XVERSE-7B-Chat

8.4K

9

7.0B

license:apache-2.0

by

xverse

Language Model

OTHER

7B params

New

8K downloads

Early-stage

Try on Hugging Face Add to Compare

Edge AI:

Mobile

Laptop

Server

16GB+ RAM

Mobile

Laptop

Server

Quick Summary

XVERSE-7B 是由深圳元象科技自主研发的支持多语言的大语言模型（Large Language Model），参数规模为 70 亿，主要特点如下： - 模型结构：XVERSE-7B 使用主流 Decoder-only 的标准 Transformer 网络结构，支持 8K 的上下文长度（Context Length...

Device Compatibility

Mobile

4-6GB RAM

Laptop

16GB RAM

Server

GPU

Minimum Recommended

7GB+ RAM

Code Examples

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Loading with Transformerspythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation.utils import GenerationConfig
model_path = "xverse/XVERSE-7B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='auto')
model.generation_config = GenerationConfig.from_pretrained(model_path)
model = model.eval()
history = [{"role": "user", "content": "1955年谁是美国总统？他是什么党派？"}]
response = model.chat(tokenizer, history)
print(response)
history.append({"role": "assistant", "content": response})
history.append({"role": "user", "content": "他任职了多少年"})
response = model.chat(tokenizer, history)
print(response)

Deploy This Model

Production-ready deployment in minutes

Together.ai

Instant API access to this model

Fastest API

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

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.