shisa-ai
/

shisa-v2-qwen2.5-32b-W8A8-INT8

8-bit precision

compressed-tensors

Model card Files Files and versions Community

Quantized w/ llm-compressor

Downloads last month: 8

Safetensors

Model size

32.8B 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-qwen2.5-32b-W8A8-INT8

Base model

Qwen/Qwen2.5-32B

Finetuned

Qwen/Qwen2.5-32B-Instruct

Finetuned

shisa-ai/shisa-v2-qwen2.5-32b

Quantized

(6)

this model

Collection including shisa-ai/shisa-v2-qwen2.5-32b-W8A8-INT8

Shisa V2

A family of bilingual JA/EN LLMs • 32 items • Updated 5 days ago • 7