InternLM
IXC-2.5-Reward inference error
@yuhangzang @panzhang0212 我的环境是安装readme.txt里面安装的，版本都是一致的，权重我下载好到了本地目录：./internlm-xcomposer2d5-7b-reward下，下面是推理的代码：
import torch
from transformers import AutoModel, AutoTokenizer
model = AutoModel.from_pretrained(
"./internlm-xcomposer2d5-7b-reward",
device_map="cuda",
torch_dtype=torch.float16,
trust_remote_code=True,
)
tokenizer = AutoTokenizer.from_pretrained("./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 = ['/cache/internlm/internlm-xcomposer2d5-7b-reward/examples/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)
运行过程中报错：
python intervl_infer.py
/home/ma-user/anaconda3/envs/cogvlm2plus/lib/python3.11/site-packages/transformers/utils/generic.py:311: UserWarning: torch.utils._pytree._register_pytree_node is deprecated. Please use torch.utils._pytree.register_pytree_node instead.
torch.utils._pytree._register_pytree_node(
/home/ma-user/anaconda3/envs/cogvlm2plus/lib/python3.11/site-packages/transformers/utils/generic.py:311: UserWarning: torch.utils._pytree._register_pytree_node is deprecated. Please use torch.utils._pytree.register_pytree_node instead.
torch.utils._pytree._register_pytree_node(
Set max length to 16384
/home/ma-user/anaconda3/envs/cogvlm2plus/lib/python3.11/site-packages/huggingface_hub/file_download.py:1142: FutureWarning: resume_download is deprecated and will be removed in version 1.0.0. Downloads always resume when possible. If you want to force a new download, use force_download=True.
warnings.warn(
urllib3.exceptions.SSLError: [SSL: CERTIFICATE_VERIFY_FAILED] certificate verify failed: self-signed certificate in certificate chain (_ssl.c:1006)
The above exception was the direct cause of the following exception:
Traceback (most recent call last): File "/home/ma-user/anaconda3/envs/cogvlm2plus/lib/python3.11/site-packages/requests/adapters.py", line 667, in send resp = conn.urlopen( ^^^^^^^^^^^^^ File "/home/ma-user/anaconda3/envs/cogvlm2plus/lib/python3.11/site-packages/urllib3/connectionpool.py", line 844, in urlopen retries = retries.increment( ^^^^^^^^^^^^^^^^^^ File "/home/ma-user/anaconda3/envs/cogvlm2plus/lib/python3.11/site-packages/urllib3/util/retry.py", line 515, in increment raise MaxRetryError(pool, url, reason) from reason # type: ignore[arg-type] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ urllib3.exceptions.MaxRetryError: HTTPSConnectionPool(host='cdn-lfs-us-1.hf.co', port=443): Max retries exceeded with url: /repos/74/0b/740b73611f9bb4cb2bf750ef61adee257d59eccbbce837c3a8fa43642f52697f/f2345623c2fe3bd46d9251d7dfdbfc8d55cea5411a1e42940ee15cde730d45c4?response-content-disposition=inline%3B+filename*%3DUTF-8%27%27pytorch_model.bin%3B+filename%3D%22pytorch_model.bin%22%3B&response-content-type=application%2Foctet-stream&Expires=1741711437&Policy=eyJTdGF0ZW1lbnQiOlt7IkNvbmRpdGlvbiI6eyJEYXRlTGVzc1RoYW4iOnsiQVdTOkVwb2NoVGltZSI6MTc0MTcxMTQzN319LCJSZXNvdXJjZSI6Imh0dHBzOi8vY2RuLWxmcy11cy0xLmhmLmNvL3JlcG9zLzc0LzBiLzc0MGI3MzYxMWY5YmI0Y2IyYmY3NTBlZjYxYWRlZTI1N2Q1OWVjY2JiY2U4MzdjM2E4ZmE0MzY0MmY1MjY5N2YvZjIzNDU2MjNjMmZlM2JkNDZkOTI1MWQ3ZGZkYmZjOGQ1NWNlYTU0MTFhMWU0Mjk0MGVlMTVjZGU3MzBkNDVjND9yZXNwb25zZS1jb250ZW50LWRpc3Bvc2l0aW9uPSomcmVzcG9uc2UtY29udGVudC10eXBlPSoifV19&Signature=Wmp0So3mIUjfrf2I92PXBqnoEenUpPTJlsc1yXfJ593JqzB7Gn5Riq2kiu8fFISuyOtR0SmjSEItwPHFoBAxBDNDGR6WkscoIfSn8wAJFQwQFYfUIIwEJJFEEADAD5s1aYPxWuwCfBy1J7P2UzyHNjnFuOaFGMGQ5UORXLzu2KrLBgKFeEicoz9AdRPYfm-Xcs6QJW9IU3ZmtREHCr~CWYNNT3nqqkRoKEJDJQP5CIFGixbjoqd34iAWYzOCb-GWIDkMYGnYegm3Ik9MbOMwMIsgPcVRQOKIGMQu5wXuZAQ~L6k~ulalPNLzf89atxf8XJPC-2a3IS97hcW~r1dJBQ_&Key-Pair-Id=K24J24Z295AEI9 (Caused by SSLError(SSLCertVerificationError(1, '[SSL: CERTIFICATE_VERIFY_FAILED] certificate verify failed: self-signed certificate in certificate chain (_ssl.c:1006)')))
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "/cache/intervl_infer.py", line 10, in
这是huggingface仓库里面的模型权重文件不全吗？期待您的解答
