Nemotron-H-8B-Base-8K

15.0K

52

8.0B

10 languages

—

by

nvidia

Language Model

OTHER

8B params

Fair

15K downloads

Community-tested

Try on Hugging Face Add to Compare

Edge AI:

Mobile

Laptop

Server

18GB+ RAM

Mobile

Laptop

Server

Quick Summary

NVIDIA Nemotron-H-8B-Base-8K is a large language model (LLM) developed by NVIDIA that is designed as a completion model for a given piece of text.

Device Compatibility

Mobile

4-6GB RAM

Laptop

16GB RAM

Server

GPU

Minimum Recommended

8GB+ RAM

Code Examples

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Model Versionpythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
tokenizer  = AutoTokenizer.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-H-8B-Base-8K", torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()

prompt = "When was NVIDIA founded?"

outputs = model.generate(**tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device))
print(tokenizer.decode(outputs[0]))

Deploy This Model

Production-ready deployment in minutes

Together.ai

Instant API access to this model

Fastest API

Production-ready inference API. Start free, scale to millions.

Replicate

One-click model deployment

Easiest Setup

Run models in the cloud with simple API. No DevOps required.

Disclosure: We may earn a commission from these partners. This helps keep LLMYourWay free.