deepseek-ai

/

DeepSeek-R1

like 12.8k

Follow

DeepSeek 104k

async def event_generator():
    input_ids = model_manager.tokenizer.encode(input_text, return_tensors="pt")
    if model_manager.model.device.type == 'cuda':
        input_ids = input_ids.cuda()
    generated_ids = []

    for _ in range(max_length):
        if await request.is_disconnected():
            break
        output = model_manager.model.generate(input_ids, max_new_tokens=1, return_dict_in_generate=True,output_scores=True)
        next_token_id = output.sequences[0, -1].item()
        generated_ids.append(next_token_id)
        input_ids = output.sequences

        # 解码并输出当前生成的词
        # 检查词元 ID 是否有效
        if next_token_id < len(model_manager.tokenizer):
            # 解码并输出当前生成的词
            print(f"解码并输出当前生成的词 : {model_manager.tokenizer}")
            print(f" 解码并输出当前生成的词 next_token_id: {next_token_id}")
            current_word = model_manager.tokenizer.decode([next_token_id], skip_special_tokens=True)
            print(f"")
            print(current_word, end="", flush=True)
            print(f"")
        else:
            print(f"Invalid token ID: {next_token_id}", end="", flush=True)

        event_data = {
            "event": "message",
            "data": current_word
        }
        # 打印要发送的事件数据
        print(f"Sending SSE data: {event_data}")
        yield event_data
        await asyncio.sleep(0.1)
        print(f"model_manager.tokenizer.eos_token_id: {model_manager.tokenizer.eos_token_id}")
        print(f"next_token_id: {next_token_id}")
        # 如果生成了结束标记，停止生成
        if next_token_id == model_manager.tokenizer.eos_token_id:
            break

输出结果

解码并输出当前生成的词 : LlamaTokenizerFast(name_or_path='../DeepSeek-R1-Distill-Qwen-7B', vocab_size=151643, model_max_length=16384, is_fast=True, padding_side='left', truncation_side='right', special_tokens={'bos_token': '<｜begin▁of▁sentence｜>', 'eos_token': '<｜end▁of▁sentence｜>', 'pad_token': '<｜end▁of▁sentence｜>'}, clean_up_tokenization_spaces=False), added_tokens_decoder={
151643: AddedToken("<｜end▁of▁sentence｜>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151644: AddedToken("<｜User｜>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151645: AddedToken("<｜Assistant｜>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151646: AddedToken("<｜begin▁of▁sentence｜>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151647: AddedToken("<|EOT|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151648: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151649: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
151657: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151658: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False),
}
解码并输出当前生成的词 next_token_id: 242
�
Sending SSE data: {'event': 'message', 'data': '�'}
model_manager.tokenizer.eos_token_id: 151643
next_token_id: 242

请问 � 这个乱码什么问题导致