Hugging Face's logo

LnL-AI
/
dbrx-base-converted-v2-4bit-gptq-gptq-v2

Text Generation
Transformers
dbrx
custom_code
4-bit precision
gptq
Model card Files Community
dbrx-base-converted-v2-4bit-gptq-gptq-v2 / combine_tensors.sh
Qubitium's picture
Qubitium
Create combine_tensors.sh
2847660 verified
raw
history blame contribute delete
92 Bytes
# combine the two files into one
cat ./*safetensors.part* > gptq_model-4bit-128g.safetensors