat ./safetensors.part > gptq_model-4bit-128g.safetensors