g-assismoraes/DeltaP2S-Llama2-13B-DeltaP2S-CodeLlama7B

TEXT GENERATIONPricing:Input $1.5 / Output $2.1Concurrent Unit Cost:1Model Size:13BQuant:FP8Context Size:4kPublished:Aug 24, 2026Architecture:Transformer Featherless Exclusive Cold

The g-assismoraes/DeltaP2S-Llama2-13B-DeltaP2S-CodeLlama7B model is a 13 billion parameter language model with a 4096-token context length. It is a merged checkpoint derived from a Delta-P2S experiment, utilizing a CodeLlama base. This model is specifically designed for tasks related to code, leveraging its CodeLlama foundation for enhanced performance in programming contexts.

Loading preview...

Model Overview

The g-assismoraes/DeltaP2S-Llama2-13B-DeltaP2S-CodeLlama7B is a 13 billion parameter language model, featuring a context length of 4096 tokens. This model represents a merged checkpoint resulting from a Delta-P2S experiment, indicating a specialized training or fine-tuning process. Its foundation is built upon a CodeLlama base, suggesting a strong orientation towards code-related tasks.

Key Characteristics

  • Architecture: Based on a CodeLlama foundation, indicating capabilities in understanding and generating code.
  • Parameter Count: 13 billion parameters, offering a balance between performance and computational requirements.
  • Context Length: Supports a 4096-token context window, suitable for processing moderately long code snippets or technical documentation.
  • Origin: A merged checkpoint from a Delta-P2S experiment, implying a focus on specific optimization or task performance.

Potential Use Cases

Given its CodeLlama base and experimental origin, this model is likely well-suited for:

  • Code generation and completion.
  • Code understanding and analysis.
  • Debugging assistance.
  • Translating between programming languages.
  • Educational tools for programming.

Finetunes
4 models