Instructions to use logihertz/nyra-C with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use logihertz/nyra-C with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="logihertz/nyra-C")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("logihertz/nyra-C")
model = AutoModelForCausalLM.from_pretrained("logihertz/nyra-C")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use logihertz/nyra-C with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "logihertz/nyra-C"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "logihertz/nyra-C",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/logihertz/nyra-C

SGLang

How to use logihertz/nyra-C with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "logihertz/nyra-C" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "logihertz/nyra-C",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "logihertz/nyra-C" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "logihertz/nyra-C",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use logihertz/nyra-C with Docker Model Runner:
```
docker model run hf.co/logihertz/nyra-C
```

🌐 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.

Downloads last month: 4

Safetensors

Model size

8B params

Tensor type

F16

Model tree for logihertz/nyra-C

Base model

meta-llama/Meta-Llama-3-8B

Finetuned

(606)

this model