Sandiago21
/

llama-13b-hf-prompt-answering

Text Generation

decapoda-research-13b-hf

prompt answering

text-generation-inference

Inference Endpoints

8-bit precision

Model card Files Files and versions Community

Sandiago21 commited on Jun 12, 2023

Commit

7c60e5e

•

1 Parent(s): 225d66b

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -108,7 +108,7 @@ MODEL_NAME = "Sandiago21/llama-13b-hf-prompt-answering"
 config = PeftConfig.from_pretrained(MODEL_NAME)
 # Setting the path to look at your repo directory, assuming that you are at that directory when running this script
-config.base_model_name_or_path = "decapoda-research/llama-7b-hf/"
 model = LlamaForCausalLM.from_pretrained(
     config.base_model_name_or_path,

 config = PeftConfig.from_pretrained(MODEL_NAME)
 # Setting the path to look at your repo directory, assuming that you are at that directory when running this script
+config.base_model_name_or_path = "decapoda-research/llama-13b-hf/"
 model = LlamaForCausalLM.from_pretrained(
     config.base_model_name_or_path,