Loda LLM

from modeling_chatglm import ChatGLMForConditionalGeneration
import torch


torch.set_default_tensor_type(torch.cuda.HalfTensor)
model = ChatGLMForConditionalGeneration.from_pretrained("THUDM/chatglm-6b", trust_remote_code=True, device_map='auto')

Load LoRA

from peft import PeftModel

model = PeftModel.from_pretrained(model, "visual-openllm/visual-openllm-chatglm-6b-rola")
torch.set_default_tensor_type(torch.cuda.FloatTensor)

Downloads last month: -; Downloads are not tracked for this model. How to track

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

visual-openllm
/

visual-openllm-chatglm-6b-rola

Datasets used to train visual-openllm/visual-openllm-chatglm-6b-rola