Instructions to use DeepNarra/Hiraya with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use DeepNarra/Hiraya with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="DeepNarra/Hiraya")# pip install -U transformers accelerate # Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("DeepNarra/Hiraya", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use DeepNarra/Hiraya with llama.cpp:
Install (macOS, Linux)
curl -LsSf https://llama.app/install.sh | sh # Start a local OpenAI-compatible server with a web UI: llama serve -hf DeepNarra/Hiraya:TQ1_0 # Run inference directly in the terminal: llama cli -hf DeepNarra/Hiraya:TQ1_0
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf DeepNarra/Hiraya:TQ1_0 # Run inference directly in the terminal: llama cli -hf DeepNarra/Hiraya:TQ1_0
Build from source code
git clone https://github.com/ggml-org/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-app # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama serve -hf DeepNarra/Hiraya:TQ1_0 # Run inference directly in the terminal: ./build/bin/llama cli -hf DeepNarra/Hiraya:TQ1_0
Use Docker
docker model run hf.co/DeepNarra/Hiraya:TQ1_0
- Llama new
- LM Studio
- Jan
- vLLM
How to use DeepNarra/Hiraya with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "DeepNarra/Hiraya" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "DeepNarra/Hiraya", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/DeepNarra/Hiraya:TQ1_0
- SGLang
How to use DeepNarra/Hiraya 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 "DeepNarra/Hiraya" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "DeepNarra/Hiraya", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'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 "DeepNarra/Hiraya" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "DeepNarra/Hiraya", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Ollama
How to use DeepNarra/Hiraya with Ollama:
ollama run hf.co/DeepNarra/Hiraya:TQ1_0
- Unsloth Desktop
- Docker Model Runner
How to use DeepNarra/Hiraya with Docker Model Runner:
docker model run hf.co/DeepNarra/Hiraya:TQ1_0
- Lemonade
How to use DeepNarra/Hiraya with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull DeepNarra/Hiraya:TQ1_0
Run and chat with the model
lemonade run user.Hiraya-TQ1_0
List all available models
lemonade list
- Atomic Chat
🍎 DeepNarra Hiraya 1.0 (28.5M-A6.2M Sovereign Edge)
The Sovereign Fruit & Flagship ("Thinker & Faster") — Continuous Latent Deliberation & Symplectic H-MoE
Organization: DeepNarra
Designation: The Sovereign Fruit & Flagship ("Thinker & Faster")
Architecture:DeepNarraHirayaForCausalLM— Two-Tier 92-Expert H-MoE + 768-D Coconut Latent Space + Symplectic Störmer-Verlet
Full-Scale 0.91B H-MoE Checkpoint:DeepNarra/Hiraya-1-Reasoning(908,645,372params)
Empirically Measured Velocity: 378.5 tok/s (42.27 mslatency) (Verified live on single Tesla T4 GPU)
Evaluation Governance: Zero Fake Scores Policy — 100% Verifiable Engineering Facts Only
🌲 NARRA 🦈 MAKO 🍎 HIRAYA
The Tree Anchored in the Sand The Water Where the Shark Thrives The Fruit of All That Work
(Unyielding Strength & Deep Roots) (Fluid Speed & Freedom) (Realization of Hopes & Dreams)
⚡
👑 DEEPNARRA PAHAM (THE SAGE)
(The Sovereign Final Frontier)
🏛️ Verified Technical Specifications (Exact Repository Match)
| Architectural Metric | Exact Verified Value in This Repository |
|---|---|
| Official Model Name | DeepNarra Hiraya 1.0 (28.5M-A6.2M Sovereign Edge) |
| Exact Safetensors Parameter Count | 28,520,370 parameters (108.95 MB in model.safetensors, 1,331 tensors) |
| Active Parameters / Token | ~6.2M Active / Token (Edge Scale) | ~100M Active / Token (0.91B Full Scale) |
| Native Ternary GGUF Binary | 5.85 MB (model-TQ1_0.gguf — BitNet b1.58 Ternary TQ1_0 at 1.58 bits/weight, 1,331 tensors) |
| Measured Inference Throughput | 378.5 tokens/sec (42.27 ms step latency on Tesla T4) |
| Continuous Latent Phase Space | 768-D Coconut Continuous Latent Reasoning with explicit <think> and <latent_thought> scratchpads |
| Hamiltonian Latent Physics | Symplectic Störmer-Verlet Integrator ($\Delta E < 10^{-13}$ energy conservation bound) |
| Geometric Manifold Projection | Minkowski Lorentz Hyperboloid Embeddings + Langevin Stochastic Exploration |
| Hierarchical MoE Structure | 23 Macro-Engines × 4 Micro-Experts = 92 Sub-Experts per layer + Persistent Shared Foundation Expert |
⚡ Distinct Architectural Innovations (Unique to Hiraya)
768-Dimensional Coconut Continuous Latent Deliberation:
- Evolves continuous thought vectors inside
ℝ⁷⁶⁸(768-D) prior to discrete token emission, preventing premature verbal commitment on complex math and coding tasks.
- Evolves continuous thought vectors inside
Symplectic Störmer-Verlet Dynamics & Minkowski Hyperboloid Geometry:
- Preserves Hamiltonian phase-space volume across multi-hop reasoning steps: $$p_{t+1/2} = p_t - rac{\eta}{2} abla_q U(q_t), \quad q_{t+1} = q_t + \eta p_{t+1/2}, \quad p_{t+1} = p_{t+1/2} - rac{\eta}{2} abla_q U(q_{t+1})$$
- Projects hierarchical concepts onto the Lorentz hyperboloid (
-x_0² + ∑ x_i² = -1/K) for distortion-free tree embeddings.
Two-Tier 92-Expert H-MoE with Persistent Shared Foundation Expert:
- Every token activates the Persistent Shared Foundation Expert plus Top-K routed domain experts across 23 specialized Macro-Engines (1,331 total weight tensors).
🚀 Quickstart Usage
1. Ollama (Native TQ1_0 GGUF + Included Modelfile)
ollama create deepnarra-hiraya -f Modelfile
ollama run deepnarra-hiraya
2. Python SafeTensors Inspection & Loading
from safetensors.torch import load_file
from huggingface_hub import hf_hub_download
weights_path = hf_hub_download(repo_id="DeepNarra/Hiraya", filename="model.safetensors")
state_dict = load_file(weights_path)
print(f"Loaded {len(state_dict)} tensors ({sum(v.numel() for v in state_dict.values()):,} parameters)")
⚖️ License, Dataset Attributions & Responsible AI Compliance
1. Model License (Apache-2.0)
This repository, including all model weights (.safetensors and .gguf), configuration manifests, and custom architectural code, is licensed under the Apache License, Version 2.0 (http://www.apache.org/licenses/LICENSE-2.0). See the LICENSE and NOTICE files in the root of this repository for full legal terms.
2. Upstream Dataset & Open-Data Attributions (ODC-By-1.0 & Apache-2.0)
In strict compliance with open-data attribution requirements:
- HuggingFaceFW/fineweb-edu: Licensed under the Open Data Commons Attribution License (ODC-By) v1.0.
- CohereForAI/aya_collection: Licensed under the Apache License 2.0.
- m-a-p/CodeFeedback-Filtered-Instruction: Licensed under the Apache License 2.0.
- HuggingFaceH4/no_robots: Attributed under CC-BY-NC-4.0 for instruction-following research evaluation.
- SymPy CAS Procedural Reasoning Stream: Synthetically generated and formally verified via SymPy (BSD-3-Clause).
3. Intended Use, Safety & Limitations
- Intended Use: Research and development in continuous latent reasoning, speculative decoding, sub-quadratic recurrent memory, edge BitNet b1.58 GGUF deployment, and sandboxed autonomous agents.
- Safety & Execution Airlock: Code execution and tool-calling capabilities are designed to run strictly inside the DeepNarra Airlock Sandbox with AST static verification and SSRF network firewalling (
169.254.169.254and RFC-1918 private subnets blocked). - Limitations & Disclaimer: As an experimental sovereign architecture trained on compact compute budgets, outputs should be independently verified for high-stakes medical, legal, financial, or safety-critical systems. Provided
"AS IS"without warranties of any kind under Section 7 of the Apache 2.0 License.
- Downloads last month
- 374
Model tree for DeepNarra/Hiraya
Base model
DeepNarra/Hiraya-1-Base