metadata
license: apache-2.0
language:
- en
metrics:
- accuracy
tags:
- document
- code
- code2doc
- instruction_tuned
- basemodel
- pytorch
- docstring
- python
- documentation
- text-generation-inference
library_name: transformers
pipeline_tag: text-generation
widget:
- text: >-
<code>def get_np_array_transition_probability_matrix(int_num_states,
np_array_A_matrix):print(np_array_A_matrix)np_array_A_matrix +=
(np.full((int_num_states, int_num_states), float_eps) -
(np.identity(int_num_states) *
float_eps))print(np_array_A_matrix)np_array_D_matrix =
np.diag(np.sum(np_array_A_matrix,
axis=1))print(np_array_D_matrix)np_array_D_matrix_inv =
np.linalg.inv(np_array_D_matrix)print(np_array_D_matrix_inv)np_array_P_matrix
= np.dot(np_array_D_matrix_inv,
np_array_A_matrix)print(np_array_P_matrix)print(np.sum(np_array_P_matrix,
axis=1))return np_array_P_matrix</code><question>Document the python code
above.</question><doc>
example_title: example
pip-code-to-doc
What have we built?
A 1.3 bn code documentation model that outperforms most models on documenting codes and making your in-house libs ready for LLM and RAG pipelines. We have also open sourced a parsing lib for the same, together the lib and model can turn your codebase to functional parse tree ready to be consumed by LLMs to execute complex tasks. This is a further trained version of pip-sql-1.3b.
How we built it?
We used softmax cross entropy and a modified form of policy grad along with Q loss, optimized in an EM set up. Loss behaviour in the set up mentioned above -
License
The model is open source under apache 2.0. License
Usage
Library use
pip3 install git+https://github.com/PipableAI/pip-library-parser
pip3 install atlassian-python-api
import torch
torch.set_default_device("cuda")
from pip_library_parser import generate_module_docs
from atlassian.jira import Jira
docs = generate_module_docs(Jira, "atlassian.jira.Jira")
print(docs)
Installation
pip install transformers
Prompt
prompt = f"""<code>{code}</code>
<question>Document the code above</question>
<doc>"""
PyTorch
from transformers import AutoModelForCausalLM, AutoTokenizer
device = "cuda"
model = AutoModelForCausalLM.from_pretrained("PipableAI/pip-code-to-doc-1.3b").to(device)
tokenizer = AutoTokenizer.from_pretrained("PipableAI/pip-code-to-doc-1.3b")
inputs = tokenizer(text, return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=300)
tokenizer.decode(outputs[0], skip_special_tokens=True).split('<doc>')[-1].split('</doc>')[0]
Examples
Code
<code>
###########################
# Generate Analytical Model
###########################
##################################################
# func: get_np_array_transition_probability_matrix
##################################################
def get_np_array_transition_probability_matrix(int_num_states, np_array_A_matrix):
print('np_array_A_matrix:')
print(np_array_A_matrix)
#####################################################
# Perturb the adjacency matrix to avoid singularities
#####################################################
np_array_A_matrix += (np.full((int_num_states, int_num_states), float_eps) - (np.identity(int_num_states) * float_eps))
print('np_array_A_matrix:')
print(np_array_A_matrix)
print('np_array_D_matrix:')
np_array_D_matrix = np.diag(np.sum(np_array_A_matrix, axis=1))
print(np_array_D_matrix)
print('np_array_D_matrix_inv:')
np_array_D_matrix_inv = np.linalg.inv(np_array_D_matrix)
print(np_array_D_matrix_inv)
print('\n\n')
print('np_array_P_matrix:')
np_array_P_matrix = np.dot(np_array_D_matrix_inv, np_array_A_matrix)
print(np_array_P_matrix)
print('np.sum(np_array_P_matrix, axis=1):')
print(np.sum(np_array_P_matrix, axis=1))
print('\n\n')
return np_array_P_matrix
##################################################
# func: get_np_array_perron_frobenius_eigen_vector
##################################################
def get_np_array_perron_frobenius_matrix(int_num_states, np_array_P_matrix):
np_array_perron_frobenius_matrix = np.linalg.matrix_power(np_array_P_matrix,1000)
np_array_perron_frobenius_vector = np_array_perron_frobenius_matrix[0,:]
print('np_array_perron_frobenius_matrix:')
print(np_array_perron_frobenius_matrix)
print('np.sum(np_array_perron_frobenius_matrix, axis=1):')
print(np.sum(np_array_perron_frobenius_matrix, axis=1))
print('np.sum(np_array_perron_frobenius_matrix, axis=0):')
print(np.sum(np_array_perron_frobenius_matrix, axis=0))
print('np.sum(np_array_perron_frobenius_matrix, axis=0)/int_num_states:')
print(np.sum(np_array_perron_frobenius_matrix, axis=0)/int_num_states)
print('np.dot(np_array_perron_frobenius_vector, np_array_P_matrix):')
print(np.dot(np_array_perron_frobenius_vector, np_array_P_matrix))
print('np_array_perron_frobenius_vector:')
print(np_array_perron_frobenius_vector)
print('\n\n')
return np_array_perron_frobenius_vector, np_array_perron_frobenius_matrix
#############################
# func: get_np_array_Z_matrix
#############################
def get_np_array_Z_matrix(int_num_states, np_array_P_matrix, np_array_perron_frobenius_matrix):
np_array_Z_matrix = np.linalg.inv(np.identity(int_num_states) - np_array_P_matrix + np_array_perron_frobenius_matrix)
print('np_array_Z_matrix:')
print(np_array_Z_matrix)
print('\n\n')
return(np_array_Z_matrix)
#############################
# func: get_np_array_H_matrix
#############################
def get_np_array_H_matrix(int_num_states, np_array_Z_matrix, np_array_perron_frobenius_vector):
np_array_H_matrix = np.zeros([int_num_states, int_num_states])
for i in range(int_num_states):
for j in range(int_num_states):
np_array_H_matrix[i][j] = (np_array_Z_matrix[j][j] - np_array_Z_matrix[i][j])/np_array_perron_frobenius_vector[j]
print('np_array_H_matrix:')
print(np_array_H_matrix)
print('\n\n')
return np_array_H_matrix
###########
# func: run
###########
def run(np_array_A_matrix):
int_num_states = len(np_array_A_matrix)
np_array_P_matrix = get_np_array_transition_probability_matrix(int_num_states, np_array_A_matrix)
np_array_perron_frobenius_vector, np_array_perron_frobenius_matrix = get_np_array_perron_frobenius_matrix(int_num_states, np_array_P_matrix)
np_array_Z_matrix = get_np_array_Z_matrix(int_num_states, np_array_P_matrix, np_array_perron_frobenius_matrix)
np_array_H_matrix = get_np_array_H_matrix(int_num_states, np_array_Z_matrix, np_array_perron_frobenius_vector)
return(np_array_H_matrix)</code>
<question>Document the python code above.
</question><doc>
Response
The Python code provided is used to generate an analytical model for a Markov chain with a given adjacency matrix.
The model is then used to compute the Perron-Frobenius eigenvector and the corresponding matrix. The resulting matrices are then used to compute the Z-matrix and
the H-matrix. The H-matrix is then returned as the output of the function. The code is designed to handle large matrices and perform computations efficiently.
The matrices are manipulated using numpy's powerful and efficient numerical computation library.
The code also includes comments to explain the functionality of each part of the code.
Team
Avi Kothari, Gyan Ranjan, Pratham Gupta, Ritvik Aryan Kalra, Soham Acharya