yuvraj17
/

Llama-3-8B-spectrum-25-GPTQ

Text Generation

Generated from Trainer

spectrum finetuning

Deepspeed MultiGPU

text-generation-inference

Inference Endpoints

4-bit precision

Model card Files Files and versions Community

Llama-3-8B-spectrum-25-GPTQ

File size: 135 Bytes

3ecd43e

version https://git-lfs.github.com/spec/v1
oid sha256:20c51cfd86b2fb0995a57879a1a54eebf3107966c7d87729a0d9daa551b6cc82
size 1050673280