Update README.md

README.md

@@ -4,6 +4,11 @@ language:
 - en
 pipeline_tag: text-generation
 library_name: transformers
+widget:
+  - example_title: "Write python function and explain"
+    text: "<s> <|sys_start|> You are an AI assistant. You will be given a task. You must generate a detailed and long answer. <|sys_end|> <|im_start|> Write a python function that takes a list of integers and returns the squared sum of the list. <|im_end|>"
+    output:
+      text: "Response:\n````\nHere's a Python function named `squared_sum_list` that takes a list of integers as input and returns the squared sum of the list:\n\n```python\ndef squared_sum_list(lst):\n\treturn sum([num ** 2 for num in lst])\n```\nThe function `squared_sum_list` uses a list comprehension to iterate over each number in the input list `lst` and calculate its square. Then, it uses the `sum` function to accumulate all the squared numbers in a single value - the squared sum of the list.\n\nFor example:\n\n```python\nnumbers = [1, 2, 3, 4, 5]\nprint(squared_sum_list(numbers))  # Outputs: 55\n```\n\nIn the above code, the list `[1, 2, 3, 4, 5]` is passed as an argument to the `squared_sum_list` function. The function calculates the sum of the squares of the elements in the list, which is `1 + 4 + 9 + 16 + 25 = 55`. The function then returns this result, which is printed to the console.</s>"
 tags:
 - llm
 - code
@@ -36,7 +41,8 @@ We also performed the same finetuning on the last **CrystalCoder** checkpoint of
 
 # Instruction Tuning Data 
 
-The fine-tuning data is a mix of publicly available language and code datasets, plus a orginally created dataset called **WebAlpaca**. The WebAlpaca dataset is created by us and is used as part of our instruction tuning training data. We will release the WebAlpaca dataset in a separate repository soon.
+The fine-tuning data is a mix of publicly available language and code datasets, plus a orginally created dataset called **WebAlpaca** on HTML coding instructions.
+The WebAlpaca dataset is created by us and is used as part of our instruction tuning training data. We will release the WebAlpaca dataset in a separate repository soon.
 
 The summary of the fine-tuning data is as follows:
 
@@ -57,8 +63,6 @@ The summary of the fine-tuning data is as follows:
 | [Programming Books](https://huggingface.co/datasets/open-phi/programming_books_llama)   | 395,628,544        | Not instruction data
 | Total | 1,102,516,224
 
-The HTML Instruction dataset was curated by LLM360 and will be made available shortly.
-
 For more details, check out the [data table](https://huggingface.co/LLM360/CrystalChat/blob/main/data_table.jpg).
 
 # Instruction Format