ESHMO-AI/Llama_Coder

TEXT GENERATIONConcurrency Cost:2Model Size:34BQuant:FP8Ctx Length:32kPublished:Apr 14, 2026License:llama2Architecture:Transformer Open Weights Cold

ESHMO-AI/Llama_Coder is a 34 billion parameter instruction-tuned generative text model based on Meta's Code Llama architecture, designed for general code synthesis and understanding. This model is specifically optimized for following instructions and chat-based code assistance. It supports code completion and is intended for commercial and research use in English and relevant programming languages. The model is an auto-regressive language model utilizing an optimized transformer architecture.

Loading preview...

ESHMO-AI/Llama_Coder: Instruction-Tuned Code Generation

This model is the 34 billion parameter instruction-tuned variant of Meta's Code Llama family, an auto-regressive language model built on an optimized transformer architecture. It is specifically designed for general code synthesis and understanding, with a focus on instruction following and chat-based interactions.

Key Capabilities

  • Code Completion: Generates code snippets and completes existing code.
  • Instruction Following / Chat: Responds to natural language instructions for code-related tasks.
  • General Code Synthesis: Capable of generating various types of code.

Good For

  • Code Assistant Applications: Ideal for building tools that help developers with coding tasks.
  • Research and Commercial Use: Suitable for both academic research and commercial deployment in English and programming languages.
  • Instruction-Based Code Generation: Excels when provided with clear instructions for desired code output.

This model is a static release, trained between January and July 2023, and is governed by a custom commercial license from Meta. More details can be found in the research paper.