kajdun
/

iubaris-13b-v3_GPTQ

Text Generation

Inference Endpoints

4-bit precision

Model card Files Files and versions Community

kajdun commited on Aug 11, 2023

Commit

8e9b3d6

·

1 Parent(s): a9a5426

Upload folder using huggingface_hub

Files changed (1) hide show

handler.py +1 -1

handler.py CHANGED Viewed

@@ -1,4 +1,4 @@
-#from typing import Dict, List, Any
 #import torch
 #from transformers import AutoTokenizer, GenerationConfig
 #from auto_gptq import AutoGPTQForCausalLM, BaseQuantizeConfig

+from typing import Dict, List, Any
 #import torch
 #from transformers import AutoTokenizer, GenerationConfig
 #from auto_gptq import AutoGPTQForCausalLM, BaseQuantizeConfig