Update README.md

README.md

@@ -2,10 +2,6 @@
 base_model: NousResearch/Llama-2-7b-hf
 inference: false
 model_type: llama
-prompt_template: |
-  <s>[INST] 
-  {prompt}
-   [/INST]
 quantized_by: mwitiderrick
 tags:
 - deepsparse
@@ -24,24 +20,24 @@ Run in a [Python pipeline](https://github.com/neuralmagic/deepsparse/blob/main/d
 ```python
 from deepsparse import TextGeneration
 
-prompt = "How to make banana bread?"
-formatted_prompt =  f"<s>[INST]{prompt}[/INST]"
+prompt = "Once upon a time "
 
 model = TextGeneration(model_path="hf:nm-testing/Llama-2-7b-hf-pruned50-quant-ds")
 
-print(model(formatted_prompt, max_new_tokens=200).generations[0].text)
+print(model(prompt, max_new_tokens=200).generations[0].text)
 """
-
+1999
+The first time I saw the movie Once Were Twice was when I was in my early teens.
+I remember watching it with my brother and sister. I remember that I was very young and that I was not able to understand the movie.
+I remember that I was very young and that I was not able to understand the movie. I remember that I was very young and that I was not able to understand the movie.
+I remember that I was very young and that I was not able to understand the movie. I remember that I was very young and that I was not able to understand the movie.
+I remember that I was very young and that I was not able to understand the movie. I remember that I was very young and that I was not able to understand the movie.
+I remember that I was very young and that I was not able to understand the movie. I remember that I was very young and that I was not able to understand the movie.
+I remember
 """
 ```
 
-## Prompt template
-```
-<s>[INST]
-<prompt>
-[/INST]
 
-```
 ## Sparsification
 For details on how this model was sparsified, see the `recipe.yaml` in this repo and follow the instructions below.