NotImplementedError when running official example code of InternLM-XComposer-2.5-Reward #473
Assignees
Comments
|
This error is raised when you use 'device_map='auto' to load the model. You may try to load the model like this: |
|
Hi @yuhangzang Thanks for your quickly reply, this error is happed when I use My environment is built follow the official instruction: with and I use the official example code on Huggingface: import torch
from transformers import AutoModel, AutoTokenizer
model = AutoModel.from_pretrained(
"internlm/internlm-xcomposer2d5-7b-reward",
device_map="cuda",
torch_dtype=torch.float16,
trust_remote_code=True,
)
tokenizer = AutoTokenizer.from_pretrained("internlm/internlm-xcomposer2d5-7b-reward", trust_remote_code=True)
model.tokenizer = tokenizer
chat_1 = [
{"role": "user", "content": 'I want to buy a car from the input image, analyze the advantages and weaknesses.'},
{"role": "assistant", "content": "The car in the image is a Mercedes-Benz G-Class. This is a luxury SUV known for its ruggedness, off-road capability, and iconic boxy design. Here's an analysis of its advantages and weaknesses: Advantages: Off-road capability: The G-Class is built on a robust ladder frame chassis and has a powerful engine, making it highly capable in off-road conditions. It features a low-range transfer case, locking differentials, and a high ground clearance. Luxury and comfort: Despite its rugged exterior, the G-Class offers a luxurious interior with high-quality materials, comfortable seats, and advanced technology features. Iconic design: The distinctive boxy shape of the G-Class has made it a cult classic. It's instantly recognizable and has a timeless appeal. Strong resale value: Due to its exclusivity and desirability, the G-Class tends to hold its value well over time. Weaknesses: Fuel efficiency: The G-Class is not known for its fuel efficiency, especially with the larger engine options. Ride quality: The firm suspension is designed for off-road performance, which can make the ride a bit bumpy on paved roads. Price: The G-Class is a very expensive vehicle, even for a luxury SUV. Size and maneuverability: The large size of the G-Class can make it challenging to park and maneuver in tight spaces."}
]
chat_2 = [
{"role": "user", "content": 'I want to buy a car from the input image, analyze the advantages and weaknesses.'},
{"role": "assistant", "content": "Based on the image, it appears to be a Ferrari F8 Tributo. Advantages: Performance: Ferraris are renowned for their exceptional performance. The F8 Tributo is no exception, boasting a powerful twin-turbocharged V8 engine that delivers exhilarating acceleration and top speed. Handling: Ferraris are known for their precise handling and agility. The F8 Tributo continues this tradition, with advanced aerodynamics and sophisticated suspension systems ensuring a thrilling driving experience. Design: Ferrari is synonymous with iconic and head-turning designs. The F8 Tributo is a testament to this, featuring sleek lines, aggressive styling, and a captivating presence. Exclusivity: Owning a Ferrari is a status symbol. It represents luxury, exclusivity, and a passion for high-performance automobiles. Weaknesses: Price: Ferraris come with a hefty price tag. The F8 Tributo is no exception, making it an investment for those with significant financial resources. Fuel Efficiency: High-performance sports cars like the F8 Tributo are not known for their fuel efficiency. You can expect lower miles per gallon compared to everyday vehicles. Maintenance Costs: Owning a Ferrari comes with associated maintenance costs, which can be higher than those for regular cars. Practicality: The F8 Tributo is primarily a two-seater sports car, making it less practical for everyday use or carrying passengers. Ride Comfort: While the F8 Tributo offers a thrilling driving experience, its stiff suspension might not be ideal for long-distance comfort."}
]
image = ['eval/InternLM-XComposer-2.5-Reward/cars1.jpg']
hd_num = 9
# get reward score for a single chat
with torch.autocast(device_type='cuda', dtype=torch.float16):
score1 = model.get_score(chat_1, image, hd_num=hd_num)
score2 = model.get_score(chat_2, image, hd_num=hd_num)
print("score1: ", score1)
print("score2: ", score2)
# >>> score1: 5.76
# >>> score2: -2.84375
# batch inference, get multiple scores at once
with torch.autocast(device_type='cuda', dtype=torch.float16):
scores = model.get_scores([chat_1, chat_2], [image, image], hd_num=hd_num)
print("scores: ", scores)
# >>> scores: [5.76171875, -2.845703125]
# compare whether chat_1 is better than chat_2
with torch.autocast(device_type='cuda', dtype=torch.float16):
compare_res = model.compare(chat_1, image, chat_2, image, hd_num=hd_num)
print("compare_res: ", compare_res)
# >>> compare_res: True
# rank multiple chats, it will return the ranking index of each chat
# the chat with the highest score will have ranking index as 0
with torch.autocast(device_type='cuda', dtype=torch.float16):
rank_res = model.rank([chat_1, chat_2], [image, image], hd_num=hd_num)
print("rank_res: ", rank_res) # lower index means higher score
# >>> rank_res: [0, 1] |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
When I run the official example code, I noticed there are warnings:
which may lead to further errors:
The text was updated successfully, but these errors were encountered: