g-assismoraes/DeltaP2S-Llama2-13B-P2S-CodeLlama7B-SameFormula-S13

TEXT GENERATIONPricing:Input $1.5 / Output $2.1Concurrent Unit Cost:1Model Size:13BQuant:FP8Context Size:4kPublished:Aug 28, 2026Architecture:Transformer Featherless Exclusive Cold

The g-assismoraes/DeltaP2S-Llama2-13B-P2S-CodeLlama7B-SameFormula-S13 is a 13 billion parameter language model, a merged checkpoint derived from a standalone Delta-P2S experiment. This model is based on a Llama 2 13B architecture, incorporating elements from CodeLlama 7B, and is specifically trained using the 'SameFormula-S13' configuration. It is designed for tasks related to its P2S training methodology, offering a context length of 4096 tokens.

Loading preview...

Model Overview

The g-assismoraes/DeltaP2S-Llama2-13B-P2S-CodeLlama7B-SameFormula-S13 is a 13 billion parameter language model, representing a merged checkpoint from a specialized Delta-P2S experiment. This model integrates a Llama 2 13B base with components from CodeLlama 7B, indicating a potential focus on code-related or structured prediction tasks.

Key Characteristics

  • Architecture: Based on Llama 2 13B, with influences from CodeLlama 7B.
  • Parameter Count: 13 billion parameters.
  • Context Length: Supports a context window of 4096 tokens.
  • Training Origin: Produced from a standalone Delta-P2S experiment package, specifically trained under the codellama_llama_SameFormula-S13 configuration.

Intended Use Cases

This model is a result of a specific research or development experiment, suggesting its utility in:

  • Research and Development: Exploring the effects of the Delta-P2S merging technique and the SameFormula-S13 training configuration.
  • Code-Related Tasks: Given the CodeLlama 7B integration, it may be suitable for tasks involving code generation, completion, or understanding.
  • Comparative Analysis: Useful for comparing performance against other Llama 2 or CodeLlama variants, especially concerning the P2S methodology.

Finetunes
2 models