You can deploy this model and start earning money today!

RichardErkhov/
semcoder_-_semcoder_1030-gguf

Name: semcoder_-_semcoder_1030-gguf
Rating: 2.5 (209 reviews)

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

semcoder_1030 - GGUF

Model creator: https://huggingface.co/semcoder/
Original model: https://huggingface.co/semcoder/semcoder_1030/

Name	Quant method	Size
semcoder_1030.Q2_K.gguf	Q2_K	2.36GB
semcoder_1030.IQ3_XS.gguf	IQ3_XS	2.61GB
semcoder_1030.IQ3_S.gguf	IQ3_S	2.75GB
semcoder_1030.Q3_K_S.gguf	Q3_K_S	2.75GB
semcoder_1030.IQ3_M.gguf	IQ3_M	2.9GB
semcoder_1030.Q3_K.gguf	Q3_K	3.07GB
semcoder_1030.Q3_K_M.gguf	Q3_K_M	3.07GB
semcoder_1030.Q3_K_L.gguf	Q3_K_L	3.35GB
semcoder_1030.IQ4_XS.gguf	IQ4_XS	3.4GB
semcoder_1030.Q4_0.gguf	Q4_0	3.56GB
semcoder_1030.IQ4_NL.gguf	IQ4_NL	3.59GB
semcoder_1030.Q4_K_S.gguf	Q4_K_S	3.59GB
semcoder_1030.Q4_K.gguf	Q4_K	3.8GB
semcoder_1030.Q4_K_M.gguf	Q4_K_M	3.8GB
semcoder_1030.Q4_1.gguf	Q4_1	3.95GB
semcoder_1030.Q5_0.gguf	Q5_0	4.33GB
semcoder_1030.Q5_K_S.gguf	Q5_K_S	4.33GB
semcoder_1030.Q5_K.gguf	Q5_K	4.46GB
semcoder_1030.Q5_K_M.gguf	Q5_K_M	4.46GB
semcoder_1030.Q5_1.gguf	Q5_1	4.72GB
semcoder_1030.Q6_K.gguf	Q6_K	5.15GB
semcoder_1030.Q8_0.gguf	Q8_0	6.67GB

Original model description:

license: other library_name: transformers license_name: deepseek license_link: https://github.com/deepseek-ai/DeepSeek-Coder/blob/main/LICENSE-MODEL pipeline_tag: text-generation

🤔 SemCoder: Training Code Language Models with Comprehensive Semantics Reasoning

Refer to our GitHub repo ARiSE-Lab/SemCoder for detailed introduction to SemCoder!

Model Details

Use the code below to get started with the model. Make sure you installed the transformers library.

python

from transformers import pipeline
import torch

generator = pipeline(
  model="semcoder/semcoder_1030",
  task="text-generation",
  torch_dtype=torch.float16,
  device_map="auto",
)

# Generate Code

CODEGEN_REQUEST = """You are an exceptionally intelligent coding assistant that consistently delivers accurate and reliable <Code> according to <NL_Description>

<NL_Description>
{desc}

<Code>
"""
desc = """You are tasked with implementing a Python class that simulates a simple version of a "To-Do List" application. The class should have the following functionalities:
1. Add a new task to the to-do list.
2. Mark a task as completed.
3. Display all tasks in the to-do list.
4. Display only the incomplete tasks in the to-do list.
"""

prompt = CODEGEN_REQUEST.format(desc=desc)
result = generator(prompt, max_length=2048, num_return_sequences=1, temperature=0.0)
code = result[0]["generated_text"].split("```python")[1].split("```")[0]
print(code)

# Understand Code with Monologues

FWD_MNL_REQUEST = """Simulate the Execution: You are given a Python function and an assertion containing a function input. Complete the assertion containing the execution output corresponding to the given input in [ANSWER] and [/ANSWER] tags.
{code}
"""

tests = """
todo_list = ToDoList()
todo_list.add_task("Buy groceries")
todo_list.add_task("Complete assignment")
todo_list.mark_completed("Buy groceries")
assert todo_list.tasks == ???
"""
code += tests
prompt = FWD_MNL_REQUEST.format(code=code)
result = generator(prompt, max_length=2048, num_return_sequences=1, temperature=0.0)
print(result[0]["generated_text"])

Citation

bibtex

@article{ding2024semcoder,
  title={SemCoder: Training Code Language Models with Comprehensive Semantics},
  author={Yangruibo Ding and Jinjun Peng and Marcus J. Min and Gail Kaiser and Junfeng Yang and Baishakhi Ray},
  journal={arXiv preprint arXiv:2406.01006},
  year={2024}
}

Important Note

SemCoder models are trained on the synthetic data generated by OpenAI models. Please pay attention to OpenAI's terms of use when using the models and the datasets. SemCoder will not compete with OpenAI's commercial products.

RichardErkhov/semcoder_-_semcoder_1030-gguf