XVERSE-13B

364

120

13.0B

license:apache-2.0

by

xverse

Language Model

OTHER

13B params

New

364 downloads

Early-stage

Try on Hugging Face Add to Compare

Edge AI:

Mobile

Laptop

Server

30GB+ RAM

Mobile

Laptop

Server

Quick Summary

AI model with specialized capabilities.

Device Compatibility

Mobile

4-6GB RAM

Laptop

16GB RAM

Server

GPU

Minimum Recommended

13GB+ RAM

Code Examples

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Loading with Transformerspythontransformers

>>> import torch
>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> tokenizer = AutoTokenizer.from_pretrained("xverse/XVERSE-13B")
>>> model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B", trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
>>> model = model.eval()
>>> inputs = tokenizer('北京的景点：故宫、天坛、万里长城等。\n深圳的景点：', return_tensors='pt').input_ids
>>> inputs = inputs.cuda()
>>> generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer.eos_token_id, repetition_penalty=1.1)
>>> print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))

Deploy This Model

Production-ready deployment in minutes

Together.ai

Instant API access to this model

Fastest API

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

Replicate

One-click model deployment

Easiest Setup

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

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