internlm-xcomposer2d5-7b

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
ckpt_path = "internlm/internlm-xcomposer2d5-7b"
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"
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"
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"
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"
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"
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"
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"
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', torch_dtype=torch.bfloat16, trust_remote_code=True).cuda().eval()
tokenizer = AutoTokenizer.from_pretrained('internlm/internlm-xcomposer2d5-7b', 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 opens with a shot of an athlete, dressed in a red and yellow uniform with the word "CHINA" emblazoned across the front, preparing for a race. 
#The athlete, Liu Xiang, is seen in a crouched position, focused and ready, with the Olympic rings visible in the background, indicating the prestigious setting of the Olympic Games. As the race commences, the athletes are seen sprinting towards the hurdles, their determination evident in their powerful strides. 
#The camera captures the intensity of the competition, with the athletes' numbers and times displayed on the screen, providing a real-time update on their performance. The race reaches a climax as Liu Xiang, still in his red and yellow uniform, triumphantly crosses the finish line, his arms raised in victory. 
#The crowd in the stands erupts into cheers, their excitement palpable as they witness the athlete's success. The video concludes with a close-up shot of Liu Xiang, still basking in the glory of his victory, as the Olympic rings continue to symbolize the significance of the event.

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, as displayed on his uniform in the video, 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', torch_dtype=torch.bfloat16, trust_remote_code=True).cuda().eval()
tokenizer = AutoTokenizer.from_pretrained('internlm/internlm-xcomposer2d5-7b', 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 opens with a shot of an athlete, dressed in a red and yellow uniform with the word "CHINA" emblazoned across the front, preparing for a race. 
#The athlete, Liu Xiang, is seen in a crouched position, focused and ready, with the Olympic rings visible in the background, indicating the prestigious setting of the Olympic Games. As the race commences, the athletes are seen sprinting towards the hurdles, their determination evident in their powerful strides. 
#The camera captures the intensity of the competition, with the athletes' numbers and times displayed on the screen, providing a real-time update on their performance. The race reaches a climax as Liu Xiang, still in his red and yellow uniform, triumphantly crosses the finish line, his arms raised in victory. 
#The crowd in the stands erupts into cheers, their excitement palpable as they witness the athlete's success. The video concludes with a close-up shot of Liu Xiang, still basking in the glory of his victory, as the Olympic rings continue to symbolize the significance of the event.

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, as displayed on his uniform in the video, 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', torch_dtype=torch.bfloat16, trust_remote_code=True).cuda().eval()
tokenizer = AutoTokenizer.from_pretrained('internlm/internlm-xcomposer2d5-7b', 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 opens with a shot of an athlete, dressed in a red and yellow uniform with the word "CHINA" emblazoned across the front, preparing for a race. 
#The athlete, Liu Xiang, is seen in a crouched position, focused and ready, with the Olympic rings visible in the background, indicating the prestigious setting of the Olympic Games. As the race commences, the athletes are seen sprinting towards the hurdles, their determination evident in their powerful strides. 
#The camera captures the intensity of the competition, with the athletes' numbers and times displayed on the screen, providing a real-time update on their performance. The race reaches a climax as Liu Xiang, still in his red and yellow uniform, triumphantly crosses the finish line, his arms raised in victory. 
#The crowd in the stands erupts into cheers, their excitement palpable as they witness the athlete's success. The video concludes with a close-up shot of Liu Xiang, still basking in the glory of his victory, as the Olympic rings continue to symbolize the significance of the event.

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, as displayed on his uniform in the video, 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', torch_dtype=torch.bfloat16, trust_remote_code=True).cuda().eval()
tokenizer = AutoTokenizer.from_pretrained('internlm/internlm-xcomposer2d5-7b', 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 opens with a shot of an athlete, dressed in a red and yellow uniform with the word "CHINA" emblazoned across the front, preparing for a race. 
#The athlete, Liu Xiang, is seen in a crouched position, focused and ready, with the Olympic rings visible in the background, indicating the prestigious setting of the Olympic Games. As the race commences, the athletes are seen sprinting towards the hurdles, their determination evident in their powerful strides. 
#The camera captures the intensity of the competition, with the athletes' numbers and times displayed on the screen, providing a real-time update on their performance. The race reaches a climax as Liu Xiang, still in his red and yellow uniform, triumphantly crosses the finish line, his arms raised in victory. 
#The crowd in the stands erupts into cheers, their excitement palpable as they witness the athlete's success. The video concludes with a close-up shot of Liu Xiang, still basking in the glory of his victory, as the Olympic rings continue to symbolize the significance of the event.

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, as displayed on his uniform in the video, 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', torch_dtype=torch.bfloat16, trust_remote_code=True).cuda().eval()
tokenizer = AutoTokenizer.from_pretrained('internlm/internlm-xcomposer2d5-7b', 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 opens with a shot of an athlete, dressed in a red and yellow uniform with the word "CHINA" emblazoned across the front, preparing for a race. 
#The athlete, Liu Xiang, is seen in a crouched position, focused and ready, with the Olympic rings visible in the background, indicating the prestigious setting of the Olympic Games. As the race commences, the athletes are seen sprinting towards the hurdles, their determination evident in their powerful strides. 
#The camera captures the intensity of the competition, with the athletes' numbers and times displayed on the screen, providing a real-time update on their performance. The race reaches a climax as Liu Xiang, still in his red and yellow uniform, triumphantly crosses the finish line, his arms raised in victory. 
#The crowd in the stands erupts into cheers, their excitement palpable as they witness the athlete's success. The video concludes with a close-up shot of Liu Xiang, still basking in the glory of his victory, as the Olympic rings continue to symbolize the significance of the event.

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, as displayed on his uniform in the video, 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', torch_dtype=torch.bfloat16, trust_remote_code=True).cuda().eval()
tokenizer = AutoTokenizer.from_pretrained('internlm/internlm-xcomposer2d5-7b', 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 opens with a shot of an athlete, dressed in a red and yellow uniform with the word "CHINA" emblazoned across the front, preparing for a race. 
#The athlete, Liu Xiang, is seen in a crouched position, focused and ready, with the Olympic rings visible in the background, indicating the prestigious setting of the Olympic Games. As the race commences, the athletes are seen sprinting towards the hurdles, their determination evident in their powerful strides. 
#The camera captures the intensity of the competition, with the athletes' numbers and times displayed on the screen, providing a real-time update on their performance. The race reaches a climax as Liu Xiang, still in his red and yellow uniform, triumphantly crosses the finish line, his arms raised in victory. 
#The crowd in the stands erupts into cheers, their excitement palpable as they witness the athlete's success. The video concludes with a close-up shot of Liu Xiang, still basking in the glory of his victory, as the Olympic rings continue to symbolize the significance of the event.

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, as displayed on his uniform in the video, 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', torch_dtype=torch.bfloat16, trust_remote_code=True).cuda().eval()
tokenizer = AutoTokenizer.from_pretrained('internlm/internlm-xcomposer2d5-7b', 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 opens with a shot of an athlete, dressed in a red and yellow uniform with the word "CHINA" emblazoned across the front, preparing for a race. 
#The athlete, Liu Xiang, is seen in a crouched position, focused and ready, with the Olympic rings visible in the background, indicating the prestigious setting of the Olympic Games. As the race commences, the athletes are seen sprinting towards the hurdles, their determination evident in their powerful strides. 
#The camera captures the intensity of the competition, with the athletes' numbers and times displayed on the screen, providing a real-time update on their performance. The race reaches a climax as Liu Xiang, still in his red and yellow uniform, triumphantly crosses the finish line, his arms raised in victory. 
#The crowd in the stands erupts into cheers, their excitement palpable as they witness the athlete's success. The video concludes with a close-up shot of Liu Xiang, still basking in the glory of his victory, as the Olympic rings continue to symbolize the significance of the event.

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, as displayed on his uniform in the video, 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', torch_dtype=torch.bfloat16, trust_remote_code=True).cuda().eval()
tokenizer = AutoTokenizer.from_pretrained('internlm/internlm-xcomposer2d5-7b', 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 opens with a shot of an athlete, dressed in a red and yellow uniform with the word "CHINA" emblazoned across the front, preparing for a race. 
#The athlete, Liu Xiang, is seen in a crouched position, focused and ready, with the Olympic rings visible in the background, indicating the prestigious setting of the Olympic Games. As the race commences, the athletes are seen sprinting towards the hurdles, their determination evident in their powerful strides. 
#The camera captures the intensity of the competition, with the athletes' numbers and times displayed on the screen, providing a real-time update on their performance. The race reaches a climax as Liu Xiang, still in his red and yellow uniform, triumphantly crosses the finish line, his arms raised in victory. 
#The crowd in the stands erupts into cheers, their excitement palpable as they witness the athlete's success. The video concludes with a close-up shot of Liu Xiang, still basking in the glory of his victory, as the Olympic rings continue to symbolize the significance of the event.

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, as displayed on his uniform in the video, is "1363".