Qwen1.5-14B-Chat推理乱码

[suckseed5]

但是Qwen-7B-Chat是可以正常推理的，有什么解决办法吗？

[dosubot]

To address the issue with Qwen1.5-14B-Chat producing garbled text, consider the following steps:

1. Check Encoding: Ensure all requests are UTF-8 encoded, especially since your payload includes Chinese characters. Set the Content-Type header to application/json; charset=utf-8. Verify both the request encoding and the server's response encoding are correctly set to UTF-8.

2. Model Configuration: The difference in behavior between Qwen1.5-14B-Chat and Qwen-7B-Chat could be due to their configurations. The larger model may have specific inference issues or require different handling compared to the smaller model.

3. Parameter Handling: Review how the "stream," "temperature," and "max_tokens" parameters are set in your request. Incorrect values or handling of these parameters could impact the model's output.

Ensure that the API and your request handling are correctly configured for the character set and model parameters you're using.

Details

Sources

• Qwen-1_8B-Chat文字对答出现乱码
• [BUG] 大部分模型运行正常，qwen-14b-chat-int8/int4均不加载模型，也不报错，卡住不动
• [BUG] Qianwen-14B 模型问答有问题
• 使用 Baichuan2-7b 模型，对话乱码
• server/model_workers/qwen.py
• configs/model_config.py.example
• tests/test_online_api.py
• knowledge_base/samples/content/test_files/langchain-ChatGLM_closed.jsonl
• server/chat/completion.py
• server/chat/chat.py
• server/chat/agent_chat.py
• server/api.py
• chains/llmchain_with_history.py
• server/agent/custom_agent/ChatGLM3Agent.py
• server/chat/knowledge_base_chat.py
• server/chat/search_engine_chat.py

About Dosu
This response is meant to be useful and save you time. It is not meant to be a precise solution, but rather a starting point for your own research.

Help me be more useful! Please leave a 👍 if this is helpful and 👎 if it is irrelevant.

To continue the conversation, mention @dosu.