firqaaa
/

indo-alpaca-lora-7b

Text Generation

Inference Endpoints

Model card Files Files and versions Community

firqaaa commited on Apr 7, 2023

Commit

0d64c06

·

1 Parent(s): e854a70

Update README.md

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -23,7 +23,7 @@ model = LlamaForCausalLM.from_pretrained("decapoda-research/llama-7b-hf",
 # Load the LoRA model
 model = PeftModel.from_pretrained(model, peft_model_id)
 ```
-## Create Prompt Template
 ```python
 def generate_prompt(instruction, input=None):
@@ -48,7 +48,7 @@ Output:"""
 ```
 ## Evaluation
-You are free to change parameters inside `GenerationConfig` to get better result.
 ```python
 generation_config = GenerationConfig(

 # Load the LoRA model
 model = PeftModel.from_pretrained(model, peft_model_id)
 ```
+## Prompt Template
 ```python
 def generate_prompt(instruction, input=None):
 ```
 ## Evaluation
+feel free to change the parameters inside `GenerationConfig` to get better result.
 ```python
 generation_config = GenerationConfig(