GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
sainikhiljuluri2015
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
sainikhiljuluri2015
Model Tree
nvidia/Nemotron-Orchestrator-8B
Input Modalities
Output Modalities
Supported Functionality
This model was trained on ~50,000 cybersecurity instruction-response pairs from:
| Parameter | Value |
|---|---|
| Base Model | nvidia/Orchestrator-8B |
| Training Framework | NVIDIA NeMo Orchestrator |
| Training Samples | ~50,000 |
| Epochs | 2 |
| LoRA Rank | 16 |
| LoRA Alpha | 32 |
| Learning Rate | 2e-4 |
| Max Sequence Length | 1024 |
python
from transformers import AutoModelForCausalLM, AutoTokenizerimport torch model = AutoModelForCausalLM.from_pretrained( "sainikhiljuluri2015/NVIDIA-Orchestrator-Cybersecurity-8B-Merged", torch_dtype=torch.bfloat16, device_map="auto", trust_remote_code=True)tokenizer = AutoTokenizer.from_pretrained("sainikhiljuluri2015/NVIDIA-Orchestrator-Cybersecurity-8B-Merged", trust_remote_code=True) prompt = "What are the indicators of a ransomware attack?"inputs = tokenizer(prompt, return_tensors="pt").to(model.device)outputs = model.generate(**inputs, max_new_tokens=256, temperature=0.7)print(tokenizer.decode(outputs[0], skip_special_tokens=True))python
import requests API_URL = "https://YOUR_ENDPOINT_URL/v1/chat/completions" response = requests.post(API_URL, json={ "model": "sainikhiljuluri2015/NVIDIA-Orchestrator-Cybersecurity-8B-Merged", "messages": [{"role": "user", "content": "What is SQL injection?"}], "max_tokens": 300})print(response.json()["choices"][0]["message"]["content"])from transformers import AutoModelForCausalLM, AutoTokenizerimport torch model = AutoModelForCausalLM.from_pretrained( "sainikhiljuluri2015/NVIDIA-Orchestrator-Cybersecurity-8B-Merged", torch_dtype=torch.bfloat16, device_map="auto", trust_remote_code=True)tokenizer = AutoTokenizer.from_pretrained("sainikhiljuluri2015/NVIDIA-Orchestrator-Cybersecurity-8B-Merged", trust_remote_code=True) prompt = "What are the indicators of a ransomware attack?"inputs = tokenizer(prompt, return_tensors="pt").to(model.device)outputs = model.generate(**inputs, max_new_tokens=256, temperature=0.7)print(tokenizer.decode(outputs[0], skip_special_tokens=True))import requests API_URL = "https://YOUR_ENDPOINT_URL/v1/chat/completions" response = requests.post(API_URL, json={ "model": "sainikhiljuluri2015/NVIDIA-Orchestrator-Cybersecurity-8B-Merged", "messages": [{"role": "user", "content": "What is SQL injection?"}], "max_tokens": 300})print(response.json()["choices"][0]["message"]["content"])