Text Generation
Transformers
Safetensors
English
multilingual
deepnarra
hiraya
instruct
chat
agent
908m
0.9b
v1.0
14-horizons
h-moe
cua
mua
Instructions to use DeepNarra/Hiraya-1-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use DeepNarra/Hiraya-1-Instruct with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="DeepNarra/Hiraya-1-Instruct")# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("DeepNarra/Hiraya-1-Instruct", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use DeepNarra/Hiraya-1-Instruct with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "DeepNarra/Hiraya-1-Instruct" # 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-1-Instruct", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/DeepNarra/Hiraya-1-Instruct
- SGLang
How to use DeepNarra/Hiraya-1-Instruct 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-1-Instruct" \ --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-1-Instruct", "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-1-Instruct" \ --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-1-Instruct", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use DeepNarra/Hiraya-1-Instruct with Docker Model Runner:
docker model run hf.co/DeepNarra/Hiraya-1-Instruct
Download config.json from DeepNarra/Hiraya-1-Instruct: direct link, hf CLI and curl.
- Browser
- Download file 1.55 kB
-
https://huggingface.co/DeepNarra/Hiraya-1-Instruct/resolve/main/config.json
- Command line
-
hf download hf://DeepNarra/Hiraya-1-Instruct/config.json
-
curl -L -o config.json https://huggingface.co/DeepNarra/Hiraya-1-Instruct/resolve/main/config.json
1.55 kB
| { | |
| "architecture": "H-MoE-Zamba2-92-Expert-Nested-Hierarchical", | |
| "macro_engines": 23, | |
| "micro_experts_per_macro": 4, | |
| "total_sub_experts": 92, | |
| "vocab_size": 32004, | |
| "d_model": 512, | |
| "num_layers": 4, | |
| "total_breakthroughs": 87, | |
| "total_training_iterations": 250, | |
| "total_seen_fingerprints": 227, | |
| "omniversal_super_agent_14_horizons": true, | |
| "curated_domains": [ | |
| "1. English Fluency (FineWeb-Edu & Tulu-3)", | |
| "2. All Code & Algorithms (StarCoder2 / Stack v2 & SmolLM Python-Edu)", | |
| "3. Deep Multi-Step Reasoning (Open-R1, Fable-5.1 & GSM8K)", | |
| "4. Agentic Tool Calling & JSON (No-Robots & Tulu-3)", | |
| "5. Visual & Document Perception (LLaVA-Instruct)", | |
| "6. Strict Constraints & Discipline (No-Robots / IFEval)", | |
| "7. Long-Context Working Memory (Tulu-3 & FineWeb)", | |
| "8. Hard Sciences & Medicine (SciQ & PubMedQA)", | |
| "9. Global Multilingual Polyglot (Tulu-3 Polyglot 65+ Languages)", | |
| "10. Cybersecurity & Secure Coding (CodeFeedback Vulnerability Auditing)", | |
| "11. Finance, Law & Contracts (FinQA & LegalBench)", | |
| "12. Creative Writing & Emotional Nuance (UltraChat-200k)", | |
| "13. Computer-Using Agent CUA (NoRobots & ScreenSpot)", | |
| "14. Mobile-Using Agent MUA (NoRobots & Mobile Actions & Auto-UI)" | |
| ], | |
| "pre_gpu_deduplication_filter": true, | |
| "doremi_auto_curriculum": true, | |
| "adaptive_loss_gate_ohem": true, | |
| "focal_loss_scaling": true, | |
| "moe_aux_loss_free_balancing": true, | |
| "sophia_2nd_order_optimizer": true, | |
| "dual_gpu_acceleration": false, | |
| "soft_stop_executed_safely": true | |
| } |