from modelscope import AutoModelForCausalLM, AutoTokenizer
model_name = "iic/QwenLong-L1-32B"
# load the tokenizer and the model
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)
# prepare the model input
template = """Please read the following text and answer the question below.
<text>
$DOC$
</text>
$Q$
Format your response as follows: "Therefore, the answer is (insert answer here)"."""
context = "<YOUR_CONTEXT_HERE>" 
question = "<YOUR_QUESTION_HERE>"
prompt = template.replace('$DOC$', context.strip()).replace('$Q$', question.strip())
messages = [
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)
# conduct text completion
generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=10000,
    temperature=0.7,
    top_p=0.95
)
output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist() 
# parsing thinking content
try:
    # rindex finding 151649 (</think>)
    index = len(output_ids) - output_ids[::-1].index(151649)
except ValueError:
    index = 0
thinking_content = tokenizer.decode(output_ids[:index], skip_special_tokens=True).strip("\n")
content = tokenizer.decode(output_ids[index:], skip_special_tokens=True).strip("\n")
print("thinking content:", thinking_content)
print("content:", content)

from modelscope import Qwen2_5_VLForConditionalGeneration, AutoTokenizer, AutoProcessor
from qwen_vl_utils import process_vision_info
# default: Load the model on the available device(s)
model = Qwen2_5_VLForConditionalGeneration.from_pretrained(
    "XiaomiMiMo/MiMo-VL-7B-SFT", torch_dtype="auto", device_map="auto"
)
# default processer
processor = AutoProcessor.from_pretrained("XiaomiMiMo/MiMo-VL-7B-SFT")
messages = [
    {
        "role": "user",
        "content": [
            {
                "type": "image",
                "image": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-VL/assets/demo.jpeg",
            },
            {"type": "text", "text": "Describe this image."},
        ],
    }
]
# Preparation for inference
text = processor.apply_chat_template(
    messages, tokenize=False, add_generation_prompt=True
)
image_inputs, video_inputs = process_vision_info(messages)
inputs = processor(
    text=[text],
    images=image_inputs,
    videos=video_inputs,
    padding=True,
    return_tensors="pt",
)
inputs = inputs.to("cuda")
# Inference: Generation of the output
generated_ids = model.generate(**inputs, max_new_tokens=128)
generated_ids_trimmed = [
    out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)
]
output_text = processor.batch_decode(
    generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False
)
print(output_text)

from modelscope import AutoModelForCausalLM, AutoTokenizer
model_name = "sarvamai/sarvam-m"
# load the tokenizer and the model
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name, torch_dtype="auto", device_map="auto"
)
# prepare the model input
prompt = "Who are you and what is your purpose on this planet?"
messages = [{"role": "user", "content": prompt}]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    enable_thinking=True,  # Switches between thinking and non-thinking modes. Default is True.
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)
# conduct text completion
generated_ids = model.generate(**model_inputs, max_new_tokens=8192)
output_ids = generated_ids[0][len(model_inputs.input_ids[0]) :].tolist()
output_text = tokenizer.decode(output_ids)
if "</think>" in output_text:
    reasoning_content = output_text.split("</think>")[0].rstrip("\n")
    content = output_text.split("</think>")[-1].lstrip("\n").rstrip("</s>")
else:
    reasoning_content = ""
    content = output_text.rstrip("</s>")
print("reasoning content:", reasoning_content)
print("content:", content)