| --- |
| license: apache-2.0 |
| base_model: BEE-spoke-data/smol_llama-220M-GQA |
| datasets: |
| - BEE-spoke-data/pypi_clean-deduped |
| - bigcode/the-stack-smol-xl |
| - EleutherAI/proof-pile-2 |
| language: |
| - en |
| tags: |
| - python |
| - codegen |
| - markdown |
| - smol_llama |
| metrics: |
| - accuracy |
| inference: |
| parameters: |
| max_new_tokens: 64 |
| min_new_tokens: 8 |
| do_sample: true |
| epsilon_cutoff: 0.0008 |
| temperature: 0.3 |
| top_p: 0.9 |
| repetition_penalty: 1.02 |
| no_repeat_ngram_size: 8 |
| renormalize_logits: true |
| widget: |
| - text: | |
| def add_numbers(a, b): |
| return |
| example_title: Add Numbers Function |
| - text: | |
| class Car: |
| def __init__(self, make, model): |
| self.make = make |
| self.model = model |
| |
| def display_car(self): |
| example_title: Car Class |
| - text: | |
| import pandas as pd |
| data = {'Name': ['Tom', 'Nick', 'John'], 'Age': [20, 21, 19]} |
| df = pd.DataFrame(data).convert_dtypes() |
| # eda |
| example_title: Pandas DataFrame |
| - text: | |
| def factorial(n): |
| if n == 0: |
| return 1 |
| else: |
| example_title: Factorial Function |
| - text: | |
| def fibonacci(n): |
| if n <= 0: |
| raise ValueError("Incorrect input") |
| elif n == 1: |
| return 0 |
| elif n == 2: |
| return 1 |
| else: |
| example_title: Fibonacci Function |
| - text: | |
| import matplotlib.pyplot as plt |
| import numpy as np |
| x = np.linspace(0, 10, 100) |
| # simple plot |
| example_title: Matplotlib Plot |
| - text: | |
| def reverse_string(s:str) -> str: |
| return |
| example_title: Reverse String Function |
| - text: | |
| def is_palindrome(word:str) -> bool: |
| return |
| example_title: Palindrome Function |
| - text: | |
| def bubble_sort(lst: list): |
| n = len(lst) |
| for i in range(n): |
| for j in range(0, n-i-1): |
| example_title: Bubble Sort Function |
| - text: | |
| def binary_search(arr, low, high, x): |
| if high >= low: |
| mid = (high + low) // 2 |
| if arr[mid] == x: |
| return mid |
| elif arr[mid] > x: |
| example_title: Binary Search Function |
| pipeline_tag: text-generation |
| --- |
| |
| # BEE-spoke-data/beecoder-220M-python |
|
|
|
|
|
|
|
|
| This is `BEE-spoke-data/smol_llama-220M-GQA` fine-tuned for code generation on: |
|
|
| - filtered version of stack-smol-XL |
| - deduped version of 'algebraic stack' from proof-pile-2 |
| - cleaned and deduped pypi (last dataset) |
|
|
| This model (and the base model) were both trained using ctx length 2048. |
|
|
| ## examples |
|
|
| > Example script for inference testing: [here](https://gist.github.com/pszemraj/c7738f664a64b935a558974d23a7aa8c) |
|
|
| It has its limitations at 220M, but seems decent for single-line or docstring generation, and/or being used for speculative decoding for such purposes. |
|
|
|
|
|
|
|  |
|
|
| The screenshot is on CPU on a laptop. |
|
|
| --- |
