S-miguel's picture
Update README.md
cca1997 verified
metadata
license: apache-2.0
language:
  - en
library_name: transformers
tags:
  - Code Generation
  - Logical Reasoning
  - Problem Solving
  - Text Generation
  - AI Programming Assistant

The-Trinity-Coder-7B: 3 Blended Coder Models - Unified Coding Intelligence

image/png

Overview

The-Trinity-Coder-7B derives from the fusion of three distinct AI models, each specializing in unique aspects of coding and programming challenges. This model unifies the capabilities of beowolx_CodeNinja-1.0-OpenChat-7B, NeuralExperiment-7b-MagicCoder, and Speechless-Zephyr-Code-Functionary-7B, creating a versatile and powerful new blended model. The integration of these models was achieved through a merging technique, in order to harmonize their strengths and mitigate their individual weaknesses.

The Blend

  • Comprehensive Coding Knowledge: TrinityAI combines knowledge of coding instructions across a wide array of programming languages, including Python, C, C++, Rust, Java, JavaScript, and more, making it a versatile assistant for coding projects of any scale.
  • Advanced Code Completion: With its extensive context window, TrinityAI excels in project-level code completion, offering suggestions that are contextually relevant and syntactically accurate.
  • Specialized Skills Integration: The-Trinity-Coder provides code completion but is also good at logical reasoning for its size, mathematical problem-solving, and understanding complex programming concepts.

Model Synthesis Approach

The blending of the three models into TrinityAI utilized a unique merging technique that focused on preserving the core strengths of each component model:

  • beowolx_CodeNinja-1.0-OpenChat-7B: This model brings an expansive database of coding instructions, refined through Supervised Fine Tuning, making it an advanced coding assistant.
  • NeuralExperiment-7b-MagicCoder: Trained on datasets focusing on logical reasoning, mathematics, and programming, this model enhances TrinityAI's problem-solving and logical reasoning capabilities.
  • Speechless-Zephyr-Code-Functionary-7B: Part of the Moloras experiments, this model contributes enhanced coding proficiency and dynamic skill integration through its unique LoRA modules.

Usage and Implementation

from transformers import AutoTokenizer, AutoModelForCausalLM

model_name = "YourRepository/The-Trinity-Coder-7B" tokenizer = AutoTokenizer.from_pretrained(model_name) model = AutoModelForCausalLM.from_pretrained(model_name)

prompt = "Your prompt here" inputs = tokenizer(prompt, return_tensors="pt") outputs = model.generate(**inputs) print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Acknowledgments

Special thanks to the creators and contributors of CodeNinja, NeuralExperiment-7b-MagicCoder, and Speechless-Zephyr-Code-Functionary-7B for providing the base models for blending.


base_model: [] library_name: transformers tags:

  • mergekit
  • merge

merged_folder

This is a merge of pre-trained language models created using mergekit.

Merge Details

Merge Method

This model was merged using the TIES merge method using uukuguy_speechless-zephyr-code-functionary-7b as a base.

Models Merged

The following models were included in the merge: *uukuguy_speechless-zephyr-code-functionary-7b

  • Kukedlc_NeuralExperiment-7b-MagicCoder-v7.5
  • beowolx_CodeNinja-1.0-OpenChat-7B

Configuration

The following YAML configuration was used to produce this model:

base_model: X:/text-generation-webui-main/models/uukuguy_speechless-zephyr-code-functionary-7b
models:
  - model: X:/text-generation-webui-main/models/beowolx_CodeNinja-1.0-OpenChat-7B
    parameters:
      density: 0.5
      weight: 0.4
  - model: X:/text-generation-webui-main/models/Kukedlc_NeuralExperiment-7b-MagicCoder-v7.5
    parameters:
      density: 0.5
      weight: 0.4
merge_method: ties
parameters:
  normalize: true
dtype: float16