chatglm4v support

[qiuxin2012]

Description

glm-4v-9b support

[qiuxin2012]

Example code:

from PIL import Image
from ipex_llm.transformers import AutoModelForCausalLM
from transformers import AutoTokenizer
import torch

device = "xpu"

tokenizer = AutoTokenizer.from_pretrained("/mnt/disk1/models/glm-4v-9b", trust_remote_code=True)

query = '描述这张图片'
image = Image.open("./a.jpg").convert('RGB')
inputs = tokenizer.apply_chat_template([{"role": "user", "image": image, "content": query}],
                                       add_generation_prompt=True, tokenize=True, return_tensors="pt",
                                       return_dict=True)  # chat mode
inputs = inputs.to(device)
model = AutoModelForCausalLM.from_pretrained(
    "/mnt/disk1/models/glm-4v-9b",
    cpu_embedding=True,
    load_in_4bit=True,
    low_cpu_mem_usage=True,
    trust_remote_code=True
).half().to(device).eval()

gen_kwargs = {"max_length": 2500, "do_sample": True, "top_k": 1}
with torch.no_grad():
    outputs = model.generate(**inputs, **gen_kwargs)
    outputs = outputs[:, inputs['input_ids'].shape[1]:]
    print(tokenizer.decode(outputs[0]))

Output:

图片展示了一个日落时分的湖泊景色。太阳正处于地平线附近，将天空染成了橙红色。湖面平静如镜，反射出太阳的光芒和周围的景色。远处可以看到轮廓分明的山脉，山脚下似乎有一些建筑或房屋。整个场景显得宁静而美丽。 <|endoftext|>

[lalalapotter]

LGTM