🌐 Nyra-C: The Instruction & Execution Core

Nyra-C is the precision-focused model developed by Logihertz Systems OPC Pvt Ltd. As part of the independent Nyra Project, this model serves as the "Instruction & Execution Core" (Tier C), optimized specifically for zero-shot instruction following, code generation, and agentic tool-use.

🛠 Model Specifications

• Developer: Logihertz Systems
• Lead Architect: Sameer Tawade
• Project Status: Independent Research
• Architecture: Optimized Llama-3-8B (Transformer-based)
• Merge Methodology: DARE-TIES + SLERP (Optimized for strict formatting and attention retention)
• Language(s): English (Primary), Python, JavaScript, C++ (Code)

🎯 Intended Use Cases

Nyra-C is engineered for backend operations, API integrations, and developer-facing tasks:

• Strict Formatting: Reliably outputting syntactically correct JSON, YAML, and XML without conversational filler.
• Code Generation: Writing, debugging, and refactoring code across multiple programming languages.
• Agentic Routing: Serving as the decision-making node in multi-agent frameworks, capable of parsing user intent and selecting the correct external tools or APIs.

📊 Evaluation & Benchmarking Matrix

This model is currently undergoing rigorous evaluation. Scores are marked as pending while the self-verified evaluation pipeline completes.

Category	Benchmark	Metric	Score	Status
Code Generation	HumanEval	Pass@1	Pending	Eval in Progress
Code Generation	MBPP	Pass@1	Pending	Eval in Progress
Instruction Following	IFEval	Prompt-level Strict	Pending	Eval in Progress
Tool Use / Agents	BFCL (Berkeley)	Overall Accuracy	Pending	Eval in Progress
General Reasoning	MMLU-Pro	5-shot Accuracy	Pending	Eval in Progress
Math Execution	MATH	4-shot Chain-of-Thought	Pending	Eval in Progress

💻 Implementation

To run Nyra-C locally, ensure you have the latest transformers library installed.

from transformers import AutoModelForCausalGeneration, AutoTokenizer
import torch

model_id = "logihertz/nyra-C"

tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalGeneration.from_pretrained(
    model_id, 
    torch_dtype=torch.float16, 
    device_map="auto"
)

prompt = "Write a Python script using the requests library to fetch data from an

⚖️ Limitations & Ethical Considerations

Nyra-C is released under the Llama 3 Community License. While highly capable at instruction following and code generation, it is not a substitute for human code review. Security vulnerabilities may occasionally be present in generated code. Users should implement secondary validation systems for critical deployments.