Hugging Face's logo

shisa-ai
/
shisa-v2-mistral-nemo-12b-W8A8-INT8

Safetensors
Japanese
English
mistral
8-bit precision
compressed-tensors
Model card Files Community

Quantized w/ llm-compressor

Downloads last month
43
Safetensors
Model size
12.2B params
Tensor type
BF16
·
I8
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for shisa-ai/shisa-v2-mistral-nemo-12b-W8A8-INT8

Base model

mistralai/Mistral-Nemo-Base-2407
Finetuned
mistralai/Mistral-Nemo-Instruct-2407
Finetuned
shisa-ai/shisa-v2-mistral-nemo-12b
Quantized
(3)
this model

Collection including shisa-ai/shisa-v2-mistral-nemo-12b-W8A8-INT8