Qwen3-Nemotron-32B-RLBFF-AWQ-8bit

Name: Qwen3-Nemotron-32B-RLBFF-AWQ-8bit
Author: cyankiwi

32.0B

1 language

—

cyankiwi

Language Model

OTHER

32B params

New

22 downloads

Early-stage

Try on Hugging Face Add to Compare

Edge AI:

Mobile

Laptop

Server

72GB+ RAM

Mobile

Laptop

Server

Quick Summary

- Quantization Method: AWQ - Bits: 8 - Group Size: 32 - Calibration Dataset: nvidia/Llama-Nemotron-Post-Training-Dataset - Quantization Tool: llm-compressor Qw...

Device Compatibility

Mobile

4-6GB RAM

Laptop

16GB RAM

Server

GPU

Minimum Recommended

30GB+ RAM

Code Examples

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

pythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "nvidia/Qwen3-Nemotron-32B-RLBFF"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r are there in strawberry?"

messages = [{'role': "user", "content": prompt}]

tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)

response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=16000, return_dict_in_generate=True, output_scores=True)

response = tokenizer.decode(response_token_ids.sequences[0].tolist())

print(response)

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.

Try Free API

Replicate

One-click model deployment

Easiest Setup

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

Deploy Now

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