fix base-model meta

The original model is a fine-tuned of `meta-llama/Llama-2-70b-chat-hf`

README.md

@@ -19,7 +19,7 @@ tags:
 - text-generation-inference
 - region:us
 model_name: WizardLM-70B-V1.0-GPTQ
-base_model: WizardLM/WizardLM-70B-V1.0
+base_model: meta-llama/Llama-2-70b-chat-hf
 inference: false
 model_creator: WizardLM
 pipeline_tag: text-generation