internlm-xcomposer2d5-7b-chat

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
ckpt_path = "internlm/internlm-xcomposer2d5-7b-chat"
tokenizer = AutoTokenizer.from_pretrained(ckpt_path, trust_remote_code=True).cuda()
# Set `torch_dtype=torch.floatb16` to load model in bfloat16, otherwise it will be loaded as float32 and might cause OOM Error.
model = AutoModelForCausalLM.from_pretrained(ckpt_path, torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()
model = model.eval()

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
ckpt_path = "internlm/internlm-xcomposer2d5-7b-chat"
tokenizer = AutoTokenizer.from_pretrained(ckpt_path, trust_remote_code=True).cuda()
# Set `torch_dtype=torch.floatb16` to load model in bfloat16, otherwise it will be loaded as float32 and might cause OOM Error.
model = AutoModelForCausalLM.from_pretrained(ckpt_path, torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()
model = model.eval()

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
ckpt_path = "internlm/internlm-xcomposer2d5-7b-chat"
tokenizer = AutoTokenizer.from_pretrained(ckpt_path, trust_remote_code=True).cuda()
# Set `torch_dtype=torch.floatb16` to load model in bfloat16, otherwise it will be loaded as float32 and might cause OOM Error.
model = AutoModelForCausalLM.from_pretrained(ckpt_path, torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()
model = model.eval()

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
ckpt_path = "internlm/internlm-xcomposer2d5-7b-chat"
tokenizer = AutoTokenizer.from_pretrained(ckpt_path, trust_remote_code=True).cuda()
# Set `torch_dtype=torch.floatb16` to load model in bfloat16, otherwise it will be loaded as float32 and might cause OOM Error.
model = AutoModelForCausalLM.from_pretrained(ckpt_path, torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()
model = model.eval()

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
ckpt_path = "internlm/internlm-xcomposer2d5-7b-chat"
tokenizer = AutoTokenizer.from_pretrained(ckpt_path, trust_remote_code=True).cuda()
# Set `torch_dtype=torch.floatb16` to load model in bfloat16, otherwise it will be loaded as float32 and might cause OOM Error.
model = AutoModelForCausalLM.from_pretrained(ckpt_path, torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()
model = model.eval()

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
ckpt_path = "internlm/internlm-xcomposer2d5-7b-chat"
tokenizer = AutoTokenizer.from_pretrained(ckpt_path, trust_remote_code=True).cuda()
# Set `torch_dtype=torch.floatb16` to load model in bfloat16, otherwise it will be loaded as float32 and might cause OOM Error.
model = AutoModelForCausalLM.from_pretrained(ckpt_path, torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()
model = model.eval()

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
ckpt_path = "internlm/internlm-xcomposer2d5-7b-chat"
tokenizer = AutoTokenizer.from_pretrained(ckpt_path, trust_remote_code=True).cuda()
# Set `torch_dtype=torch.floatb16` to load model in bfloat16, otherwise it will be loaded as float32 and might cause OOM Error.
model = AutoModelForCausalLM.from_pretrained(ckpt_path, torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()
model = model.eval()

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
ckpt_path = "internlm/internlm-xcomposer2d5-7b-chat"
tokenizer = AutoTokenizer.from_pretrained(ckpt_path, trust_remote_code=True).cuda()
# Set `torch_dtype=torch.floatb16` to load model in bfloat16, otherwise it will be loaded as float32 and might cause OOM Error.
model = AutoModelForCausalLM.from_pretrained(ckpt_path, torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()
model = model.eval()

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
ckpt_path = "internlm/internlm-xcomposer2d5-7b-chat"
tokenizer = AutoTokenizer.from_pretrained(ckpt_path, trust_remote_code=True).cuda()
# Set `torch_dtype=torch.floatb16` to load model in bfloat16, otherwise it will be loaded as float32 and might cause OOM Error.
model = AutoModelForCausalLM.from_pretrained(ckpt_path, torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()
model = model.eval()

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
ckpt_path = "internlm/internlm-xcomposer2d5-7b-chat"
tokenizer = AutoTokenizer.from_pretrained(ckpt_path, trust_remote_code=True).cuda()
# Set `torch_dtype=torch.floatb16` to load model in bfloat16, otherwise it will be loaded as float32 and might cause OOM Error.
model = AutoModelForCausalLM.from_pretrained(ckpt_path, torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()
model = model.eval()

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
ckpt_path = "internlm/internlm-xcomposer2d5-7b-chat"
tokenizer = AutoTokenizer.from_pretrained(ckpt_path, trust_remote_code=True).cuda()
# Set `torch_dtype=torch.floatb16` to load model in bfloat16, otherwise it will be loaded as float32 and might cause OOM Error.
model = AutoModelForCausalLM.from_pretrained(ckpt_path, torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()
model = model.eval()

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
ckpt_path = "internlm/internlm-xcomposer2d5-7b-chat"
tokenizer = AutoTokenizer.from_pretrained(ckpt_path, trust_remote_code=True).cuda()
# Set `torch_dtype=torch.floatb16` to load model in bfloat16, otherwise it will be loaded as float32 and might cause OOM Error.
model = AutoModelForCausalLM.from_pretrained(ckpt_path, torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()
model = model.eval()

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
ckpt_path = "internlm/internlm-xcomposer2d5-7b-chat"
tokenizer = AutoTokenizer.from_pretrained(ckpt_path, trust_remote_code=True).cuda()
# Set `torch_dtype=torch.floatb16` to load model in bfloat16, otherwise it will be loaded as float32 and might cause OOM Error.
model = AutoModelForCausalLM.from_pretrained(ckpt_path, torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()
model = model.eval()

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
ckpt_path = "internlm/internlm-xcomposer2d5-7b-chat"
tokenizer = AutoTokenizer.from_pretrained(ckpt_path, trust_remote_code=True).cuda()
# Set `torch_dtype=torch.floatb16` to load model in bfloat16, otherwise it will be loaded as float32 and might cause OOM Error.
model = AutoModelForCausalLM.from_pretrained(ckpt_path, torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()
model = model.eval()

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
ckpt_path = "internlm/internlm-xcomposer2d5-7b-chat"
tokenizer = AutoTokenizer.from_pretrained(ckpt_path, trust_remote_code=True).cuda()
# Set `torch_dtype=torch.floatb16` to load model in bfloat16, otherwise it will be loaded as float32 and might cause OOM Error.
model = AutoModelForCausalLM.from_pretrained(ckpt_path, torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()
model = model.eval()

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
ckpt_path = "internlm/internlm-xcomposer2d5-7b-chat"
tokenizer = AutoTokenizer.from_pretrained(ckpt_path, trust_remote_code=True).cuda()
# Set `torch_dtype=torch.floatb16` to load model in bfloat16, otherwise it will be loaded as float32 and might cause OOM Error.
model = AutoModelForCausalLM.from_pretrained(ckpt_path, torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()
model = model.eval()

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
ckpt_path = "internlm/internlm-xcomposer2d5-7b-chat"
tokenizer = AutoTokenizer.from_pretrained(ckpt_path, trust_remote_code=True).cuda()
# Set `torch_dtype=torch.floatb16` to load model in bfloat16, otherwise it will be loaded as float32 and might cause OOM Error.
model = AutoModelForCausalLM.from_pretrained(ckpt_path, torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()
model = model.eval()

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
ckpt_path = "internlm/internlm-xcomposer2d5-7b-chat"
tokenizer = AutoTokenizer.from_pretrained(ckpt_path, trust_remote_code=True).cuda()
# Set `torch_dtype=torch.floatb16` to load model in bfloat16, otherwise it will be loaded as float32 and might cause OOM Error.
model = AutoModelForCausalLM.from_pretrained(ckpt_path, torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()
model = model.eval()

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
ckpt_path = "internlm/internlm-xcomposer2d5-7b-chat"
tokenizer = AutoTokenizer.from_pretrained(ckpt_path, trust_remote_code=True).cuda()
# Set `torch_dtype=torch.floatb16` to load model in bfloat16, otherwise it will be loaded as float32 and might cause OOM Error.
model = AutoModelForCausalLM.from_pretrained(ckpt_path, torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()
model = model.eval()

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
ckpt_path = "internlm/internlm-xcomposer2d5-7b-chat"
tokenizer = AutoTokenizer.from_pretrained(ckpt_path, trust_remote_code=True).cuda()
# Set `torch_dtype=torch.floatb16` to load model in bfloat16, otherwise it will be loaded as float32 and might cause OOM Error.
model = AutoModelForCausalLM.from_pretrained(ckpt_path, torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()
model = model.eval()

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
ckpt_path = "internlm/internlm-xcomposer2d5-7b-chat"
tokenizer = AutoTokenizer.from_pretrained(ckpt_path, trust_remote_code=True).cuda()
# Set `torch_dtype=torch.floatb16` to load model in bfloat16, otherwise it will be loaded as float32 and might cause OOM Error.
model = AutoModelForCausalLM.from_pretrained(ckpt_path, torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()
model = model.eval()

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
ckpt_path = "internlm/internlm-xcomposer2d5-7b-chat"
tokenizer = AutoTokenizer.from_pretrained(ckpt_path, trust_remote_code=True).cuda()
# Set `torch_dtype=torch.floatb16` to load model in bfloat16, otherwise it will be loaded as float32 and might cause OOM Error.
model = AutoModelForCausalLM.from_pretrained(ckpt_path, torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()
model = model.eval()

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
ckpt_path = "internlm/internlm-xcomposer2d5-7b-chat"
tokenizer = AutoTokenizer.from_pretrained(ckpt_path, trust_remote_code=True).cuda()
# Set `torch_dtype=torch.floatb16` to load model in bfloat16, otherwise it will be loaded as float32 and might cause OOM Error.
model = AutoModelForCausalLM.from_pretrained(ckpt_path, torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()
model = model.eval()

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
ckpt_path = "internlm/internlm-xcomposer2d5-7b-chat"
tokenizer = AutoTokenizer.from_pretrained(ckpt_path, trust_remote_code=True).cuda()
# Set `torch_dtype=torch.floatb16` to load model in bfloat16, otherwise it will be loaded as float32 and might cause OOM Error.
model = AutoModelForCausalLM.from_pretrained(ckpt_path, torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()
model = model.eval()

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
ckpt_path = "internlm/internlm-xcomposer2d5-7b-chat"
tokenizer = AutoTokenizer.from_pretrained(ckpt_path, trust_remote_code=True).cuda()
# Set `torch_dtype=torch.floatb16` to load model in bfloat16, otherwise it will be loaded as float32 and might cause OOM Error.
model = AutoModelForCausalLM.from_pretrained(ckpt_path, torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()
model = model.eval()

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
ckpt_path = "internlm/internlm-xcomposer2d5-7b-chat"
tokenizer = AutoTokenizer.from_pretrained(ckpt_path, trust_remote_code=True).cuda()
# Set `torch_dtype=torch.floatb16` to load model in bfloat16, otherwise it will be loaded as float32 and might cause OOM Error.
model = AutoModelForCausalLM.from_pretrained(ckpt_path, torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()
model = model.eval()

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
ckpt_path = "internlm/internlm-xcomposer2d5-7b-chat"
tokenizer = AutoTokenizer.from_pretrained(ckpt_path, trust_remote_code=True).cuda()
# Set `torch_dtype=torch.floatb16` to load model in bfloat16, otherwise it will be loaded as float32 and might cause OOM Error.
model = AutoModelForCausalLM.from_pretrained(ckpt_path, torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()
model = model.eval()

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
ckpt_path = "internlm/internlm-xcomposer2d5-7b-chat"
tokenizer = AutoTokenizer.from_pretrained(ckpt_path, trust_remote_code=True).cuda()
# Set `torch_dtype=torch.floatb16` to load model in bfloat16, otherwise it will be loaded as float32 and might cause OOM Error.
model = AutoModelForCausalLM.from_pretrained(ckpt_path, torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()
model = model.eval()

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
ckpt_path = "internlm/internlm-xcomposer2d5-7b-chat"
tokenizer = AutoTokenizer.from_pretrained(ckpt_path, trust_remote_code=True).cuda()
# Set `torch_dtype=torch.floatb16` to load model in bfloat16, otherwise it will be loaded as float32 and might cause OOM Error.
model = AutoModelForCausalLM.from_pretrained(ckpt_path, torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()
model = model.eval()

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
ckpt_path = "internlm/internlm-xcomposer2d5-7b-chat"
tokenizer = AutoTokenizer.from_pretrained(ckpt_path, trust_remote_code=True).cuda()
# Set `torch_dtype=torch.floatb16` to load model in bfloat16, otherwise it will be loaded as float32 and might cause OOM Error.
model = AutoModelForCausalLM.from_pretrained(ckpt_path, torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()
model = model.eval()

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
ckpt_path = "internlm/internlm-xcomposer2d5-7b-chat"
tokenizer = AutoTokenizer.from_pretrained(ckpt_path, trust_remote_code=True).cuda()
# Set `torch_dtype=torch.floatb16` to load model in bfloat16, otherwise it will be loaded as float32 and might cause OOM Error.
model = AutoModelForCausalLM.from_pretrained(ckpt_path, torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()
model = model.eval()

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
ckpt_path = "internlm/internlm-xcomposer2d5-7b-chat"
tokenizer = AutoTokenizer.from_pretrained(ckpt_path, trust_remote_code=True).cuda()
# Set `torch_dtype=torch.floatb16` to load model in bfloat16, otherwise it will be loaded as float32 and might cause OOM Error.
model = AutoModelForCausalLM.from_pretrained(ckpt_path, torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()
model = model.eval()

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
ckpt_path = "internlm/internlm-xcomposer2d5-7b-chat"
tokenizer = AutoTokenizer.from_pretrained(ckpt_path, trust_remote_code=True).cuda()
# Set `torch_dtype=torch.floatb16` to load model in bfloat16, otherwise it will be loaded as float32 and might cause OOM Error.
model = AutoModelForCausalLM.from_pretrained(ckpt_path, torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()
model = model.eval()

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
ckpt_path = "internlm/internlm-xcomposer2d5-7b-chat"
tokenizer = AutoTokenizer.from_pretrained(ckpt_path, trust_remote_code=True).cuda()
# Set `torch_dtype=torch.floatb16` to load model in bfloat16, otherwise it will be loaded as float32 and might cause OOM Error.
model = AutoModelForCausalLM.from_pretrained(ckpt_path, torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()
model = model.eval()

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
ckpt_path = "internlm/internlm-xcomposer2d5-7b-chat"
tokenizer = AutoTokenizer.from_pretrained(ckpt_path, trust_remote_code=True).cuda()
# Set `torch_dtype=torch.floatb16` to load model in bfloat16, otherwise it will be loaded as float32 and might cause OOM Error.
model = AutoModelForCausalLM.from_pretrained(ckpt_path, torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()
model = model.eval()

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
ckpt_path = "internlm/internlm-xcomposer2d5-7b-chat"
tokenizer = AutoTokenizer.from_pretrained(ckpt_path, trust_remote_code=True).cuda()
# Set `torch_dtype=torch.floatb16` to load model in bfloat16, otherwise it will be loaded as float32 and might cause OOM Error.
model = AutoModelForCausalLM.from_pretrained(ckpt_path, torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()
model = model.eval()

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
ckpt_path = "internlm/internlm-xcomposer2d5-7b-chat"
tokenizer = AutoTokenizer.from_pretrained(ckpt_path, trust_remote_code=True).cuda()
# Set `torch_dtype=torch.floatb16` to load model in bfloat16, otherwise it will be loaded as float32 and might cause OOM Error.
model = AutoModelForCausalLM.from_pretrained(ckpt_path, torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()
model = model.eval()

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
ckpt_path = "internlm/internlm-xcomposer2d5-7b-chat"
tokenizer = AutoTokenizer.from_pretrained(ckpt_path, trust_remote_code=True).cuda()
# Set `torch_dtype=torch.floatb16` to load model in bfloat16, otherwise it will be loaded as float32 and might cause OOM Error.
model = AutoModelForCausalLM.from_pretrained(ckpt_path, torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()
model = model.eval()

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
ckpt_path = "internlm/internlm-xcomposer2d5-7b-chat"
tokenizer = AutoTokenizer.from_pretrained(ckpt_path, trust_remote_code=True).cuda()
# Set `torch_dtype=torch.floatb16` to load model in bfloat16, otherwise it will be loaded as float32 and might cause OOM Error.
model = AutoModelForCausalLM.from_pretrained(ckpt_path, torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()
model = model.eval()

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
ckpt_path = "internlm/internlm-xcomposer2d5-7b-chat"
tokenizer = AutoTokenizer.from_pretrained(ckpt_path, trust_remote_code=True).cuda()
# Set `torch_dtype=torch.floatb16` to load model in bfloat16, otherwise it will be loaded as float32 and might cause OOM Error.
model = AutoModelForCausalLM.from_pretrained(ckpt_path, torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()
model = model.eval()

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
ckpt_path = "internlm/internlm-xcomposer2d5-7b-chat"
tokenizer = AutoTokenizer.from_pretrained(ckpt_path, trust_remote_code=True).cuda()
# Set `torch_dtype=torch.floatb16` to load model in bfloat16, otherwise it will be loaded as float32 and might cause OOM Error.
model = AutoModelForCausalLM.from_pretrained(ckpt_path, torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()
model = model.eval()

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
ckpt_path = "internlm/internlm-xcomposer2d5-7b-chat"
tokenizer = AutoTokenizer.from_pretrained(ckpt_path, trust_remote_code=True).cuda()
# Set `torch_dtype=torch.floatb16` to load model in bfloat16, otherwise it will be loaded as float32 and might cause OOM Error.
model = AutoModelForCausalLM.from_pretrained(ckpt_path, torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()
model = model.eval()

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
ckpt_path = "internlm/internlm-xcomposer2d5-7b-chat"
tokenizer = AutoTokenizer.from_pretrained(ckpt_path, trust_remote_code=True).cuda()
# Set `torch_dtype=torch.floatb16` to load model in bfloat16, otherwise it will be loaded as float32 and might cause OOM Error.
model = AutoModelForCausalLM.from_pretrained(ckpt_path, torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()
model = model.eval()

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
ckpt_path = "internlm/internlm-xcomposer2d5-7b-chat"
tokenizer = AutoTokenizer.from_pretrained(ckpt_path, trust_remote_code=True).cuda()
# Set `torch_dtype=torch.floatb16` to load model in bfloat16, otherwise it will be loaded as float32 and might cause OOM Error.
model = AutoModelForCausalLM.from_pretrained(ckpt_path, torch_dtype=torch.bfloat16, trust_remote_code=True).cuda()
model = model.eval()

import torch
from transformers import AutoModel, AutoTokenizer

torch.set_grad_enabled(False)

# init model and tokenizer
model = AutoModel.from_pretrained('internlm/internlm-xcomposer2d5-7b-chat', torch_dtype=torch.bfloat16, trust_remote_code=True).cuda().eval()
tokenizer = AutoTokenizer.from_pretrained('internlm/internlm-xcomposer2d5-7b-chat', trust_remote_code=True)
model.tokenizer = tokenizer

query = 'Here are some frames of a video. Describe this video in detail'
image = ['./examples/liuxiang.mp4',]
with torch.autocast(device_type='cuda', dtype=torch.float16):
    response, his = model.chat(tokenizer, query, image, do_sample=False, num_beams=3, use_meta=True)
print(response)
# The video begins with a man in a red and yellow uniform standing on the starting line of a track, preparing to compete in the 110-meter hurdles at the Athens 2004 Olympic Games. He is identified as Liu Xiang, a Chinese athlete, and his bib number is 1363. The scene is set in a stadium filled with spectators, indicating the significance of the event.
# As the race begins, all the athletes start running, but Liu Xiang quickly takes the lead. However, he encounters a hurdle and knocks it over. Despite this setback, he quickly recovers and continues to run. The race is intense, with athletes from various countries competing fiercely. In the end, Liu Xiang emerges as the winner with a time of 12.91 seconds, securing the gold medal for China.
# The video then transitions to a slow-motion replay of the race, focusing on Liu Xiang's performance and the knockdown of the hurdle. This allows viewers to appreciate the skill and determination of the athlete.
# Following the race, Liu Xiang is seen lying on the track, possibly exhausted from the intense competition. He then stands up and begins to celebrate his victory, waving his arms in the air and running around the track. The crowd cheers and celebrates with him, creating a joyful atmosphere.
# The video concludes with a replay of Liu Xiang's gold medal-winning moment, emphasizing the significance of his achievement at the Athens 2004 Olympic Games.
# Throughout the video, the Olympic logo is prominently displayed, reminding viewers of the global significance of the event and the athletes' dedication and perseverance in their pursuit of victory.

query = 'tell me the athlete code of Liu Xiang'
image = ['./examples/liuxiang.mp4',]
with torch.autocast(device_type='cuda', dtype=torch.float16):
    response, _ = model.chat(tokenizer, query, image, history=his, do_sample=False, num_beams=3, use_meta=True)
print(response)
# The athlete code of Liu Xiang is 1363.

import torch
from transformers import AutoModel, AutoTokenizer

torch.set_grad_enabled(False)

# init model and tokenizer
model = AutoModel.from_pretrained('internlm/internlm-xcomposer2d5-7b-chat', torch_dtype=torch.bfloat16, trust_remote_code=True).cuda().eval()
tokenizer = AutoTokenizer.from_pretrained('internlm/internlm-xcomposer2d5-7b-chat', trust_remote_code=True)
model.tokenizer = tokenizer

query = 'Here are some frames of a video. Describe this video in detail'
image = ['./examples/liuxiang.mp4',]
with torch.autocast(device_type='cuda', dtype=torch.float16):
    response, his = model.chat(tokenizer, query, image, do_sample=False, num_beams=3, use_meta=True)
print(response)
# The video begins with a man in a red and yellow uniform standing on the starting line of a track, preparing to compete in the 110-meter hurdles at the Athens 2004 Olympic Games. He is identified as Liu Xiang, a Chinese athlete, and his bib number is 1363. The scene is set in a stadium filled with spectators, indicating the significance of the event.
# As the race begins, all the athletes start running, but Liu Xiang quickly takes the lead. However, he encounters a hurdle and knocks it over. Despite this setback, he quickly recovers and continues to run. The race is intense, with athletes from various countries competing fiercely. In the end, Liu Xiang emerges as the winner with a time of 12.91 seconds, securing the gold medal for China.
# The video then transitions to a slow-motion replay of the race, focusing on Liu Xiang's performance and the knockdown of the hurdle. This allows viewers to appreciate the skill and determination of the athlete.
# Following the race, Liu Xiang is seen lying on the track, possibly exhausted from the intense competition. He then stands up and begins to celebrate his victory, waving his arms in the air and running around the track. The crowd cheers and celebrates with him, creating a joyful atmosphere.
# The video concludes with a replay of Liu Xiang's gold medal-winning moment, emphasizing the significance of his achievement at the Athens 2004 Olympic Games.
# Throughout the video, the Olympic logo is prominently displayed, reminding viewers of the global significance of the event and the athletes' dedication and perseverance in their pursuit of victory.

query = 'tell me the athlete code of Liu Xiang'
image = ['./examples/liuxiang.mp4',]
with torch.autocast(device_type='cuda', dtype=torch.float16):
    response, _ = model.chat(tokenizer, query, image, history=his, do_sample=False, num_beams=3, use_meta=True)
print(response)
# The athlete code of Liu Xiang is 1363.

import torch
from transformers import AutoModel, AutoTokenizer

torch.set_grad_enabled(False)

# init model and tokenizer
model = AutoModel.from_pretrained('internlm/internlm-xcomposer2d5-7b-chat', torch_dtype=torch.bfloat16, trust_remote_code=True).cuda().eval()
tokenizer = AutoTokenizer.from_pretrained('internlm/internlm-xcomposer2d5-7b-chat', trust_remote_code=True)
model.tokenizer = tokenizer

query = 'Here are some frames of a video. Describe this video in detail'
image = ['./examples/liuxiang.mp4',]
with torch.autocast(device_type='cuda', dtype=torch.float16):
    response, his = model.chat(tokenizer, query, image, do_sample=False, num_beams=3, use_meta=True)
print(response)
# The video begins with a man in a red and yellow uniform standing on the starting line of a track, preparing to compete in the 110-meter hurdles at the Athens 2004 Olympic Games. He is identified as Liu Xiang, a Chinese athlete, and his bib number is 1363. The scene is set in a stadium filled with spectators, indicating the significance of the event.
# As the race begins, all the athletes start running, but Liu Xiang quickly takes the lead. However, he encounters a hurdle and knocks it over. Despite this setback, he quickly recovers and continues to run. The race is intense, with athletes from various countries competing fiercely. In the end, Liu Xiang emerges as the winner with a time of 12.91 seconds, securing the gold medal for China.
# The video then transitions to a slow-motion replay of the race, focusing on Liu Xiang's performance and the knockdown of the hurdle. This allows viewers to appreciate the skill and determination of the athlete.
# Following the race, Liu Xiang is seen lying on the track, possibly exhausted from the intense competition. He then stands up and begins to celebrate his victory, waving his arms in the air and running around the track. The crowd cheers and celebrates with him, creating a joyful atmosphere.
# The video concludes with a replay of Liu Xiang's gold medal-winning moment, emphasizing the significance of his achievement at the Athens 2004 Olympic Games.
# Throughout the video, the Olympic logo is prominently displayed, reminding viewers of the global significance of the event and the athletes' dedication and perseverance in their pursuit of victory.

query = 'tell me the athlete code of Liu Xiang'
image = ['./examples/liuxiang.mp4',]
with torch.autocast(device_type='cuda', dtype=torch.float16):
    response, _ = model.chat(tokenizer, query, image, history=his, do_sample=False, num_beams=3, use_meta=True)
print(response)
# The athlete code of Liu Xiang is 1363.

import torch
from transformers import AutoModel, AutoTokenizer

torch.set_grad_enabled(False)

# init model and tokenizer
model = AutoModel.from_pretrained('internlm/internlm-xcomposer2d5-7b-chat', torch_dtype=torch.bfloat16, trust_remote_code=True).cuda().eval()
tokenizer = AutoTokenizer.from_pretrained('internlm/internlm-xcomposer2d5-7b-chat', trust_remote_code=True)
model.tokenizer = tokenizer

query = 'Here are some frames of a video. Describe this video in detail'
image = ['./examples/liuxiang.mp4',]
with torch.autocast(device_type='cuda', dtype=torch.float16):
    response, his = model.chat(tokenizer, query, image, do_sample=False, num_beams=3, use_meta=True)
print(response)
# The video begins with a man in a red and yellow uniform standing on the starting line of a track, preparing to compete in the 110-meter hurdles at the Athens 2004 Olympic Games. He is identified as Liu Xiang, a Chinese athlete, and his bib number is 1363. The scene is set in a stadium filled with spectators, indicating the significance of the event.
# As the race begins, all the athletes start running, but Liu Xiang quickly takes the lead. However, he encounters a hurdle and knocks it over. Despite this setback, he quickly recovers and continues to run. The race is intense, with athletes from various countries competing fiercely. In the end, Liu Xiang emerges as the winner with a time of 12.91 seconds, securing the gold medal for China.
# The video then transitions to a slow-motion replay of the race, focusing on Liu Xiang's performance and the knockdown of the hurdle. This allows viewers to appreciate the skill and determination of the athlete.
# Following the race, Liu Xiang is seen lying on the track, possibly exhausted from the intense competition. He then stands up and begins to celebrate his victory, waving his arms in the air and running around the track. The crowd cheers and celebrates with him, creating a joyful atmosphere.
# The video concludes with a replay of Liu Xiang's gold medal-winning moment, emphasizing the significance of his achievement at the Athens 2004 Olympic Games.
# Throughout the video, the Olympic logo is prominently displayed, reminding viewers of the global significance of the event and the athletes' dedication and perseverance in their pursuit of victory.

query = 'tell me the athlete code of Liu Xiang'
image = ['./examples/liuxiang.mp4',]
with torch.autocast(device_type='cuda', dtype=torch.float16):
    response, _ = model.chat(tokenizer, query, image, history=his, do_sample=False, num_beams=3, use_meta=True)
print(response)
# The athlete code of Liu Xiang is 1363.

import torch
from transformers import AutoModel, AutoTokenizer

torch.set_grad_enabled(False)

# init model and tokenizer
model = AutoModel.from_pretrained('internlm/internlm-xcomposer2d5-7b-chat', torch_dtype=torch.bfloat16, trust_remote_code=True).cuda().eval()
tokenizer = AutoTokenizer.from_pretrained('internlm/internlm-xcomposer2d5-7b-chat', trust_remote_code=True)
model.tokenizer = tokenizer

query = 'Here are some frames of a video. Describe this video in detail'
image = ['./examples/liuxiang.mp4',]
with torch.autocast(device_type='cuda', dtype=torch.float16):
    response, his = model.chat(tokenizer, query, image, do_sample=False, num_beams=3, use_meta=True)
print(response)
# The video begins with a man in a red and yellow uniform standing on the starting line of a track, preparing to compete in the 110-meter hurdles at the Athens 2004 Olympic Games. He is identified as Liu Xiang, a Chinese athlete, and his bib number is 1363. The scene is set in a stadium filled with spectators, indicating the significance of the event.
# As the race begins, all the athletes start running, but Liu Xiang quickly takes the lead. However, he encounters a hurdle and knocks it over. Despite this setback, he quickly recovers and continues to run. The race is intense, with athletes from various countries competing fiercely. In the end, Liu Xiang emerges as the winner with a time of 12.91 seconds, securing the gold medal for China.
# The video then transitions to a slow-motion replay of the race, focusing on Liu Xiang's performance and the knockdown of the hurdle. This allows viewers to appreciate the skill and determination of the athlete.
# Following the race, Liu Xiang is seen lying on the track, possibly exhausted from the intense competition. He then stands up and begins to celebrate his victory, waving his arms in the air and running around the track. The crowd cheers and celebrates with him, creating a joyful atmosphere.
# The video concludes with a replay of Liu Xiang's gold medal-winning moment, emphasizing the significance of his achievement at the Athens 2004 Olympic Games.
# Throughout the video, the Olympic logo is prominently displayed, reminding viewers of the global significance of the event and the athletes' dedication and perseverance in their pursuit of victory.

query = 'tell me the athlete code of Liu Xiang'
image = ['./examples/liuxiang.mp4',]
with torch.autocast(device_type='cuda', dtype=torch.float16):
    response, _ = model.chat(tokenizer, query, image, history=his, do_sample=False, num_beams=3, use_meta=True)
print(response)
# The athlete code of Liu Xiang is 1363.

import torch
from transformers import AutoModel, AutoTokenizer

torch.set_grad_enabled(False)

# init model and tokenizer
model = AutoModel.from_pretrained('internlm/internlm-xcomposer2d5-7b-chat', torch_dtype=torch.bfloat16, trust_remote_code=True).cuda().eval()
tokenizer = AutoTokenizer.from_pretrained('internlm/internlm-xcomposer2d5-7b-chat', trust_remote_code=True)
model.tokenizer = tokenizer

query = 'Here are some frames of a video. Describe this video in detail'
image = ['./examples/liuxiang.mp4',]
with torch.autocast(device_type='cuda', dtype=torch.float16):
    response, his = model.chat(tokenizer, query, image, do_sample=False, num_beams=3, use_meta=True)
print(response)
# The video begins with a man in a red and yellow uniform standing on the starting line of a track, preparing to compete in the 110-meter hurdles at the Athens 2004 Olympic Games. He is identified as Liu Xiang, a Chinese athlete, and his bib number is 1363. The scene is set in a stadium filled with spectators, indicating the significance of the event.
# As the race begins, all the athletes start running, but Liu Xiang quickly takes the lead. However, he encounters a hurdle and knocks it over. Despite this setback, he quickly recovers and continues to run. The race is intense, with athletes from various countries competing fiercely. In the end, Liu Xiang emerges as the winner with a time of 12.91 seconds, securing the gold medal for China.
# The video then transitions to a slow-motion replay of the race, focusing on Liu Xiang's performance and the knockdown of the hurdle. This allows viewers to appreciate the skill and determination of the athlete.
# Following the race, Liu Xiang is seen lying on the track, possibly exhausted from the intense competition. He then stands up and begins to celebrate his victory, waving his arms in the air and running around the track. The crowd cheers and celebrates with him, creating a joyful atmosphere.
# The video concludes with a replay of Liu Xiang's gold medal-winning moment, emphasizing the significance of his achievement at the Athens 2004 Olympic Games.
# Throughout the video, the Olympic logo is prominently displayed, reminding viewers of the global significance of the event and the athletes' dedication and perseverance in their pursuit of victory.

query = 'tell me the athlete code of Liu Xiang'
image = ['./examples/liuxiang.mp4',]
with torch.autocast(device_type='cuda', dtype=torch.float16):
    response, _ = model.chat(tokenizer, query, image, history=his, do_sample=False, num_beams=3, use_meta=True)
print(response)
# The athlete code of Liu Xiang is 1363.

import torch
from transformers import AutoModel, AutoTokenizer

torch.set_grad_enabled(False)

# init model and tokenizer
model = AutoModel.from_pretrained('internlm/internlm-xcomposer2d5-7b-chat', torch_dtype=torch.bfloat16, trust_remote_code=True).cuda().eval()
tokenizer = AutoTokenizer.from_pretrained('internlm/internlm-xcomposer2d5-7b-chat', trust_remote_code=True)
model.tokenizer = tokenizer

query = 'Here are some frames of a video. Describe this video in detail'
image = ['./examples/liuxiang.mp4',]
with torch.autocast(device_type='cuda', dtype=torch.float16):
    response, his = model.chat(tokenizer, query, image, do_sample=False, num_beams=3, use_meta=True)
print(response)
# The video begins with a man in a red and yellow uniform standing on the starting line of a track, preparing to compete in the 110-meter hurdles at the Athens 2004 Olympic Games. He is identified as Liu Xiang, a Chinese athlete, and his bib number is 1363. The scene is set in a stadium filled with spectators, indicating the significance of the event.
# As the race begins, all the athletes start running, but Liu Xiang quickly takes the lead. However, he encounters a hurdle and knocks it over. Despite this setback, he quickly recovers and continues to run. The race is intense, with athletes from various countries competing fiercely. In the end, Liu Xiang emerges as the winner with a time of 12.91 seconds, securing the gold medal for China.
# The video then transitions to a slow-motion replay of the race, focusing on Liu Xiang's performance and the knockdown of the hurdle. This allows viewers to appreciate the skill and determination of the athlete.
# Following the race, Liu Xiang is seen lying on the track, possibly exhausted from the intense competition. He then stands up and begins to celebrate his victory, waving his arms in the air and running around the track. The crowd cheers and celebrates with him, creating a joyful atmosphere.
# The video concludes with a replay of Liu Xiang's gold medal-winning moment, emphasizing the significance of his achievement at the Athens 2004 Olympic Games.
# Throughout the video, the Olympic logo is prominently displayed, reminding viewers of the global significance of the event and the athletes' dedication and perseverance in their pursuit of victory.

query = 'tell me the athlete code of Liu Xiang'
image = ['./examples/liuxiang.mp4',]
with torch.autocast(device_type='cuda', dtype=torch.float16):
    response, _ = model.chat(tokenizer, query, image, history=his, do_sample=False, num_beams=3, use_meta=True)
print(response)
# The athlete code of Liu Xiang is 1363.

import torch
from transformers import AutoModel, AutoTokenizer

torch.set_grad_enabled(False)

# init model and tokenizer
model = AutoModel.from_pretrained('internlm/internlm-xcomposer2d5-7b-chat', torch_dtype=torch.bfloat16, trust_remote_code=True).cuda().eval()
tokenizer = AutoTokenizer.from_pretrained('internlm/internlm-xcomposer2d5-7b-chat', trust_remote_code=True)
model.tokenizer = tokenizer

query = 'Here are some frames of a video. Describe this video in detail'
image = ['./examples/liuxiang.mp4',]
with torch.autocast(device_type='cuda', dtype=torch.float16):
    response, his = model.chat(tokenizer, query, image, do_sample=False, num_beams=3, use_meta=True)
print(response)
# The video begins with a man in a red and yellow uniform standing on the starting line of a track, preparing to compete in the 110-meter hurdles at the Athens 2004 Olympic Games. He is identified as Liu Xiang, a Chinese athlete, and his bib number is 1363. The scene is set in a stadium filled with spectators, indicating the significance of the event.
# As the race begins, all the athletes start running, but Liu Xiang quickly takes the lead. However, he encounters a hurdle and knocks it over. Despite this setback, he quickly recovers and continues to run. The race is intense, with athletes from various countries competing fiercely. In the end, Liu Xiang emerges as the winner with a time of 12.91 seconds, securing the gold medal for China.
# The video then transitions to a slow-motion replay of the race, focusing on Liu Xiang's performance and the knockdown of the hurdle. This allows viewers to appreciate the skill and determination of the athlete.
# Following the race, Liu Xiang is seen lying on the track, possibly exhausted from the intense competition. He then stands up and begins to celebrate his victory, waving his arms in the air and running around the track. The crowd cheers and celebrates with him, creating a joyful atmosphere.
# The video concludes with a replay of Liu Xiang's gold medal-winning moment, emphasizing the significance of his achievement at the Athens 2004 Olympic Games.
# Throughout the video, the Olympic logo is prominently displayed, reminding viewers of the global significance of the event and the athletes' dedication and perseverance in their pursuit of victory.

query = 'tell me the athlete code of Liu Xiang'
image = ['./examples/liuxiang.mp4',]
with torch.autocast(device_type='cuda', dtype=torch.float16):
    response, _ = model.chat(tokenizer, query, image, history=his, do_sample=False, num_beams=3, use_meta=True)
print(response)
# The athlete code of Liu Xiang is 1363.

import torch
from transformers import AutoModel, AutoTokenizer

torch.set_grad_enabled(False)

# init model and tokenizer
model = AutoModel.from_pretrained('internlm/internlm-xcomposer2d5-7b-chat', torch_dtype=torch.bfloat16, trust_remote_code=True).cuda().eval()
tokenizer = AutoTokenizer.from_pretrained('internlm/internlm-xcomposer2d5-7b-chat', trust_remote_code=True)
model.tokenizer = tokenizer

query = 'Here are some frames of a video. Describe this video in detail'
image = ['./examples/liuxiang.mp4',]
with torch.autocast(device_type='cuda', dtype=torch.float16):
    response, his = model.chat(tokenizer, query, image, do_sample=False, num_beams=3, use_meta=True)
print(response)
# The video begins with a man in a red and yellow uniform standing on the starting line of a track, preparing to compete in the 110-meter hurdles at the Athens 2004 Olympic Games. He is identified as Liu Xiang, a Chinese athlete, and his bib number is 1363. The scene is set in a stadium filled with spectators, indicating the significance of the event.
# As the race begins, all the athletes start running, but Liu Xiang quickly takes the lead. However, he encounters a hurdle and knocks it over. Despite this setback, he quickly recovers and continues to run. The race is intense, with athletes from various countries competing fiercely. In the end, Liu Xiang emerges as the winner with a time of 12.91 seconds, securing the gold medal for China.
# The video then transitions to a slow-motion replay of the race, focusing on Liu Xiang's performance and the knockdown of the hurdle. This allows viewers to appreciate the skill and determination of the athlete.
# Following the race, Liu Xiang is seen lying on the track, possibly exhausted from the intense competition. He then stands up and begins to celebrate his victory, waving his arms in the air and running around the track. The crowd cheers and celebrates with him, creating a joyful atmosphere.
# The video concludes with a replay of Liu Xiang's gold medal-winning moment, emphasizing the significance of his achievement at the Athens 2004 Olympic Games.
# Throughout the video, the Olympic logo is prominently displayed, reminding viewers of the global significance of the event and the athletes' dedication and perseverance in their pursuit of victory.

query = 'tell me the athlete code of Liu Xiang'
image = ['./examples/liuxiang.mp4',]
with torch.autocast(device_type='cuda', dtype=torch.float16):
    response, _ = model.chat(tokenizer, query, image, history=his, do_sample=False, num_beams=3, use_meta=True)
print(response)
# The athlete code of Liu Xiang is 1363.

import torch
from transformers import AutoModel, AutoTokenizer

torch.set_grad_enabled(False)

# init model and tokenizer
model = AutoModel.from_pretrained('internlm/internlm-xcomposer2d5-7b-chat', torch_dtype=torch.bfloat16, trust_remote_code=True).cuda().eval()
tokenizer = AutoTokenizer.from_pretrained('internlm/internlm-xcomposer2d5-7b-chat', trust_remote_code=True)
model.tokenizer = tokenizer

query = 'Here are some frames of a video. Describe this video in detail'
image = ['./examples/liuxiang.mp4',]
with torch.autocast(device_type='cuda', dtype=torch.float16):
    response, his = model.chat(tokenizer, query, image, do_sample=False, num_beams=3, use_meta=True)
print(response)
# The video begins with a man in a red and yellow uniform standing on the starting line of a track, preparing to compete in the 110-meter hurdles at the Athens 2004 Olympic Games. He is identified as Liu Xiang, a Chinese athlete, and his bib number is 1363. The scene is set in a stadium filled with spectators, indicating the significance of the event.
# As the race begins, all the athletes start running, but Liu Xiang quickly takes the lead. However, he encounters a hurdle and knocks it over. Despite this setback, he quickly recovers and continues to run. The race is intense, with athletes from various countries competing fiercely. In the end, Liu Xiang emerges as the winner with a time of 12.91 seconds, securing the gold medal for China.
# The video then transitions to a slow-motion replay of the race, focusing on Liu Xiang's performance and the knockdown of the hurdle. This allows viewers to appreciate the skill and determination of the athlete.
# Following the race, Liu Xiang is seen lying on the track, possibly exhausted from the intense competition. He then stands up and begins to celebrate his victory, waving his arms in the air and running around the track. The crowd cheers and celebrates with him, creating a joyful atmosphere.
# The video concludes with a replay of Liu Xiang's gold medal-winning moment, emphasizing the significance of his achievement at the Athens 2004 Olympic Games.
# Throughout the video, the Olympic logo is prominently displayed, reminding viewers of the global significance of the event and the athletes' dedication and perseverance in their pursuit of victory.

query = 'tell me the athlete code of Liu Xiang'
image = ['./examples/liuxiang.mp4',]
with torch.autocast(device_type='cuda', dtype=torch.float16):
    response, _ = model.chat(tokenizer, query, image, history=his, do_sample=False, num_beams=3, use_meta=True)
print(response)
# The athlete code of Liu Xiang is 1363.

import torch
from transformers import AutoModel, AutoTokenizer

torch.set_grad_enabled(False)

# init model and tokenizer
model = AutoModel.from_pretrained('internlm/internlm-xcomposer2d5-7b-chat', torch_dtype=torch.bfloat16, trust_remote_code=True).cuda().eval()
tokenizer = AutoTokenizer.from_pretrained('internlm/internlm-xcomposer2d5-7b-chat', trust_remote_code=True)
model.tokenizer = tokenizer

query = 'Here are some frames of a video. Describe this video in detail'
image = ['./examples/liuxiang.mp4',]
with torch.autocast(device_type='cuda', dtype=torch.float16):
    response, his = model.chat(tokenizer, query, image, do_sample=False, num_beams=3, use_meta=True)
print(response)
# The video begins with a man in a red and yellow uniform standing on the starting line of a track, preparing to compete in the 110-meter hurdles at the Athens 2004 Olympic Games. He is identified as Liu Xiang, a Chinese athlete, and his bib number is 1363. The scene is set in a stadium filled with spectators, indicating the significance of the event.
# As the race begins, all the athletes start running, but Liu Xiang quickly takes the lead. However, he encounters a hurdle and knocks it over. Despite this setback, he quickly recovers and continues to run. The race is intense, with athletes from various countries competing fiercely. In the end, Liu Xiang emerges as the winner with a time of 12.91 seconds, securing the gold medal for China.
# The video then transitions to a slow-motion replay of the race, focusing on Liu Xiang's performance and the knockdown of the hurdle. This allows viewers to appreciate the skill and determination of the athlete.
# Following the race, Liu Xiang is seen lying on the track, possibly exhausted from the intense competition. He then stands up and begins to celebrate his victory, waving his arms in the air and running around the track. The crowd cheers and celebrates with him, creating a joyful atmosphere.
# The video concludes with a replay of Liu Xiang's gold medal-winning moment, emphasizing the significance of his achievement at the Athens 2004 Olympic Games.
# Throughout the video, the Olympic logo is prominently displayed, reminding viewers of the global significance of the event and the athletes' dedication and perseverance in their pursuit of victory.

query = 'tell me the athlete code of Liu Xiang'
image = ['./examples/liuxiang.mp4',]
with torch.autocast(device_type='cuda', dtype=torch.float16):
    response, _ = model.chat(tokenizer, query, image, history=his, do_sample=False, num_beams=3, use_meta=True)
print(response)
# The athlete code of Liu Xiang is 1363.

import torch
from transformers import AutoModel, AutoTokenizer

torch.set_grad_enabled(False)

# init model and tokenizer
model = AutoModel.from_pretrained('internlm/internlm-xcomposer2d5-7b-chat', torch_dtype=torch.bfloat16, trust_remote_code=True).cuda().eval()
tokenizer = AutoTokenizer.from_pretrained('internlm/internlm-xcomposer2d5-7b-chat', trust_remote_code=True)
model.tokenizer = tokenizer

query = 'Here are some frames of a video. Describe this video in detail'
image = ['./examples/liuxiang.mp4',]
with torch.autocast(device_type='cuda', dtype=torch.float16):
    response, his = model.chat(tokenizer, query, image, do_sample=False, num_beams=3, use_meta=True)
print(response)
# The video begins with a man in a red and yellow uniform standing on the starting line of a track, preparing to compete in the 110-meter hurdles at the Athens 2004 Olympic Games. He is identified as Liu Xiang, a Chinese athlete, and his bib number is 1363. The scene is set in a stadium filled with spectators, indicating the significance of the event.
# As the race begins, all the athletes start running, but Liu Xiang quickly takes the lead. However, he encounters a hurdle and knocks it over. Despite this setback, he quickly recovers and continues to run. The race is intense, with athletes from various countries competing fiercely. In the end, Liu Xiang emerges as the winner with a time of 12.91 seconds, securing the gold medal for China.
# The video then transitions to a slow-motion replay of the race, focusing on Liu Xiang's performance and the knockdown of the hurdle. This allows viewers to appreciate the skill and determination of the athlete.
# Following the race, Liu Xiang is seen lying on the track, possibly exhausted from the intense competition. He then stands up and begins to celebrate his victory, waving his arms in the air and running around the track. The crowd cheers and celebrates with him, creating a joyful atmosphere.
# The video concludes with a replay of Liu Xiang's gold medal-winning moment, emphasizing the significance of his achievement at the Athens 2004 Olympic Games.
# Throughout the video, the Olympic logo is prominently displayed, reminding viewers of the global significance of the event and the athletes' dedication and perseverance in their pursuit of victory.

query = 'tell me the athlete code of Liu Xiang'
image = ['./examples/liuxiang.mp4',]
with torch.autocast(device_type='cuda', dtype=torch.float16):
    response, _ = model.chat(tokenizer, query, image, history=his, do_sample=False, num_beams=3, use_meta=True)
print(response)
# The athlete code of Liu Xiang is 1363.

import torch
from transformers import AutoModel, AutoTokenizer

torch.set_grad_enabled(False)

# init model and tokenizer
model = AutoModel.from_pretrained('internlm/internlm-xcomposer2d5-7b-chat', torch_dtype=torch.bfloat16, trust_remote_code=True).cuda().eval()
tokenizer = AutoTokenizer.from_pretrained('internlm/internlm-xcomposer2d5-7b-chat', trust_remote_code=True)
model.tokenizer = tokenizer

query = 'Here are some frames of a video. Describe this video in detail'
image = ['./examples/liuxiang.mp4',]
with torch.autocast(device_type='cuda', dtype=torch.float16):
    response, his = model.chat(tokenizer, query, image, do_sample=False, num_beams=3, use_meta=True)
print(response)
# The video begins with a man in a red and yellow uniform standing on the starting line of a track, preparing to compete in the 110-meter hurdles at the Athens 2004 Olympic Games. He is identified as Liu Xiang, a Chinese athlete, and his bib number is 1363. The scene is set in a stadium filled with spectators, indicating the significance of the event.
# As the race begins, all the athletes start running, but Liu Xiang quickly takes the lead. However, he encounters a hurdle and knocks it over. Despite this setback, he quickly recovers and continues to run. The race is intense, with athletes from various countries competing fiercely. In the end, Liu Xiang emerges as the winner with a time of 12.91 seconds, securing the gold medal for China.
# The video then transitions to a slow-motion replay of the race, focusing on Liu Xiang's performance and the knockdown of the hurdle. This allows viewers to appreciate the skill and determination of the athlete.
# Following the race, Liu Xiang is seen lying on the track, possibly exhausted from the intense competition. He then stands up and begins to celebrate his victory, waving his arms in the air and running around the track. The crowd cheers and celebrates with him, creating a joyful atmosphere.
# The video concludes with a replay of Liu Xiang's gold medal-winning moment, emphasizing the significance of his achievement at the Athens 2004 Olympic Games.
# Throughout the video, the Olympic logo is prominently displayed, reminding viewers of the global significance of the event and the athletes' dedication and perseverance in their pursuit of victory.

query = 'tell me the athlete code of Liu Xiang'
image = ['./examples/liuxiang.mp4',]
with torch.autocast(device_type='cuda', dtype=torch.float16):
    response, _ = model.chat(tokenizer, query, image, history=his, do_sample=False, num_beams=3, use_meta=True)
print(response)
# The athlete code of Liu Xiang is 1363.

import torch
from transformers import AutoModel, AutoTokenizer

torch.set_grad_enabled(False)

# init model and tokenizer
model = AutoModel.from_pretrained('internlm/internlm-xcomposer2d5-7b-chat', torch_dtype=torch.bfloat16, trust_remote_code=True).cuda().eval()
tokenizer = AutoTokenizer.from_pretrained('internlm/internlm-xcomposer2d5-7b-chat', trust_remote_code=True)
model.tokenizer = tokenizer

query = 'Here are some frames of a video. Describe this video in detail'
image = ['./examples/liuxiang.mp4',]
with torch.autocast(device_type='cuda', dtype=torch.float16):
    response, his = model.chat(tokenizer, query, image, do_sample=False, num_beams=3, use_meta=True)
print(response)
# The video begins with a man in a red and yellow uniform standing on the starting line of a track, preparing to compete in the 110-meter hurdles at the Athens 2004 Olympic Games. He is identified as Liu Xiang, a Chinese athlete, and his bib number is 1363. The scene is set in a stadium filled with spectators, indicating the significance of the event.
# As the race begins, all the athletes start running, but Liu Xiang quickly takes the lead. However, he encounters a hurdle and knocks it over. Despite this setback, he quickly recovers and continues to run. The race is intense, with athletes from various countries competing fiercely. In the end, Liu Xiang emerges as the winner with a time of 12.91 seconds, securing the gold medal for China.
# The video then transitions to a slow-motion replay of the race, focusing on Liu Xiang's performance and the knockdown of the hurdle. This allows viewers to appreciate the skill and determination of the athlete.
# Following the race, Liu Xiang is seen lying on the track, possibly exhausted from the intense competition. He then stands up and begins to celebrate his victory, waving his arms in the air and running around the track. The crowd cheers and celebrates with him, creating a joyful atmosphere.
# The video concludes with a replay of Liu Xiang's gold medal-winning moment, emphasizing the significance of his achievement at the Athens 2004 Olympic Games.
# Throughout the video, the Olympic logo is prominently displayed, reminding viewers of the global significance of the event and the athletes' dedication and perseverance in their pursuit of victory.

query = 'tell me the athlete code of Liu Xiang'
image = ['./examples/liuxiang.mp4',]
with torch.autocast(device_type='cuda', dtype=torch.float16):
    response, _ = model.chat(tokenizer, query, image, history=his, do_sample=False, num_beams=3, use_meta=True)
print(response)
# The athlete code of Liu Xiang is 1363.

import torch
from transformers import AutoModel, AutoTokenizer

torch.set_grad_enabled(False)

# init model and tokenizer
model = AutoModel.from_pretrained('internlm/internlm-xcomposer2d5-7b-chat', torch_dtype=torch.bfloat16, trust_remote_code=True).cuda().eval()
tokenizer = AutoTokenizer.from_pretrained('internlm/internlm-xcomposer2d5-7b-chat', trust_remote_code=True)
model.tokenizer = tokenizer

query = 'Here are some frames of a video. Describe this video in detail'
image = ['./examples/liuxiang.mp4',]
with torch.autocast(device_type='cuda', dtype=torch.float16):
    response, his = model.chat(tokenizer, query, image, do_sample=False, num_beams=3, use_meta=True)
print(response)
# The video begins with a man in a red and yellow uniform standing on the starting line of a track, preparing to compete in the 110-meter hurdles at the Athens 2004 Olympic Games. He is identified as Liu Xiang, a Chinese athlete, and his bib number is 1363. The scene is set in a stadium filled with spectators, indicating the significance of the event.
# As the race begins, all the athletes start running, but Liu Xiang quickly takes the lead. However, he encounters a hurdle and knocks it over. Despite this setback, he quickly recovers and continues to run. The race is intense, with athletes from various countries competing fiercely. In the end, Liu Xiang emerges as the winner with a time of 12.91 seconds, securing the gold medal for China.
# The video then transitions to a slow-motion replay of the race, focusing on Liu Xiang's performance and the knockdown of the hurdle. This allows viewers to appreciate the skill and determination of the athlete.
# Following the race, Liu Xiang is seen lying on the track, possibly exhausted from the intense competition. He then stands up and begins to celebrate his victory, waving his arms in the air and running around the track. The crowd cheers and celebrates with him, creating a joyful atmosphere.
# The video concludes with a replay of Liu Xiang's gold medal-winning moment, emphasizing the significance of his achievement at the Athens 2004 Olympic Games.
# Throughout the video, the Olympic logo is prominently displayed, reminding viewers of the global significance of the event and the athletes' dedication and perseverance in their pursuit of victory.

query = 'tell me the athlete code of Liu Xiang'
image = ['./examples/liuxiang.mp4',]
with torch.autocast(device_type='cuda', dtype=torch.float16):
    response, _ = model.chat(tokenizer, query, image, history=his, do_sample=False, num_beams=3, use_meta=True)
print(response)
# The athlete code of Liu Xiang is 1363.

import torch
from transformers import AutoModel, AutoTokenizer

torch.set_grad_enabled(False)

# init model and tokenizer
model = AutoModel.from_pretrained('internlm/internlm-xcomposer2d5-7b-chat', torch_dtype=torch.bfloat16, trust_remote_code=True).cuda().eval()
tokenizer = AutoTokenizer.from_pretrained('internlm/internlm-xcomposer2d5-7b-chat', trust_remote_code=True)
model.tokenizer = tokenizer

query = 'Here are some frames of a video. Describe this video in detail'
image = ['./examples/liuxiang.mp4',]
with torch.autocast(device_type='cuda', dtype=torch.float16):
    response, his = model.chat(tokenizer, query, image, do_sample=False, num_beams=3, use_meta=True)
print(response)
# The video begins with a man in a red and yellow uniform standing on the starting line of a track, preparing to compete in the 110-meter hurdles at the Athens 2004 Olympic Games. He is identified as Liu Xiang, a Chinese athlete, and his bib number is 1363. The scene is set in a stadium filled with spectators, indicating the significance of the event.
# As the race begins, all the athletes start running, but Liu Xiang quickly takes the lead. However, he encounters a hurdle and knocks it over. Despite this setback, he quickly recovers and continues to run. The race is intense, with athletes from various countries competing fiercely. In the end, Liu Xiang emerges as the winner with a time of 12.91 seconds, securing the gold medal for China.
# The video then transitions to a slow-motion replay of the race, focusing on Liu Xiang's performance and the knockdown of the hurdle. This allows viewers to appreciate the skill and determination of the athlete.
# Following the race, Liu Xiang is seen lying on the track, possibly exhausted from the intense competition. He then stands up and begins to celebrate his victory, waving his arms in the air and running around the track. The crowd cheers and celebrates with him, creating a joyful atmosphere.
# The video concludes with a replay of Liu Xiang's gold medal-winning moment, emphasizing the significance of his achievement at the Athens 2004 Olympic Games.
# Throughout the video, the Olympic logo is prominently displayed, reminding viewers of the global significance of the event and the athletes' dedication and perseverance in their pursuit of victory.

query = 'tell me the athlete code of Liu Xiang'
image = ['./examples/liuxiang.mp4',]
with torch.autocast(device_type='cuda', dtype=torch.float16):
    response, _ = model.chat(tokenizer, query, image, history=his, do_sample=False, num_beams=3, use_meta=True)
print(response)
# The athlete code of Liu Xiang is 1363.

import torch
from transformers import AutoModel, AutoTokenizer

torch.set_grad_enabled(False)

# init model and tokenizer
model = AutoModel.from_pretrained('internlm/internlm-xcomposer2d5-7b-chat', torch_dtype=torch.bfloat16, trust_remote_code=True).cuda().eval()
tokenizer = AutoTokenizer.from_pretrained('internlm/internlm-xcomposer2d5-7b-chat', trust_remote_code=True)
model.tokenizer = tokenizer

query = 'Here are some frames of a video. Describe this video in detail'
image = ['./examples/liuxiang.mp4',]
with torch.autocast(device_type='cuda', dtype=torch.float16):
    response, his = model.chat(tokenizer, query, image, do_sample=False, num_beams=3, use_meta=True)
print(response)
# The video begins with a man in a red and yellow uniform standing on the starting line of a track, preparing to compete in the 110-meter hurdles at the Athens 2004 Olympic Games. He is identified as Liu Xiang, a Chinese athlete, and his bib number is 1363. The scene is set in a stadium filled with spectators, indicating the significance of the event.
# As the race begins, all the athletes start running, but Liu Xiang quickly takes the lead. However, he encounters a hurdle and knocks it over. Despite this setback, he quickly recovers and continues to run. The race is intense, with athletes from various countries competing fiercely. In the end, Liu Xiang emerges as the winner with a time of 12.91 seconds, securing the gold medal for China.
# The video then transitions to a slow-motion replay of the race, focusing on Liu Xiang's performance and the knockdown of the hurdle. This allows viewers to appreciate the skill and determination of the athlete.
# Following the race, Liu Xiang is seen lying on the track, possibly exhausted from the intense competition. He then stands up and begins to celebrate his victory, waving his arms in the air and running around the track. The crowd cheers and celebrates with him, creating a joyful atmosphere.
# The video concludes with a replay of Liu Xiang's gold medal-winning moment, emphasizing the significance of his achievement at the Athens 2004 Olympic Games.
# Throughout the video, the Olympic logo is prominently displayed, reminding viewers of the global significance of the event and the athletes' dedication and perseverance in their pursuit of victory.

query = 'tell me the athlete code of Liu Xiang'
image = ['./examples/liuxiang.mp4',]
with torch.autocast(device_type='cuda', dtype=torch.float16):
    response, _ = model.chat(tokenizer, query, image, history=his, do_sample=False, num_beams=3, use_meta=True)
print(response)
# The athlete code of Liu Xiang is 1363.

import torch
from transformers import AutoModel, AutoTokenizer

torch.set_grad_enabled(False)

# init model and tokenizer
model = AutoModel.from_pretrained('internlm/internlm-xcomposer2d5-7b-chat', torch_dtype=torch.bfloat16, trust_remote_code=True).cuda().eval()
tokenizer = AutoTokenizer.from_pretrained('internlm/internlm-xcomposer2d5-7b-chat', trust_remote_code=True)
model.tokenizer = tokenizer

query = 'Here are some frames of a video. Describe this video in detail'
image = ['./examples/liuxiang.mp4',]
with torch.autocast(device_type='cuda', dtype=torch.float16):
    response, his = model.chat(tokenizer, query, image, do_sample=False, num_beams=3, use_meta=True)
print(response)
# The video begins with a man in a red and yellow uniform standing on the starting line of a track, preparing to compete in the 110-meter hurdles at the Athens 2004 Olympic Games. He is identified as Liu Xiang, a Chinese athlete, and his bib number is 1363. The scene is set in a stadium filled with spectators, indicating the significance of the event.
# As the race begins, all the athletes start running, but Liu Xiang quickly takes the lead. However, he encounters a hurdle and knocks it over. Despite this setback, he quickly recovers and continues to run. The race is intense, with athletes from various countries competing fiercely. In the end, Liu Xiang emerges as the winner with a time of 12.91 seconds, securing the gold medal for China.
# The video then transitions to a slow-motion replay of the race, focusing on Liu Xiang's performance and the knockdown of the hurdle. This allows viewers to appreciate the skill and determination of the athlete.
# Following the race, Liu Xiang is seen lying on the track, possibly exhausted from the intense competition. He then stands up and begins to celebrate his victory, waving his arms in the air and running around the track. The crowd cheers and celebrates with him, creating a joyful atmosphere.
# The video concludes with a replay of Liu Xiang's gold medal-winning moment, emphasizing the significance of his achievement at the Athens 2004 Olympic Games.
# Throughout the video, the Olympic logo is prominently displayed, reminding viewers of the global significance of the event and the athletes' dedication and perseverance in their pursuit of victory.

query = 'tell me the athlete code of Liu Xiang'
image = ['./examples/liuxiang.mp4',]
with torch.autocast(device_type='cuda', dtype=torch.float16):
    response, _ = model.chat(tokenizer, query, image, history=his, do_sample=False, num_beams=3, use_meta=True)
print(response)
# The athlete code of Liu Xiang is 1363.

import torch
from transformers import AutoModel, AutoTokenizer

torch.set_grad_enabled(False)

# init model and tokenizer
model = AutoModel.from_pretrained('internlm/internlm-xcomposer2d5-7b-chat', torch_dtype=torch.bfloat16, trust_remote_code=True).cuda().eval()
tokenizer = AutoTokenizer.from_pretrained('internlm/internlm-xcomposer2d5-7b-chat', trust_remote_code=True)
model.tokenizer = tokenizer

query = 'Here are some frames of a video. Describe this video in detail'
image = ['./examples/liuxiang.mp4',]
with torch.autocast(device_type='cuda', dtype=torch.float16):
    response, his = model.chat(tokenizer, query, image, do_sample=False, num_beams=3, use_meta=True)
print(response)
# The video begins with a man in a red and yellow uniform standing on the starting line of a track, preparing to compete in the 110-meter hurdles at the Athens 2004 Olympic Games. He is identified as Liu Xiang, a Chinese athlete, and his bib number is 1363. The scene is set in a stadium filled with spectators, indicating the significance of the event.
# As the race begins, all the athletes start running, but Liu Xiang quickly takes the lead. However, he encounters a hurdle and knocks it over. Despite this setback, he quickly recovers and continues to run. The race is intense, with athletes from various countries competing fiercely. In the end, Liu Xiang emerges as the winner with a time of 12.91 seconds, securing the gold medal for China.
# The video then transitions to a slow-motion replay of the race, focusing on Liu Xiang's performance and the knockdown of the hurdle. This allows viewers to appreciate the skill and determination of the athlete.
# Following the race, Liu Xiang is seen lying on the track, possibly exhausted from the intense competition. He then stands up and begins to celebrate his victory, waving his arms in the air and running around the track. The crowd cheers and celebrates with him, creating a joyful atmosphere.
# The video concludes with a replay of Liu Xiang's gold medal-winning moment, emphasizing the significance of his achievement at the Athens 2004 Olympic Games.
# Throughout the video, the Olympic logo is prominently displayed, reminding viewers of the global significance of the event and the athletes' dedication and perseverance in their pursuit of victory.

query = 'tell me the athlete code of Liu Xiang'
image = ['./examples/liuxiang.mp4',]
with torch.autocast(device_type='cuda', dtype=torch.float16):
    response, _ = model.chat(tokenizer, query, image, history=his, do_sample=False, num_beams=3, use_meta=True)
print(response)
# The athlete code of Liu Xiang is 1363.

import torch
from transformers import AutoModel, AutoTokenizer

torch.set_grad_enabled(False)

# init model and tokenizer
model = AutoModel.from_pretrained('internlm/internlm-xcomposer2d5-7b-chat', torch_dtype=torch.bfloat16, trust_remote_code=True).cuda().eval()
tokenizer = AutoTokenizer.from_pretrained('internlm/internlm-xcomposer2d5-7b-chat', trust_remote_code=True)
model.tokenizer = tokenizer

query = 'Here are some frames of a video. Describe this video in detail'
image = ['./examples/liuxiang.mp4',]
with torch.autocast(device_type='cuda', dtype=torch.float16):
    response, his = model.chat(tokenizer, query, image, do_sample=False, num_beams=3, use_meta=True)
print(response)
# The video begins with a man in a red and yellow uniform standing on the starting line of a track, preparing to compete in the 110-meter hurdles at the Athens 2004 Olympic Games. He is identified as Liu Xiang, a Chinese athlete, and his bib number is 1363. The scene is set in a stadium filled with spectators, indicating the significance of the event.
# As the race begins, all the athletes start running, but Liu Xiang quickly takes the lead. However, he encounters a hurdle and knocks it over. Despite this setback, he quickly recovers and continues to run. The race is intense, with athletes from various countries competing fiercely. In the end, Liu Xiang emerges as the winner with a time of 12.91 seconds, securing the gold medal for China.
# The video then transitions to a slow-motion replay of the race, focusing on Liu Xiang's performance and the knockdown of the hurdle. This allows viewers to appreciate the skill and determination of the athlete.
# Following the race, Liu Xiang is seen lying on the track, possibly exhausted from the intense competition. He then stands up and begins to celebrate his victory, waving his arms in the air and running around the track. The crowd cheers and celebrates with him, creating a joyful atmosphere.
# The video concludes with a replay of Liu Xiang's gold medal-winning moment, emphasizing the significance of his achievement at the Athens 2004 Olympic Games.
# Throughout the video, the Olympic logo is prominently displayed, reminding viewers of the global significance of the event and the athletes' dedication and perseverance in their pursuit of victory.

query = 'tell me the athlete code of Liu Xiang'
image = ['./examples/liuxiang.mp4',]
with torch.autocast(device_type='cuda', dtype=torch.float16):
    response, _ = model.chat(tokenizer, query, image, history=his, do_sample=False, num_beams=3, use_meta=True)
print(response)
# The athlete code of Liu Xiang is 1363.

import torch
from transformers import AutoModel, AutoTokenizer

torch.set_grad_enabled(False)

# init model and tokenizer
model = AutoModel.from_pretrained('internlm/internlm-xcomposer2d5-7b-chat', torch_dtype=torch.bfloat16, trust_remote_code=True).cuda().eval()
tokenizer = AutoTokenizer.from_pretrained('internlm/internlm-xcomposer2d5-7b-chat', trust_remote_code=True)
model.tokenizer = tokenizer

query = 'Here are some frames of a video. Describe this video in detail'
image = ['./examples/liuxiang.mp4',]
with torch.autocast(device_type='cuda', dtype=torch.float16):
    response, his = model.chat(tokenizer, query, image, do_sample=False, num_beams=3, use_meta=True)
print(response)
# The video begins with a man in a red and yellow uniform standing on the starting line of a track, preparing to compete in the 110-meter hurdles at the Athens 2004 Olympic Games. He is identified as Liu Xiang, a Chinese athlete, and his bib number is 1363. The scene is set in a stadium filled with spectators, indicating the significance of the event.
# As the race begins, all the athletes start running, but Liu Xiang quickly takes the lead. However, he encounters a hurdle and knocks it over. Despite this setback, he quickly recovers and continues to run. The race is intense, with athletes from various countries competing fiercely. In the end, Liu Xiang emerges as the winner with a time of 12.91 seconds, securing the gold medal for China.
# The video then transitions to a slow-motion replay of the race, focusing on Liu Xiang's performance and the knockdown of the hurdle. This allows viewers to appreciate the skill and determination of the athlete.
# Following the race, Liu Xiang is seen lying on the track, possibly exhausted from the intense competition. He then stands up and begins to celebrate his victory, waving his arms in the air and running around the track. The crowd cheers and celebrates with him, creating a joyful atmosphere.
# The video concludes with a replay of Liu Xiang's gold medal-winning moment, emphasizing the significance of his achievement at the Athens 2004 Olympic Games.
# Throughout the video, the Olympic logo is prominently displayed, reminding viewers of the global significance of the event and the athletes' dedication and perseverance in their pursuit of victory.

query = 'tell me the athlete code of Liu Xiang'
image = ['./examples/liuxiang.mp4',]
with torch.autocast(device_type='cuda', dtype=torch.float16):
    response, _ = model.chat(tokenizer, query, image, history=his, do_sample=False, num_beams=3, use_meta=True)
print(response)
# The athlete code of Liu Xiang is 1363.

import torch
from transformers import AutoModel, AutoTokenizer

torch.set_grad_enabled(False)

# init model and tokenizer
model = AutoModel.from_pretrained('internlm/internlm-xcomposer2d5-7b-chat', torch_dtype=torch.bfloat16, trust_remote_code=True).cuda().eval()
tokenizer = AutoTokenizer.from_pretrained('internlm/internlm-xcomposer2d5-7b-chat', trust_remote_code=True)
model.tokenizer = tokenizer

query = 'Here are some frames of a video. Describe this video in detail'
image = ['./examples/liuxiang.mp4',]
with torch.autocast(device_type='cuda', dtype=torch.float16):
    response, his = model.chat(tokenizer, query, image, do_sample=False, num_beams=3, use_meta=True)
print(response)
# The video begins with a man in a red and yellow uniform standing on the starting line of a track, preparing to compete in the 110-meter hurdles at the Athens 2004 Olympic Games. He is identified as Liu Xiang, a Chinese athlete, and his bib number is 1363. The scene is set in a stadium filled with spectators, indicating the significance of the event.
# As the race begins, all the athletes start running, but Liu Xiang quickly takes the lead. However, he encounters a hurdle and knocks it over. Despite this setback, he quickly recovers and continues to run. The race is intense, with athletes from various countries competing fiercely. In the end, Liu Xiang emerges as the winner with a time of 12.91 seconds, securing the gold medal for China.
# The video then transitions to a slow-motion replay of the race, focusing on Liu Xiang's performance and the knockdown of the hurdle. This allows viewers to appreciate the skill and determination of the athlete.
# Following the race, Liu Xiang is seen lying on the track, possibly exhausted from the intense competition. He then stands up and begins to celebrate his victory, waving his arms in the air and running around the track. The crowd cheers and celebrates with him, creating a joyful atmosphere.
# The video concludes with a replay of Liu Xiang's gold medal-winning moment, emphasizing the significance of his achievement at the Athens 2004 Olympic Games.
# Throughout the video, the Olympic logo is prominently displayed, reminding viewers of the global significance of the event and the athletes' dedication and perseverance in their pursuit of victory.

query = 'tell me the athlete code of Liu Xiang'
image = ['./examples/liuxiang.mp4',]
with torch.autocast(device_type='cuda', dtype=torch.float16):
    response, _ = model.chat(tokenizer, query, image, history=his, do_sample=False, num_beams=3, use_meta=True)
print(response)
# The athlete code of Liu Xiang is 1363.

import torch
from transformers import AutoModel, AutoTokenizer

torch.set_grad_enabled(False)

# init model and tokenizer
model = AutoModel.from_pretrained('internlm/internlm-xcomposer2d5-7b-chat', torch_dtype=torch.bfloat16, trust_remote_code=True).cuda().eval()
tokenizer = AutoTokenizer.from_pretrained('internlm/internlm-xcomposer2d5-7b-chat', trust_remote_code=True)
model.tokenizer = tokenizer

query = 'Here are some frames of a video. Describe this video in detail'
image = ['./examples/liuxiang.mp4',]
with torch.autocast(device_type='cuda', dtype=torch.float16):
    response, his = model.chat(tokenizer, query, image, do_sample=False, num_beams=3, use_meta=True)
print(response)
# The video begins with a man in a red and yellow uniform standing on the starting line of a track, preparing to compete in the 110-meter hurdles at the Athens 2004 Olympic Games. He is identified as Liu Xiang, a Chinese athlete, and his bib number is 1363. The scene is set in a stadium filled with spectators, indicating the significance of the event.
# As the race begins, all the athletes start running, but Liu Xiang quickly takes the lead. However, he encounters a hurdle and knocks it over. Despite this setback, he quickly recovers and continues to run. The race is intense, with athletes from various countries competing fiercely. In the end, Liu Xiang emerges as the winner with a time of 12.91 seconds, securing the gold medal for China.
# The video then transitions to a slow-motion replay of the race, focusing on Liu Xiang's performance and the knockdown of the hurdle. This allows viewers to appreciate the skill and determination of the athlete.
# Following the race, Liu Xiang is seen lying on the track, possibly exhausted from the intense competition. He then stands up and begins to celebrate his victory, waving his arms in the air and running around the track. The crowd cheers and celebrates with him, creating a joyful atmosphere.
# The video concludes with a replay of Liu Xiang's gold medal-winning moment, emphasizing the significance of his achievement at the Athens 2004 Olympic Games.
# Throughout the video, the Olympic logo is prominently displayed, reminding viewers of the global significance of the event and the athletes' dedication and perseverance in their pursuit of victory.

query = 'tell me the athlete code of Liu Xiang'
image = ['./examples/liuxiang.mp4',]
with torch.autocast(device_type='cuda', dtype=torch.float16):
    response, _ = model.chat(tokenizer, query, image, history=his, do_sample=False, num_beams=3, use_meta=True)
print(response)
# The athlete code of Liu Xiang is 1363.

import torch
from transformers import AutoModel, AutoTokenizer

torch.set_grad_enabled(False)

# init model and tokenizer
model = AutoModel.from_pretrained('internlm/internlm-xcomposer2d5-7b-chat', torch_dtype=torch.bfloat16, trust_remote_code=True).cuda().eval()
tokenizer = AutoTokenizer.from_pretrained('internlm/internlm-xcomposer2d5-7b-chat', trust_remote_code=True)
model.tokenizer = tokenizer

query = 'Here are some frames of a video. Describe this video in detail'
image = ['./examples/liuxiang.mp4',]
with torch.autocast(device_type='cuda', dtype=torch.float16):
    response, his = model.chat(tokenizer, query, image, do_sample=False, num_beams=3, use_meta=True)
print(response)
# The video begins with a man in a red and yellow uniform standing on the starting line of a track, preparing to compete in the 110-meter hurdles at the Athens 2004 Olympic Games. He is identified as Liu Xiang, a Chinese athlete, and his bib number is 1363. The scene is set in a stadium filled with spectators, indicating the significance of the event.
# As the race begins, all the athletes start running, but Liu Xiang quickly takes the lead. However, he encounters a hurdle and knocks it over. Despite this setback, he quickly recovers and continues to run. The race is intense, with athletes from various countries competing fiercely. In the end, Liu Xiang emerges as the winner with a time of 12.91 seconds, securing the gold medal for China.
# The video then transitions to a slow-motion replay of the race, focusing on Liu Xiang's performance and the knockdown of the hurdle. This allows viewers to appreciate the skill and determination of the athlete.
# Following the race, Liu Xiang is seen lying on the track, possibly exhausted from the intense competition. He then stands up and begins to celebrate his victory, waving his arms in the air and running around the track. The crowd cheers and celebrates with him, creating a joyful atmosphere.
# The video concludes with a replay of Liu Xiang's gold medal-winning moment, emphasizing the significance of his achievement at the Athens 2004 Olympic Games.
# Throughout the video, the Olympic logo is prominently displayed, reminding viewers of the global significance of the event and the athletes' dedication and perseverance in their pursuit of victory.

query = 'tell me the athlete code of Liu Xiang'
image = ['./examples/liuxiang.mp4',]
with torch.autocast(device_type='cuda', dtype=torch.float16):
    response, _ = model.chat(tokenizer, query, image, history=his, do_sample=False, num_beams=3, use_meta=True)
print(response)
# The athlete code of Liu Xiang is 1363.

import torch
from transformers import AutoModel, AutoTokenizer

torch.set_grad_enabled(False)

# init model and tokenizer
model = AutoModel.from_pretrained('internlm/internlm-xcomposer2d5-7b-chat', torch_dtype=torch.bfloat16, trust_remote_code=True).cuda().eval()
tokenizer = AutoTokenizer.from_pretrained('internlm/internlm-xcomposer2d5-7b-chat', trust_remote_code=True)
model.tokenizer = tokenizer

query = 'Here are some frames of a video. Describe this video in detail'
image = ['./examples/liuxiang.mp4',]
with torch.autocast(device_type='cuda', dtype=torch.float16):
    response, his = model.chat(tokenizer, query, image, do_sample=False, num_beams=3, use_meta=True)
print(response)
# The video begins with a man in a red and yellow uniform standing on the starting line of a track, preparing to compete in the 110-meter hurdles at the Athens 2004 Olympic Games. He is identified as Liu Xiang, a Chinese athlete, and his bib number is 1363. The scene is set in a stadium filled with spectators, indicating the significance of the event.
# As the race begins, all the athletes start running, but Liu Xiang quickly takes the lead. However, he encounters a hurdle and knocks it over. Despite this setback, he quickly recovers and continues to run. The race is intense, with athletes from various countries competing fiercely. In the end, Liu Xiang emerges as the winner with a time of 12.91 seconds, securing the gold medal for China.
# The video then transitions to a slow-motion replay of the race, focusing on Liu Xiang's performance and the knockdown of the hurdle. This allows viewers to appreciate the skill and determination of the athlete.
# Following the race, Liu Xiang is seen lying on the track, possibly exhausted from the intense competition. He then stands up and begins to celebrate his victory, waving his arms in the air and running around the track. The crowd cheers and celebrates with him, creating a joyful atmosphere.
# The video concludes with a replay of Liu Xiang's gold medal-winning moment, emphasizing the significance of his achievement at the Athens 2004 Olympic Games.
# Throughout the video, the Olympic logo is prominently displayed, reminding viewers of the global significance of the event and the athletes' dedication and perseverance in their pursuit of victory.

query = 'tell me the athlete code of Liu Xiang'
image = ['./examples/liuxiang.mp4',]
with torch.autocast(device_type='cuda', dtype=torch.float16):
    response, _ = model.chat(tokenizer, query, image, history=his, do_sample=False, num_beams=3, use_meta=True)
print(response)
# The athlete code of Liu Xiang is 1363.

import torch
from transformers import AutoModel, AutoTokenizer

torch.set_grad_enabled(False)

# init model and tokenizer
model = AutoModel.from_pretrained('internlm/internlm-xcomposer2d5-7b-chat', torch_dtype=torch.bfloat16, trust_remote_code=True).cuda().eval()
tokenizer = AutoTokenizer.from_pretrained('internlm/internlm-xcomposer2d5-7b-chat', trust_remote_code=True)
model.tokenizer = tokenizer

query = 'Here are some frames of a video. Describe this video in detail'
image = ['./examples/liuxiang.mp4',]
with torch.autocast(device_type='cuda', dtype=torch.float16):
    response, his = model.chat(tokenizer, query, image, do_sample=False, num_beams=3, use_meta=True)
print(response)
# The video begins with a man in a red and yellow uniform standing on the starting line of a track, preparing to compete in the 110-meter hurdles at the Athens 2004 Olympic Games. He is identified as Liu Xiang, a Chinese athlete, and his bib number is 1363. The scene is set in a stadium filled with spectators, indicating the significance of the event.
# As the race begins, all the athletes start running, but Liu Xiang quickly takes the lead. However, he encounters a hurdle and knocks it over. Despite this setback, he quickly recovers and continues to run. The race is intense, with athletes from various countries competing fiercely. In the end, Liu Xiang emerges as the winner with a time of 12.91 seconds, securing the gold medal for China.
# The video then transitions to a slow-motion replay of the race, focusing on Liu Xiang's performance and the knockdown of the hurdle. This allows viewers to appreciate the skill and determination of the athlete.
# Following the race, Liu Xiang is seen lying on the track, possibly exhausted from the intense competition. He then stands up and begins to celebrate his victory, waving his arms in the air and running around the track. The crowd cheers and celebrates with him, creating a joyful atmosphere.
# The video concludes with a replay of Liu Xiang's gold medal-winning moment, emphasizing the significance of his achievement at the Athens 2004 Olympic Games.
# Throughout the video, the Olympic logo is prominently displayed, reminding viewers of the global significance of the event and the athletes' dedication and perseverance in their pursuit of victory.

query = 'tell me the athlete code of Liu Xiang'
image = ['./examples/liuxiang.mp4',]
with torch.autocast(device_type='cuda', dtype=torch.float16):
    response, _ = model.chat(tokenizer, query, image, history=his, do_sample=False, num_beams=3, use_meta=True)
print(response)
# The athlete code of Liu Xiang is 1363.

import torch
from transformers import AutoModel, AutoTokenizer

torch.set_grad_enabled(False)

# init model and tokenizer
model = AutoModel.from_pretrained('internlm/internlm-xcomposer2d5-7b-chat', torch_dtype=torch.bfloat16, trust_remote_code=True).cuda().eval()
tokenizer = AutoTokenizer.from_pretrained('internlm/internlm-xcomposer2d5-7b-chat', trust_remote_code=True)
model.tokenizer = tokenizer

query = 'Here are some frames of a video. Describe this video in detail'
image = ['./examples/liuxiang.mp4',]
with torch.autocast(device_type='cuda', dtype=torch.float16):
    response, his = model.chat(tokenizer, query, image, do_sample=False, num_beams=3, use_meta=True)
print(response)
# The video begins with a man in a red and yellow uniform standing on the starting line of a track, preparing to compete in the 110-meter hurdles at the Athens 2004 Olympic Games. He is identified as Liu Xiang, a Chinese athlete, and his bib number is 1363. The scene is set in a stadium filled with spectators, indicating the significance of the event.
# As the race begins, all the athletes start running, but Liu Xiang quickly takes the lead. However, he encounters a hurdle and knocks it over. Despite this setback, he quickly recovers and continues to run. The race is intense, with athletes from various countries competing fiercely. In the end, Liu Xiang emerges as the winner with a time of 12.91 seconds, securing the gold medal for China.
# The video then transitions to a slow-motion replay of the race, focusing on Liu Xiang's performance and the knockdown of the hurdle. This allows viewers to appreciate the skill and determination of the athlete.
# Following the race, Liu Xiang is seen lying on the track, possibly exhausted from the intense competition. He then stands up and begins to celebrate his victory, waving his arms in the air and running around the track. The crowd cheers and celebrates with him, creating a joyful atmosphere.
# The video concludes with a replay of Liu Xiang's gold medal-winning moment, emphasizing the significance of his achievement at the Athens 2004 Olympic Games.
# Throughout the video, the Olympic logo is prominently displayed, reminding viewers of the global significance of the event and the athletes' dedication and perseverance in their pursuit of victory.

query = 'tell me the athlete code of Liu Xiang'
image = ['./examples/liuxiang.mp4',]
with torch.autocast(device_type='cuda', dtype=torch.float16):
    response, _ = model.chat(tokenizer, query, image, history=his, do_sample=False, num_beams=3, use_meta=True)
print(response)
# The athlete code of Liu Xiang is 1363.

import torch
from transformers import AutoModel, AutoTokenizer

torch.set_grad_enabled(False)

# init model and tokenizer
model = AutoModel.from_pretrained('internlm/internlm-xcomposer2d5-7b-chat', torch_dtype=torch.bfloat16, trust_remote_code=True).cuda().eval()
tokenizer = AutoTokenizer.from_pretrained('internlm/internlm-xcomposer2d5-7b-chat', trust_remote_code=True)
model.tokenizer = tokenizer

query = 'Here are some frames of a video. Describe this video in detail'
image = ['./examples/liuxiang.mp4',]
with torch.autocast(device_type='cuda', dtype=torch.float16):
    response, his = model.chat(tokenizer, query, image, do_sample=False, num_beams=3, use_meta=True)
print(response)
# The video begins with a man in a red and yellow uniform standing on the starting line of a track, preparing to compete in the 110-meter hurdles at the Athens 2004 Olympic Games. He is identified as Liu Xiang, a Chinese athlete, and his bib number is 1363. The scene is set in a stadium filled with spectators, indicating the significance of the event.
# As the race begins, all the athletes start running, but Liu Xiang quickly takes the lead. However, he encounters a hurdle and knocks it over. Despite this setback, he quickly recovers and continues to run. The race is intense, with athletes from various countries competing fiercely. In the end, Liu Xiang emerges as the winner with a time of 12.91 seconds, securing the gold medal for China.
# The video then transitions to a slow-motion replay of the race, focusing on Liu Xiang's performance and the knockdown of the hurdle. This allows viewers to appreciate the skill and determination of the athlete.
# Following the race, Liu Xiang is seen lying on the track, possibly exhausted from the intense competition. He then stands up and begins to celebrate his victory, waving his arms in the air and running around the track. The crowd cheers and celebrates with him, creating a joyful atmosphere.
# The video concludes with a replay of Liu Xiang's gold medal-winning moment, emphasizing the significance of his achievement at the Athens 2004 Olympic Games.
# Throughout the video, the Olympic logo is prominently displayed, reminding viewers of the global significance of the event and the athletes' dedication and perseverance in their pursuit of victory.

query = 'tell me the athlete code of Liu Xiang'
image = ['./examples/liuxiang.mp4',]
with torch.autocast(device_type='cuda', dtype=torch.float16):
    response, _ = model.chat(tokenizer, query, image, history=his, do_sample=False, num_beams=3, use_meta=True)
print(response)
# The athlete code of Liu Xiang is 1363.

import torch
from transformers import AutoModel, AutoTokenizer

torch.set_grad_enabled(False)

# init model and tokenizer
model = AutoModel.from_pretrained('internlm/internlm-xcomposer2d5-7b-chat', torch_dtype=torch.bfloat16, trust_remote_code=True).cuda().eval()
tokenizer = AutoTokenizer.from_pretrained('internlm/internlm-xcomposer2d5-7b-chat', trust_remote_code=True)
model.tokenizer = tokenizer

query = 'Here are some frames of a video. Describe this video in detail'
image = ['./examples/liuxiang.mp4',]
with torch.autocast(device_type='cuda', dtype=torch.float16):
    response, his = model.chat(tokenizer, query, image, do_sample=False, num_beams=3, use_meta=True)
print(response)
# The video begins with a man in a red and yellow uniform standing on the starting line of a track, preparing to compete in the 110-meter hurdles at the Athens 2004 Olympic Games. He is identified as Liu Xiang, a Chinese athlete, and his bib number is 1363. The scene is set in a stadium filled with spectators, indicating the significance of the event.
# As the race begins, all the athletes start running, but Liu Xiang quickly takes the lead. However, he encounters a hurdle and knocks it over. Despite this setback, he quickly recovers and continues to run. The race is intense, with athletes from various countries competing fiercely. In the end, Liu Xiang emerges as the winner with a time of 12.91 seconds, securing the gold medal for China.
# The video then transitions to a slow-motion replay of the race, focusing on Liu Xiang's performance and the knockdown of the hurdle. This allows viewers to appreciate the skill and determination of the athlete.
# Following the race, Liu Xiang is seen lying on the track, possibly exhausted from the intense competition. He then stands up and begins to celebrate his victory, waving his arms in the air and running around the track. The crowd cheers and celebrates with him, creating a joyful atmosphere.
# The video concludes with a replay of Liu Xiang's gold medal-winning moment, emphasizing the significance of his achievement at the Athens 2004 Olympic Games.
# Throughout the video, the Olympic logo is prominently displayed, reminding viewers of the global significance of the event and the athletes' dedication and perseverance in their pursuit of victory.

query = 'tell me the athlete code of Liu Xiang'
image = ['./examples/liuxiang.mp4',]
with torch.autocast(device_type='cuda', dtype=torch.float16):
    response, _ = model.chat(tokenizer, query, image, history=his, do_sample=False, num_beams=3, use_meta=True)
print(response)
# The athlete code of Liu Xiang is 1363.

import torch
from transformers import AutoModel, AutoTokenizer

torch.set_grad_enabled(False)

# init model and tokenizer
model = AutoModel.from_pretrained('internlm/internlm-xcomposer2d5-7b-chat', torch_dtype=torch.bfloat16, trust_remote_code=True).cuda().eval()
tokenizer = AutoTokenizer.from_pretrained('internlm/internlm-xcomposer2d5-7b-chat', trust_remote_code=True)
model.tokenizer = tokenizer

query = 'Here are some frames of a video. Describe this video in detail'
image = ['./examples/liuxiang.mp4',]
with torch.autocast(device_type='cuda', dtype=torch.float16):
    response, his = model.chat(tokenizer, query, image, do_sample=False, num_beams=3, use_meta=True)
print(response)
# The video begins with a man in a red and yellow uniform standing on the starting line of a track, preparing to compete in the 110-meter hurdles at the Athens 2004 Olympic Games. He is identified as Liu Xiang, a Chinese athlete, and his bib number is 1363. The scene is set in a stadium filled with spectators, indicating the significance of the event.
# As the race begins, all the athletes start running, but Liu Xiang quickly takes the lead. However, he encounters a hurdle and knocks it over. Despite this setback, he quickly recovers and continues to run. The race is intense, with athletes from various countries competing fiercely. In the end, Liu Xiang emerges as the winner with a time of 12.91 seconds, securing the gold medal for China.
# The video then transitions to a slow-motion replay of the race, focusing on Liu Xiang's performance and the knockdown of the hurdle. This allows viewers to appreciate the skill and determination of the athlete.
# Following the race, Liu Xiang is seen lying on the track, possibly exhausted from the intense competition. He then stands up and begins to celebrate his victory, waving his arms in the air and running around the track. The crowd cheers and celebrates with him, creating a joyful atmosphere.
# The video concludes with a replay of Liu Xiang's gold medal-winning moment, emphasizing the significance of his achievement at the Athens 2004 Olympic Games.
# Throughout the video, the Olympic logo is prominently displayed, reminding viewers of the global significance of the event and the athletes' dedication and perseverance in their pursuit of victory.

query = 'tell me the athlete code of Liu Xiang'
image = ['./examples/liuxiang.mp4',]
with torch.autocast(device_type='cuda', dtype=torch.float16):
    response, _ = model.chat(tokenizer, query, image, history=his, do_sample=False, num_beams=3, use_meta=True)
print(response)
# The athlete code of Liu Xiang is 1363.

import torch
from transformers import AutoModel, AutoTokenizer

torch.set_grad_enabled(False)

# init model and tokenizer
model = AutoModel.from_pretrained('internlm/internlm-xcomposer2d5-7b-chat', torch_dtype=torch.bfloat16, trust_remote_code=True).cuda().eval()
tokenizer = AutoTokenizer.from_pretrained('internlm/internlm-xcomposer2d5-7b-chat', trust_remote_code=True)
model.tokenizer = tokenizer

query = 'Here are some frames of a video. Describe this video in detail'
image = ['./examples/liuxiang.mp4',]
with torch.autocast(device_type='cuda', dtype=torch.float16):
    response, his = model.chat(tokenizer, query, image, do_sample=False, num_beams=3, use_meta=True)
print(response)
# The video begins with a man in a red and yellow uniform standing on the starting line of a track, preparing to compete in the 110-meter hurdles at the Athens 2004 Olympic Games. He is identified as Liu Xiang, a Chinese athlete, and his bib number is 1363. The scene is set in a stadium filled with spectators, indicating the significance of the event.
# As the race begins, all the athletes start running, but Liu Xiang quickly takes the lead. However, he encounters a hurdle and knocks it over. Despite this setback, he quickly recovers and continues to run. The race is intense, with athletes from various countries competing fiercely. In the end, Liu Xiang emerges as the winner with a time of 12.91 seconds, securing the gold medal for China.
# The video then transitions to a slow-motion replay of the race, focusing on Liu Xiang's performance and the knockdown of the hurdle. This allows viewers to appreciate the skill and determination of the athlete.
# Following the race, Liu Xiang is seen lying on the track, possibly exhausted from the intense competition. He then stands up and begins to celebrate his victory, waving his arms in the air and running around the track. The crowd cheers and celebrates with him, creating a joyful atmosphere.
# The video concludes with a replay of Liu Xiang's gold medal-winning moment, emphasizing the significance of his achievement at the Athens 2004 Olympic Games.
# Throughout the video, the Olympic logo is prominently displayed, reminding viewers of the global significance of the event and the athletes' dedication and perseverance in their pursuit of victory.

query = 'tell me the athlete code of Liu Xiang'
image = ['./examples/liuxiang.mp4',]
with torch.autocast(device_type='cuda', dtype=torch.float16):
    response, _ = model.chat(tokenizer, query, image, history=his, do_sample=False, num_beams=3, use_meta=True)
print(response)
# The athlete code of Liu Xiang is 1363.

import torch
from transformers import AutoModel, AutoTokenizer

torch.set_grad_enabled(False)

# init model and tokenizer
model = AutoModel.from_pretrained('internlm/internlm-xcomposer2d5-7b-chat', torch_dtype=torch.bfloat16, trust_remote_code=True).cuda().eval()
tokenizer = AutoTokenizer.from_pretrained('internlm/internlm-xcomposer2d5-7b-chat', trust_remote_code=True)
model.tokenizer = tokenizer

query = 'Here are some frames of a video. Describe this video in detail'
image = ['./examples/liuxiang.mp4',]
with torch.autocast(device_type='cuda', dtype=torch.float16):
    response, his = model.chat(tokenizer, query, image, do_sample=False, num_beams=3, use_meta=True)
print(response)
# The video begins with a man in a red and yellow uniform standing on the starting line of a track, preparing to compete in the 110-meter hurdles at the Athens 2004 Olympic Games. He is identified as Liu Xiang, a Chinese athlete, and his bib number is 1363. The scene is set in a stadium filled with spectators, indicating the significance of the event.
# As the race begins, all the athletes start running, but Liu Xiang quickly takes the lead. However, he encounters a hurdle and knocks it over. Despite this setback, he quickly recovers and continues to run. The race is intense, with athletes from various countries competing fiercely. In the end, Liu Xiang emerges as the winner with a time of 12.91 seconds, securing the gold medal for China.
# The video then transitions to a slow-motion replay of the race, focusing on Liu Xiang's performance and the knockdown of the hurdle. This allows viewers to appreciate the skill and determination of the athlete.
# Following the race, Liu Xiang is seen lying on the track, possibly exhausted from the intense competition. He then stands up and begins to celebrate his victory, waving his arms in the air and running around the track. The crowd cheers and celebrates with him, creating a joyful atmosphere.
# The video concludes with a replay of Liu Xiang's gold medal-winning moment, emphasizing the significance of his achievement at the Athens 2004 Olympic Games.
# Throughout the video, the Olympic logo is prominently displayed, reminding viewers of the global significance of the event and the athletes' dedication and perseverance in their pursuit of victory.

query = 'tell me the athlete code of Liu Xiang'
image = ['./examples/liuxiang.mp4',]
with torch.autocast(device_type='cuda', dtype=torch.float16):
    response, _ = model.chat(tokenizer, query, image, history=his, do_sample=False, num_beams=3, use_meta=True)
print(response)
# The athlete code of Liu Xiang is 1363.

import torch
from transformers import AutoModel, AutoTokenizer

torch.set_grad_enabled(False)

# init model and tokenizer
model = AutoModel.from_pretrained('internlm/internlm-xcomposer2d5-7b-chat', torch_dtype=torch.bfloat16, trust_remote_code=True).cuda().eval()
tokenizer = AutoTokenizer.from_pretrained('internlm/internlm-xcomposer2d5-7b-chat', trust_remote_code=True)
model.tokenizer = tokenizer

query = 'Here are some frames of a video. Describe this video in detail'
image = ['./examples/liuxiang.mp4',]
with torch.autocast(device_type='cuda', dtype=torch.float16):
    response, his = model.chat(tokenizer, query, image, do_sample=False, num_beams=3, use_meta=True)
print(response)
# The video begins with a man in a red and yellow uniform standing on the starting line of a track, preparing to compete in the 110-meter hurdles at the Athens 2004 Olympic Games. He is identified as Liu Xiang, a Chinese athlete, and his bib number is 1363. The scene is set in a stadium filled with spectators, indicating the significance of the event.
# As the race begins, all the athletes start running, but Liu Xiang quickly takes the lead. However, he encounters a hurdle and knocks it over. Despite this setback, he quickly recovers and continues to run. The race is intense, with athletes from various countries competing fiercely. In the end, Liu Xiang emerges as the winner with a time of 12.91 seconds, securing the gold medal for China.
# The video then transitions to a slow-motion replay of the race, focusing on Liu Xiang's performance and the knockdown of the hurdle. This allows viewers to appreciate the skill and determination of the athlete.
# Following the race, Liu Xiang is seen lying on the track, possibly exhausted from the intense competition. He then stands up and begins to celebrate his victory, waving his arms in the air and running around the track. The crowd cheers and celebrates with him, creating a joyful atmosphere.
# The video concludes with a replay of Liu Xiang's gold medal-winning moment, emphasizing the significance of his achievement at the Athens 2004 Olympic Games.
# Throughout the video, the Olympic logo is prominently displayed, reminding viewers of the global significance of the event and the athletes' dedication and perseverance in their pursuit of victory.

query = 'tell me the athlete code of Liu Xiang'
image = ['./examples/liuxiang.mp4',]
with torch.autocast(device_type='cuda', dtype=torch.float16):
    response, _ = model.chat(tokenizer, query, image, history=his, do_sample=False, num_beams=3, use_meta=True)
print(response)
# The athlete code of Liu Xiang is 1363.

import torch
from transformers import AutoModel, AutoTokenizer

torch.set_grad_enabled(False)

# init model and tokenizer
model = AutoModel.from_pretrained('internlm/internlm-xcomposer2d5-7b-chat', torch_dtype=torch.bfloat16, trust_remote_code=True).cuda().eval()
tokenizer = AutoTokenizer.from_pretrained('internlm/internlm-xcomposer2d5-7b-chat', trust_remote_code=True)
model.tokenizer = tokenizer

query = 'Here are some frames of a video. Describe this video in detail'
image = ['./examples/liuxiang.mp4',]
with torch.autocast(device_type='cuda', dtype=torch.float16):
    response, his = model.chat(tokenizer, query, image, do_sample=False, num_beams=3, use_meta=True)
print(response)
# The video begins with a man in a red and yellow uniform standing on the starting line of a track, preparing to compete in the 110-meter hurdles at the Athens 2004 Olympic Games. He is identified as Liu Xiang, a Chinese athlete, and his bib number is 1363. The scene is set in a stadium filled with spectators, indicating the significance of the event.
# As the race begins, all the athletes start running, but Liu Xiang quickly takes the lead. However, he encounters a hurdle and knocks it over. Despite this setback, he quickly recovers and continues to run. The race is intense, with athletes from various countries competing fiercely. In the end, Liu Xiang emerges as the winner with a time of 12.91 seconds, securing the gold medal for China.
# The video then transitions to a slow-motion replay of the race, focusing on Liu Xiang's performance and the knockdown of the hurdle. This allows viewers to appreciate the skill and determination of the athlete.
# Following the race, Liu Xiang is seen lying on the track, possibly exhausted from the intense competition. He then stands up and begins to celebrate his victory, waving his arms in the air and running around the track. The crowd cheers and celebrates with him, creating a joyful atmosphere.
# The video concludes with a replay of Liu Xiang's gold medal-winning moment, emphasizing the significance of his achievement at the Athens 2004 Olympic Games.
# Throughout the video, the Olympic logo is prominently displayed, reminding viewers of the global significance of the event and the athletes' dedication and perseverance in their pursuit of victory.

query = 'tell me the athlete code of Liu Xiang'
image = ['./examples/liuxiang.mp4',]
with torch.autocast(device_type='cuda', dtype=torch.float16):
    response, _ = model.chat(tokenizer, query, image, history=his, do_sample=False, num_beams=3, use_meta=True)
print(response)
# The athlete code of Liu Xiang is 1363.

import torch
from transformers import AutoModel, AutoTokenizer

torch.set_grad_enabled(False)

# init model and tokenizer
model = AutoModel.from_pretrained('internlm/internlm-xcomposer2d5-7b-chat', torch_dtype=torch.bfloat16, trust_remote_code=True).cuda().eval()
tokenizer = AutoTokenizer.from_pretrained('internlm/internlm-xcomposer2d5-7b-chat', trust_remote_code=True)
model.tokenizer = tokenizer

query = 'Here are some frames of a video. Describe this video in detail'
image = ['./examples/liuxiang.mp4',]
with torch.autocast(device_type='cuda', dtype=torch.float16):
    response, his = model.chat(tokenizer, query, image, do_sample=False, num_beams=3, use_meta=True)
print(response)
# The video begins with a man in a red and yellow uniform standing on the starting line of a track, preparing to compete in the 110-meter hurdles at the Athens 2004 Olympic Games. He is identified as Liu Xiang, a Chinese athlete, and his bib number is 1363. The scene is set in a stadium filled with spectators, indicating the significance of the event.
# As the race begins, all the athletes start running, but Liu Xiang quickly takes the lead. However, he encounters a hurdle and knocks it over. Despite this setback, he quickly recovers and continues to run. The race is intense, with athletes from various countries competing fiercely. In the end, Liu Xiang emerges as the winner with a time of 12.91 seconds, securing the gold medal for China.
# The video then transitions to a slow-motion replay of the race, focusing on Liu Xiang's performance and the knockdown of the hurdle. This allows viewers to appreciate the skill and determination of the athlete.
# Following the race, Liu Xiang is seen lying on the track, possibly exhausted from the intense competition. He then stands up and begins to celebrate his victory, waving his arms in the air and running around the track. The crowd cheers and celebrates with him, creating a joyful atmosphere.
# The video concludes with a replay of Liu Xiang's gold medal-winning moment, emphasizing the significance of his achievement at the Athens 2004 Olympic Games.
# Throughout the video, the Olympic logo is prominently displayed, reminding viewers of the global significance of the event and the athletes' dedication and perseverance in their pursuit of victory.

query = 'tell me the athlete code of Liu Xiang'
image = ['./examples/liuxiang.mp4',]
with torch.autocast(device_type='cuda', dtype=torch.float16):
    response, _ = model.chat(tokenizer, query, image, history=his, do_sample=False, num_beams=3, use_meta=True)
print(response)
# The athlete code of Liu Xiang is 1363.

import torch
from transformers import AutoModel, AutoTokenizer

torch.set_grad_enabled(False)

# init model and tokenizer
model = AutoModel.from_pretrained('internlm/internlm-xcomposer2d5-7b-chat', torch_dtype=torch.bfloat16, trust_remote_code=True).cuda().eval()
tokenizer = AutoTokenizer.from_pretrained('internlm/internlm-xcomposer2d5-7b-chat', trust_remote_code=True)
model.tokenizer = tokenizer

query = 'Here are some frames of a video. Describe this video in detail'
image = ['./examples/liuxiang.mp4',]
with torch.autocast(device_type='cuda', dtype=torch.float16):
    response, his = model.chat(tokenizer, query, image, do_sample=False, num_beams=3, use_meta=True)
print(response)
# The video begins with a man in a red and yellow uniform standing on the starting line of a track, preparing to compete in the 110-meter hurdles at the Athens 2004 Olympic Games. He is identified as Liu Xiang, a Chinese athlete, and his bib number is 1363. The scene is set in a stadium filled with spectators, indicating the significance of the event.
# As the race begins, all the athletes start running, but Liu Xiang quickly takes the lead. However, he encounters a hurdle and knocks it over. Despite this setback, he quickly recovers and continues to run. The race is intense, with athletes from various countries competing fiercely. In the end, Liu Xiang emerges as the winner with a time of 12.91 seconds, securing the gold medal for China.
# The video then transitions to a slow-motion replay of the race, focusing on Liu Xiang's performance and the knockdown of the hurdle. This allows viewers to appreciate the skill and determination of the athlete.
# Following the race, Liu Xiang is seen lying on the track, possibly exhausted from the intense competition. He then stands up and begins to celebrate his victory, waving his arms in the air and running around the track. The crowd cheers and celebrates with him, creating a joyful atmosphere.
# The video concludes with a replay of Liu Xiang's gold medal-winning moment, emphasizing the significance of his achievement at the Athens 2004 Olympic Games.
# Throughout the video, the Olympic logo is prominently displayed, reminding viewers of the global significance of the event and the athletes' dedication and perseverance in their pursuit of victory.

query = 'tell me the athlete code of Liu Xiang'
image = ['./examples/liuxiang.mp4',]
with torch.autocast(device_type='cuda', dtype=torch.float16):
    response, _ = model.chat(tokenizer, query, image, history=his, do_sample=False, num_beams=3, use_meta=True)
print(response)
# The athlete code of Liu Xiang is 1363.

import torch
from transformers import AutoModel, AutoTokenizer

torch.set_grad_enabled(False)

# init model and tokenizer
model = AutoModel.from_pretrained('internlm/internlm-xcomposer2d5-7b-chat', torch_dtype=torch.bfloat16, trust_remote_code=True).cuda().eval()
tokenizer = AutoTokenizer.from_pretrained('internlm/internlm-xcomposer2d5-7b-chat', trust_remote_code=True)
model.tokenizer = tokenizer

query = 'Here are some frames of a video. Describe this video in detail'
image = ['./examples/liuxiang.mp4',]
with torch.autocast(device_type='cuda', dtype=torch.float16):
    response, his = model.chat(tokenizer, query, image, do_sample=False, num_beams=3, use_meta=True)
print(response)
# The video begins with a man in a red and yellow uniform standing on the starting line of a track, preparing to compete in the 110-meter hurdles at the Athens 2004 Olympic Games. He is identified as Liu Xiang, a Chinese athlete, and his bib number is 1363. The scene is set in a stadium filled with spectators, indicating the significance of the event.
# As the race begins, all the athletes start running, but Liu Xiang quickly takes the lead. However, he encounters a hurdle and knocks it over. Despite this setback, he quickly recovers and continues to run. The race is intense, with athletes from various countries competing fiercely. In the end, Liu Xiang emerges as the winner with a time of 12.91 seconds, securing the gold medal for China.
# The video then transitions to a slow-motion replay of the race, focusing on Liu Xiang's performance and the knockdown of the hurdle. This allows viewers to appreciate the skill and determination of the athlete.
# Following the race, Liu Xiang is seen lying on the track, possibly exhausted from the intense competition. He then stands up and begins to celebrate his victory, waving his arms in the air and running around the track. The crowd cheers and celebrates with him, creating a joyful atmosphere.
# The video concludes with a replay of Liu Xiang's gold medal-winning moment, emphasizing the significance of his achievement at the Athens 2004 Olympic Games.
# Throughout the video, the Olympic logo is prominently displayed, reminding viewers of the global significance of the event and the athletes' dedication and perseverance in their pursuit of victory.

query = 'tell me the athlete code of Liu Xiang'
image = ['./examples/liuxiang.mp4',]
with torch.autocast(device_type='cuda', dtype=torch.float16):
    response, _ = model.chat(tokenizer, query, image, history=his, do_sample=False, num_beams=3, use_meta=True)
print(response)
# The athlete code of Liu Xiang is 1363.

import torch
from transformers import AutoModel, AutoTokenizer

torch.set_grad_enabled(False)

# init model and tokenizer
model = AutoModel.from_pretrained('internlm/internlm-xcomposer2d5-7b-chat', torch_dtype=torch.bfloat16, trust_remote_code=True).cuda().eval()
tokenizer = AutoTokenizer.from_pretrained('internlm/internlm-xcomposer2d5-7b-chat', trust_remote_code=True)
model.tokenizer = tokenizer

query = 'Here are some frames of a video. Describe this video in detail'
image = ['./examples/liuxiang.mp4',]
with torch.autocast(device_type='cuda', dtype=torch.float16):
    response, his = model.chat(tokenizer, query, image, do_sample=False, num_beams=3, use_meta=True)
print(response)
# The video begins with a man in a red and yellow uniform standing on the starting line of a track, preparing to compete in the 110-meter hurdles at the Athens 2004 Olympic Games. He is identified as Liu Xiang, a Chinese athlete, and his bib number is 1363. The scene is set in a stadium filled with spectators, indicating the significance of the event.
# As the race begins, all the athletes start running, but Liu Xiang quickly takes the lead. However, he encounters a hurdle and knocks it over. Despite this setback, he quickly recovers and continues to run. The race is intense, with athletes from various countries competing fiercely. In the end, Liu Xiang emerges as the winner with a time of 12.91 seconds, securing the gold medal for China.
# The video then transitions to a slow-motion replay of the race, focusing on Liu Xiang's performance and the knockdown of the hurdle. This allows viewers to appreciate the skill and determination of the athlete.
# Following the race, Liu Xiang is seen lying on the track, possibly exhausted from the intense competition. He then stands up and begins to celebrate his victory, waving his arms in the air and running around the track. The crowd cheers and celebrates with him, creating a joyful atmosphere.
# The video concludes with a replay of Liu Xiang's gold medal-winning moment, emphasizing the significance of his achievement at the Athens 2004 Olympic Games.
# Throughout the video, the Olympic logo is prominently displayed, reminding viewers of the global significance of the event and the athletes' dedication and perseverance in their pursuit of victory.

query = 'tell me the athlete code of Liu Xiang'
image = ['./examples/liuxiang.mp4',]
with torch.autocast(device_type='cuda', dtype=torch.float16):
    response, _ = model.chat(tokenizer, query, image, history=his, do_sample=False, num_beams=3, use_meta=True)
print(response)
# The athlete code of Liu Xiang is 1363.

import torch
from transformers import AutoModel, AutoTokenizer

torch.set_grad_enabled(False)

# init model and tokenizer
model = AutoModel.from_pretrained('internlm/internlm-xcomposer2d5-7b-chat', torch_dtype=torch.bfloat16, trust_remote_code=True).cuda().eval()
tokenizer = AutoTokenizer.from_pretrained('internlm/internlm-xcomposer2d5-7b-chat', trust_remote_code=True)
model.tokenizer = tokenizer

query = 'Here are some frames of a video. Describe this video in detail'
image = ['./examples/liuxiang.mp4',]
with torch.autocast(device_type='cuda', dtype=torch.float16):
    response, his = model.chat(tokenizer, query, image, do_sample=False, num_beams=3, use_meta=True)
print(response)
# The video begins with a man in a red and yellow uniform standing on the starting line of a track, preparing to compete in the 110-meter hurdles at the Athens 2004 Olympic Games. He is identified as Liu Xiang, a Chinese athlete, and his bib number is 1363. The scene is set in a stadium filled with spectators, indicating the significance of the event.
# As the race begins, all the athletes start running, but Liu Xiang quickly takes the lead. However, he encounters a hurdle and knocks it over. Despite this setback, he quickly recovers and continues to run. The race is intense, with athletes from various countries competing fiercely. In the end, Liu Xiang emerges as the winner with a time of 12.91 seconds, securing the gold medal for China.
# The video then transitions to a slow-motion replay of the race, focusing on Liu Xiang's performance and the knockdown of the hurdle. This allows viewers to appreciate the skill and determination of the athlete.
# Following the race, Liu Xiang is seen lying on the track, possibly exhausted from the intense competition. He then stands up and begins to celebrate his victory, waving his arms in the air and running around the track. The crowd cheers and celebrates with him, creating a joyful atmosphere.
# The video concludes with a replay of Liu Xiang's gold medal-winning moment, emphasizing the significance of his achievement at the Athens 2004 Olympic Games.
# Throughout the video, the Olympic logo is prominently displayed, reminding viewers of the global significance of the event and the athletes' dedication and perseverance in their pursuit of victory.

query = 'tell me the athlete code of Liu Xiang'
image = ['./examples/liuxiang.mp4',]
with torch.autocast(device_type='cuda', dtype=torch.float16):
    response, _ = model.chat(tokenizer, query, image, history=his, do_sample=False, num_beams=3, use_meta=True)
print(response)
# The athlete code of Liu Xiang is 1363.

import torch
from transformers import AutoModel, AutoTokenizer

torch.set_grad_enabled(False)

# init model and tokenizer
model = AutoModel.from_pretrained('internlm/internlm-xcomposer2d5-7b-chat', torch_dtype=torch.bfloat16, trust_remote_code=True).cuda().eval()
tokenizer = AutoTokenizer.from_pretrained('internlm/internlm-xcomposer2d5-7b-chat', trust_remote_code=True)
model.tokenizer = tokenizer

query = 'Here are some frames of a video. Describe this video in detail'
image = ['./examples/liuxiang.mp4',]
with torch.autocast(device_type='cuda', dtype=torch.float16):
    response, his = model.chat(tokenizer, query, image, do_sample=False, num_beams=3, use_meta=True)
print(response)
# The video begins with a man in a red and yellow uniform standing on the starting line of a track, preparing to compete in the 110-meter hurdles at the Athens 2004 Olympic Games. He is identified as Liu Xiang, a Chinese athlete, and his bib number is 1363. The scene is set in a stadium filled with spectators, indicating the significance of the event.
# As the race begins, all the athletes start running, but Liu Xiang quickly takes the lead. However, he encounters a hurdle and knocks it over. Despite this setback, he quickly recovers and continues to run. The race is intense, with athletes from various countries competing fiercely. In the end, Liu Xiang emerges as the winner with a time of 12.91 seconds, securing the gold medal for China.
# The video then transitions to a slow-motion replay of the race, focusing on Liu Xiang's performance and the knockdown of the hurdle. This allows viewers to appreciate the skill and determination of the athlete.
# Following the race, Liu Xiang is seen lying on the track, possibly exhausted from the intense competition. He then stands up and begins to celebrate his victory, waving his arms in the air and running around the track. The crowd cheers and celebrates with him, creating a joyful atmosphere.
# The video concludes with a replay of Liu Xiang's gold medal-winning moment, emphasizing the significance of his achievement at the Athens 2004 Olympic Games.
# Throughout the video, the Olympic logo is prominently displayed, reminding viewers of the global significance of the event and the athletes' dedication and perseverance in their pursuit of victory.

query = 'tell me the athlete code of Liu Xiang'
image = ['./examples/liuxiang.mp4',]
with torch.autocast(device_type='cuda', dtype=torch.float16):
    response, _ = model.chat(tokenizer, query, image, history=his, do_sample=False, num_beams=3, use_meta=True)
print(response)
# The athlete code of Liu Xiang is 1363.

import torch
from transformers import AutoModel, AutoTokenizer

torch.set_grad_enabled(False)

# init model and tokenizer
model = AutoModel.from_pretrained('internlm/internlm-xcomposer2d5-7b-chat', torch_dtype=torch.bfloat16, trust_remote_code=True).cuda().eval()
tokenizer = AutoTokenizer.from_pretrained('internlm/internlm-xcomposer2d5-7b-chat', trust_remote_code=True)
model.tokenizer = tokenizer

query = 'Here are some frames of a video. Describe this video in detail'
image = ['./examples/liuxiang.mp4',]
with torch.autocast(device_type='cuda', dtype=torch.float16):
    response, his = model.chat(tokenizer, query, image, do_sample=False, num_beams=3, use_meta=True)
print(response)
# The video begins with a man in a red and yellow uniform standing on the starting line of a track, preparing to compete in the 110-meter hurdles at the Athens 2004 Olympic Games. He is identified as Liu Xiang, a Chinese athlete, and his bib number is 1363. The scene is set in a stadium filled with spectators, indicating the significance of the event.
# As the race begins, all the athletes start running, but Liu Xiang quickly takes the lead. However, he encounters a hurdle and knocks it over. Despite this setback, he quickly recovers and continues to run. The race is intense, with athletes from various countries competing fiercely. In the end, Liu Xiang emerges as the winner with a time of 12.91 seconds, securing the gold medal for China.
# The video then transitions to a slow-motion replay of the race, focusing on Liu Xiang's performance and the knockdown of the hurdle. This allows viewers to appreciate the skill and determination of the athlete.
# Following the race, Liu Xiang is seen lying on the track, possibly exhausted from the intense competition. He then stands up and begins to celebrate his victory, waving his arms in the air and running around the track. The crowd cheers and celebrates with him, creating a joyful atmosphere.
# The video concludes with a replay of Liu Xiang's gold medal-winning moment, emphasizing the significance of his achievement at the Athens 2004 Olympic Games.
# Throughout the video, the Olympic logo is prominently displayed, reminding viewers of the global significance of the event and the athletes' dedication and perseverance in their pursuit of victory.

query = 'tell me the athlete code of Liu Xiang'
image = ['./examples/liuxiang.mp4',]
with torch.autocast(device_type='cuda', dtype=torch.float16):
    response, _ = model.chat(tokenizer, query, image, history=his, do_sample=False, num_beams=3, use_meta=True)
print(response)
# The athlete code of Liu Xiang is 1363.

import torch
from transformers import AutoModel, AutoTokenizer

torch.set_grad_enabled(False)

# init model and tokenizer
model = AutoModel.from_pretrained('internlm/internlm-xcomposer2d5-7b-chat', torch_dtype=torch.bfloat16, trust_remote_code=True).cuda().eval()
tokenizer = AutoTokenizer.from_pretrained('internlm/internlm-xcomposer2d5-7b-chat', trust_remote_code=True)
model.tokenizer = tokenizer

query = 'Here are some frames of a video. Describe this video in detail'
image = ['./examples/liuxiang.mp4',]
with torch.autocast(device_type='cuda', dtype=torch.float16):
    response, his = model.chat(tokenizer, query, image, do_sample=False, num_beams=3, use_meta=True)
print(response)
# The video begins with a man in a red and yellow uniform standing on the starting line of a track, preparing to compete in the 110-meter hurdles at the Athens 2004 Olympic Games. He is identified as Liu Xiang, a Chinese athlete, and his bib number is 1363. The scene is set in a stadium filled with spectators, indicating the significance of the event.
# As the race begins, all the athletes start running, but Liu Xiang quickly takes the lead. However, he encounters a hurdle and knocks it over. Despite this setback, he quickly recovers and continues to run. The race is intense, with athletes from various countries competing fiercely. In the end, Liu Xiang emerges as the winner with a time of 12.91 seconds, securing the gold medal for China.
# The video then transitions to a slow-motion replay of the race, focusing on Liu Xiang's performance and the knockdown of the hurdle. This allows viewers to appreciate the skill and determination of the athlete.
# Following the race, Liu Xiang is seen lying on the track, possibly exhausted from the intense competition. He then stands up and begins to celebrate his victory, waving his arms in the air and running around the track. The crowd cheers and celebrates with him, creating a joyful atmosphere.
# The video concludes with a replay of Liu Xiang's gold medal-winning moment, emphasizing the significance of his achievement at the Athens 2004 Olympic Games.
# Throughout the video, the Olympic logo is prominently displayed, reminding viewers of the global significance of the event and the athletes' dedication and perseverance in their pursuit of victory.

query = 'tell me the athlete code of Liu Xiang'
image = ['./examples/liuxiang.mp4',]
with torch.autocast(device_type='cuda', dtype=torch.float16):
    response, _ = model.chat(tokenizer, query, image, history=his, do_sample=False, num_beams=3, use_meta=True)
print(response)
# The athlete code of Liu Xiang is 1363.

import torch
from transformers import AutoModel, AutoTokenizer

torch.set_grad_enabled(False)

# init model and tokenizer
model = AutoModel.from_pretrained('internlm/internlm-xcomposer2d5-7b-chat', torch_dtype=torch.bfloat16, trust_remote_code=True).cuda().eval()
tokenizer = AutoTokenizer.from_pretrained('internlm/internlm-xcomposer2d5-7b-chat', trust_remote_code=True)
model.tokenizer = tokenizer

query = 'Here are some frames of a video. Describe this video in detail'
image = ['./examples/liuxiang.mp4',]
with torch.autocast(device_type='cuda', dtype=torch.float16):
    response, his = model.chat(tokenizer, query, image, do_sample=False, num_beams=3, use_meta=True)
print(response)
# The video begins with a man in a red and yellow uniform standing on the starting line of a track, preparing to compete in the 110-meter hurdles at the Athens 2004 Olympic Games. He is identified as Liu Xiang, a Chinese athlete, and his bib number is 1363. The scene is set in a stadium filled with spectators, indicating the significance of the event.
# As the race begins, all the athletes start running, but Liu Xiang quickly takes the lead. However, he encounters a hurdle and knocks it over. Despite this setback, he quickly recovers and continues to run. The race is intense, with athletes from various countries competing fiercely. In the end, Liu Xiang emerges as the winner with a time of 12.91 seconds, securing the gold medal for China.
# The video then transitions to a slow-motion replay of the race, focusing on Liu Xiang's performance and the knockdown of the hurdle. This allows viewers to appreciate the skill and determination of the athlete.
# Following the race, Liu Xiang is seen lying on the track, possibly exhausted from the intense competition. He then stands up and begins to celebrate his victory, waving his arms in the air and running around the track. The crowd cheers and celebrates with him, creating a joyful atmosphere.
# The video concludes with a replay of Liu Xiang's gold medal-winning moment, emphasizing the significance of his achievement at the Athens 2004 Olympic Games.
# Throughout the video, the Olympic logo is prominently displayed, reminding viewers of the global significance of the event and the athletes' dedication and perseverance in their pursuit of victory.

query = 'tell me the athlete code of Liu Xiang'
image = ['./examples/liuxiang.mp4',]
with torch.autocast(device_type='cuda', dtype=torch.float16):
    response, _ = model.chat(tokenizer, query, image, history=his, do_sample=False, num_beams=3, use_meta=True)
print(response)
# The athlete code of Liu Xiang is 1363.

import torch
from transformers import AutoModel, AutoTokenizer

torch.set_grad_enabled(False)

# init model and tokenizer
model = AutoModel.from_pretrained('internlm/internlm-xcomposer2d5-7b-chat', torch_dtype=torch.bfloat16, trust_remote_code=True).cuda().eval()
tokenizer = AutoTokenizer.from_pretrained('internlm/internlm-xcomposer2d5-7b-chat', trust_remote_code=True)
model.tokenizer = tokenizer

query = 'Here are some frames of a video. Describe this video in detail'
image = ['./examples/liuxiang.mp4',]
with torch.autocast(device_type='cuda', dtype=torch.float16):
    response, his = model.chat(tokenizer, query, image, do_sample=False, num_beams=3, use_meta=True)
print(response)
# The video begins with a man in a red and yellow uniform standing on the starting line of a track, preparing to compete in the 110-meter hurdles at the Athens 2004 Olympic Games. He is identified as Liu Xiang, a Chinese athlete, and his bib number is 1363. The scene is set in a stadium filled with spectators, indicating the significance of the event.
# As the race begins, all the athletes start running, but Liu Xiang quickly takes the lead. However, he encounters a hurdle and knocks it over. Despite this setback, he quickly recovers and continues to run. The race is intense, with athletes from various countries competing fiercely. In the end, Liu Xiang emerges as the winner with a time of 12.91 seconds, securing the gold medal for China.
# The video then transitions to a slow-motion replay of the race, focusing on Liu Xiang's performance and the knockdown of the hurdle. This allows viewers to appreciate the skill and determination of the athlete.
# Following the race, Liu Xiang is seen lying on the track, possibly exhausted from the intense competition. He then stands up and begins to celebrate his victory, waving his arms in the air and running around the track. The crowd cheers and celebrates with him, creating a joyful atmosphere.
# The video concludes with a replay of Liu Xiang's gold medal-winning moment, emphasizing the significance of his achievement at the Athens 2004 Olympic Games.
# Throughout the video, the Olympic logo is prominently displayed, reminding viewers of the global significance of the event and the athletes' dedication and perseverance in their pursuit of victory.

query = 'tell me the athlete code of Liu Xiang'
image = ['./examples/liuxiang.mp4',]
with torch.autocast(device_type='cuda', dtype=torch.float16):
    response, _ = model.chat(tokenizer, query, image, history=his, do_sample=False, num_beams=3, use_meta=True)
print(response)
# The athlete code of Liu Xiang is 1363.