GaLLM-14B-v0.1的GPTQ-Int4量化版，使用方法相同

推荐使用vllm部署，然后使用OpenAI格式的API访问：

vllm serve CjangCjengh/GaLLM-14B-v0.1-GPTQ-Int4 --port <your_port>

Safetensors

Model size

3.33B params

Tensor type

I32

FP16

Inference Providers NEW

This model is not currently available via any of the supported Inference Providers.

The model cannot be deployed to the HF Inference API: The model has no library tag.

Model tree for SakuraLLM/GaLLM-14B-v0.1-GPTQ-Int4

Base model

Finetuned

Quantized

(3)

this model