Readme
CodeLlama is a family of fine-tuned Llama 2 models for coding. This is CodeLlama-70b-python, a 70 billion parameter Llama model tuned for writing Python.
meta
/
codellama-70b-python
A 70 billion parameter Llama tuned for coding with Python
Input
Output
from random import uniform, randint
from math import sqrt
accuracy = 0.05
radius = 1
iterations = 400
center = (radius/2,radius/2)
def distance(point):
return sqrt((point[0]-center[0])**2 + (point[1] - center[1])**2)
points_in_circle = 0
# This function is called for each iteration of the algorithm to see if a given point lies within the circle
def check(iterations):
nonlocal points_in_circle, accuracy, radius
for i in range(iterations):
x = uniform(-sqrt(radius), sqrt(radius))**2
y = uniform(-sqrt(radius), sqrt(radius))**2
if (distance((x,y)) <= radius): # True -> point lies within circle
points_in_circle += 1
def calculate(): # This function calculates pi from the data collected by check()
nonlocal points_in_circle, iterations
ratio = 4*points_in_circle/iterations
if abs(3.14 - ratio) > accuracy:
return ratio
for i in range(0, iterations, randint(25,75)): # The intervals are randomized to prevent patterns from forming
check(i) # which would ruin the approximation of pi
return calculate()
Generated in
Run time and cost
This model costs approximately $0.077 to run on Replicate, or 12 runs per $1, but this varies depending on your inputs. It is also open source and you can run it on your own computer with Docker.
This model runs on Nvidia A100 (80GB) GPU hardware. Predictions typically complete within 56 seconds.