metadata

language:
  - en
license:
  - apache-2.0
  - cc-by-nc-4.0
tags:
  - generated_from_trainer
  - instruct
  - instructions
  - code
  - instructiongen
datasets: pszemraj/fleece2instructions-codealpaca
metrics:
  - rouge
widget:
  - text: |
      git lfs install
      huggingface-cli lfs-enable-largefiles .
      git lfs track "*.bin"
      git add .
      git commit -a -m "add fp32 chkpt"
      git push
    example_title: bash
  - text: |
      export interface DocumentParams {
        pageContent: string;

        // eslint-disable-next-line @typescript-eslint/no-explicit-any
        metadata: Record<string, any>;
      }

      /**
       * Interface for interacting with a document.
       */
      export class Document implements DocumentParams {
        pageContent: string;

        // eslint-disable-next-line @typescript-eslint/no-explicit-any
        metadata: Record<string, any>;

        constructor(fields?: Partial<DocumentParams>) {
          this.pageContent = fields?.pageContent ?? this.pageContent;
          this.metadata = fields?.metadata ?? {};
        }
      }
    example_title: js
  - text: |
      def merge(left, right):
          if len(left) == 0:
              return right

          if len(right) == 0:
              return left

          result = []
          index_left = index_right = 0

          while len(result) < len(left) + len(right):
              if left[index_left] <= right[index_right]:
                  result.append(left[index_left])
                  index_left += 1
              else:
                  result.append(right[index_right])
                  index_right += 1

              if index_right == len(right):
                  result += left[index_left:]
                  break

              if index_left == len(left):
                  result += right[index_right:]
                  break

          return result
    example_title: merge
  - text: >
      import pandas as pd

      import plotly.graph_objects as go


      df =
      pd.read_csv('https://raw.githubusercontent.com/plotly/datasets/master/2014_apple_stock.csv')


      fig = go.Figure(go.Scatter(x = df['AAPL_x'], y = df['AAPL_y'],
                        name='Share Prices (in USD)'))

      fig.update_layout(title='Apple Share Prices over time (2014)',
                         plot_bgcolor='rgb(230, 230,230)',
                         showlegend=True)

      fig.show()
    example_title: plot
  - text: |
      from spellchecker import SpellChecker

      spell = SpellChecker()

      def check_word_spelling(word: str):
          misspelled = spell.unknown([word])
          return len(misspelled) == 0

      def eval_and_replace(text: str, match_token: str = "- "):
          if match_token not in text:
              return text
          else:
              while True:
                  full_before_text = text.split(match_token, maxsplit=1)[0]
                  before_text = [
                      char for char in full_before_text.split()[-1] if char.isalpha()
                  ]
                  before_text = "".join(before_text)
                  full_after_text = text.split(match_token, maxsplit=1)[-1]
                  after_text = [char for char in full_after_text.split()[0] if char.isalpha()]
                  after_text = "".join(after_text)
                  full_text = before_text + after_text
                  if check_word_spelling(full_text):
                      text = full_before_text + full_after_text
                  else:
                      text = full_before_text + " " + full_after_text
                  if match_token not in text:
                      break
              return text

      text = "I- am- a go- od- boy"
      eval_and_replace(text)
    example_title: spell check
  - text: >
      import torch

      from transformers import AutoTokenizer, AutoModelForSequenceClassification


      checkpoint = "distilbert-base-uncased-finetuned-sst-2-english"

      tokenizer = AutoTokenizer.from_pretrained(checkpoint)

      model = AutoModelForSequenceClassification.from_pretrained(checkpoint)

      sequences = ["I've been waiting for a HuggingFace course my whole life.",
      "So have I!"]


      tokens = tokenizer(sequences, padding=True, truncation=True,
      return_tensors="pt")

      output = model(**tokens)
    example_title: model inference
inference:
  parameters:
    max_length: 96
    num_beams: 4
base_model: facebook/bart-large

bart-large-code-instructiongen

Use this text2text model to find out what LLM instructions might be able to generate an arbitary piece of code!

Check out a basic demo on Spaces
An example of how to use instructiongen models in a CLI script can be found here
You can find other models fine-tuned for instruction generation by searching for the instructiongen tag

about

This model is a fine-tuned version of facebook/bart-large on the pszemraj/fleece2instructions-codealpaca dataset. It achieves the following results on the evaluation set:

Loss: 0.9222
Rouge1: 62.0692
Rouge2: 36.1947
Rougel: 57.5128
Rougelsum: 58.6613
Gen Len: 31.0060

Intended uses & limitations

🚨 note: as the authors elected to release the original dataset under cc-by-nc, the license carries over to this model and cannot be used for commercial activity.

Intended use: Research on domain adaptation and/or other improvements to LLMs by extending instruction:text data pairs.

Training and evaluation data

Refer to the linked dataset card for pszemraj/fleece2instructions-codealpaca or the original dataset repo.

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 6e-05
train_batch_size: 16
eval_batch_size: 8
seed: 42
distributed_type: multi-GPU
gradient_accumulation_steps: 2
total_train_batch_size: 32
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.03
num_epochs: 3.0

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
1.0914	1.0	563	1.0303	60.288	34.1884	55.9293	57.0714	30.6267
0.8688	2.0	1126	0.9333	61.0409	34.9823	56.4887	57.6662	31.7255
0.6773	3.0	1689	0.9222	62.0692	36.1947	57.5128	58.6613	31.0060