Create README.md
Browse files
README.md
ADDED
@@ -0,0 +1,102 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
source_model: BEE-spoke-data/smol_llama-220M-GQA
|
4 |
+
datasets:
|
5 |
+
- BEE-spoke-data/pypi_clean-deduped
|
6 |
+
- bigcode/the-stack-smol-xl
|
7 |
+
- EleutherAI/proof-pile-2
|
8 |
+
language:
|
9 |
+
- en
|
10 |
+
tags:
|
11 |
+
- python
|
12 |
+
- codegen
|
13 |
+
- markdown
|
14 |
+
- smol_llama
|
15 |
+
metrics:
|
16 |
+
- accuracy
|
17 |
+
inference:
|
18 |
+
parameters:
|
19 |
+
max_new_tokens: 48
|
20 |
+
min_new_tokens: 8
|
21 |
+
num_beams: 3
|
22 |
+
early_stopping: true
|
23 |
+
repetition_penalty: 1.1
|
24 |
+
no_repeat_ngram_size: 6
|
25 |
+
renormalize_logits: true
|
26 |
+
widget:
|
27 |
+
- text: |
|
28 |
+
def add_numbers(a, b):
|
29 |
+
return
|
30 |
+
example_title: Add Numbers Function
|
31 |
+
- text: |
|
32 |
+
class Car:
|
33 |
+
def __init__(self, make, model):
|
34 |
+
self.make = make
|
35 |
+
self.model = model
|
36 |
+
|
37 |
+
def display_car(self):
|
38 |
+
example_title: Car Class
|
39 |
+
- text: |
|
40 |
+
import pandas as pd
|
41 |
+
data = {'Name': ['Tom', 'Nick', 'John'], 'Age': [20, 21, 19]}
|
42 |
+
df = pd.DataFrame(data).convert_dtypes()
|
43 |
+
# eda
|
44 |
+
example_title: Pandas DataFrame
|
45 |
+
- text: |
|
46 |
+
def factorial(n):
|
47 |
+
if n == 0:
|
48 |
+
return 1
|
49 |
+
else:
|
50 |
+
example_title: Factorial Function
|
51 |
+
- text: |
|
52 |
+
def fibonacci(n):
|
53 |
+
if n <= 0:
|
54 |
+
raise ValueError("Incorrect input")
|
55 |
+
elif n == 1:
|
56 |
+
return 0
|
57 |
+
elif n == 2:
|
58 |
+
return 1
|
59 |
+
else:
|
60 |
+
example_title: Fibonacci Function
|
61 |
+
- text: |
|
62 |
+
import matplotlib.pyplot as plt
|
63 |
+
import numpy as np
|
64 |
+
x = np.linspace(0, 10, 100)
|
65 |
+
# simple plot
|
66 |
+
example_title: Matplotlib Plot
|
67 |
+
- text: |
|
68 |
+
def reverse_string(s:str) -> str:
|
69 |
+
return
|
70 |
+
example_title: Reverse String Function
|
71 |
+
- text: |
|
72 |
+
def is_palindrome(word:str) -> bool:
|
73 |
+
return
|
74 |
+
example_title: Palindrome Function
|
75 |
+
- text: |
|
76 |
+
def bubble_sort(lst: list):
|
77 |
+
n = len(lst)
|
78 |
+
for i in range(n):
|
79 |
+
for j in range(0, n-i-1):
|
80 |
+
example_title: Bubble Sort Function
|
81 |
+
- text: |
|
82 |
+
def binary_search(arr, low, high, x):
|
83 |
+
if high >= low:
|
84 |
+
mid = (high + low) // 2
|
85 |
+
if arr[mid] == x:
|
86 |
+
return mid
|
87 |
+
elif arr[mid] > x:
|
88 |
+
example_title: Binary Search Function
|
89 |
+
pipeline_tag: text-generation
|
90 |
+
---
|
91 |
+
|
92 |
+
# BEE-spoke-data/beecoder-220M-python
|
93 |
+
|
94 |
+
|
95 |
+
> model card WIP, more details to come.
|
96 |
+
|
97 |
+
|
98 |
+
This is `BEE-spoke-data/pypi_clean-deduped` fine-tuned for code generation on:
|
99 |
+
|
100 |
+
- filtered version of stack-smol-XL
|
101 |
+
- deduped version of 'algebraic stack' from proof-pile-2
|
102 |
+
- cleaned and deduped pypi (last dataset)
|