mwitiderrick commited on
Commit
ffa0c7d
·
1 Parent(s): 70af130

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +14 -5
README.md CHANGED
@@ -28,15 +28,24 @@ The modified version of the dataset can be found [here](mwitiderrick/Open-Platyp
28
  ```python
29
  from transformers import AutoTokenizer, AutoModelForCausalLM,pipeline
30
 
31
- tokenizer = AutoTokenizer.from_pretrained("mwitiderrick/open_llama_3b_chat_v_0.1")
32
- model = AutoModelForCausalLM.from_pretrained("mwitiderrick/open_llama_3b_chat_v_0.1")
33
- query = "How can I evaluate the performance and quality of the generated text from language models?"
34
  text_gen = pipeline(task="text-generation", model=model, tokenizer=tokenizer, max_length=200)
35
  output = text_gen(f"### Instruction:\n{query}### Response:\n")
36
  print(output[0]['generated_text'])
37
  """
38
  ### Instruction:
39
- How can I evaluate the performance and quality of the generated text from language models?### Response:
40
- I want to evaluate the performance of the language model by comparing the generated text with the original text. I can use a similarity measure to compare the two texts. For example, I can use the Levenshtein distance, which measures the number of edits needed to transform one text into another. The Levenshtein distance between two texts is the minimum number of edits needed to transform one text into another. The Levenshtein distance between two texts is the minimum number of edits needed to transform one text into another. The Levenshtein distance between two texts is the minimum number of edits needed to transform one text into another. The Levenshtein distance between two texts is the minimum number of edits needed to transform one text into another. The Levenshtein distance between two texts is the minimum number
 
 
 
 
 
 
 
 
 
41
  """
42
  ```
 
28
  ```python
29
  from transformers import AutoTokenizer, AutoModelForCausalLM,pipeline
30
 
31
+ tokenizer = AutoTokenizer.from_pretrained("mwitiderrick/open_llama_3b_instruct_v_0.2")
32
+ model = AutoModelForCausalLM.from_pretrained("mwitiderrick/open_llama_3b_instruct_v_0.2")
33
+ query = "Provide step-by-step instructions for making banana bread"
34
  text_gen = pipeline(task="text-generation", model=model, tokenizer=tokenizer, max_length=200)
35
  output = text_gen(f"### Instruction:\n{query}### Response:\n")
36
  print(output[0]['generated_text'])
37
  """
38
  ### Instruction:
39
+ Provide step-by-step instructions for making banana bread### Response:
40
+ 1. Preheat the oven to 350 degrees Fahrenheit.
41
+ 2. Sift together the flour, baking soda, and salt into a large bowl.
42
+ 3. In a separate bowl, whisk together the sugar, oil, and eggs.
43
+ 4. Add the wet ingredients to the dry ingredients and mix until combined.
44
+ 5. Stir in the bananas and nuts.
45
+ 6. Pour the batter into a greased loaf pan and bake for 50-60 minutes, or until a toothpick inserted into the center comes out clean.
46
+ 7. Allow the bread to cool completely before slicing and serving.
47
+ 8. Store in an airtight container for up to 3 days.
48
+ 9. Repeat steps 1-8 until all the bananas are used up.
49
+ 10. Repeat steps 1
50
  """
51
  ```