xldistance
xldistance
Mine is the same, version 1.1.11 server-side and client-side fill in the .pub key or key mismatch error, and then with version 1.1.10-3 can be used normally!
query_history应该在交易接口里面调用而不是在主程序中调用
Version 0.3.3 is still not compatible with OpenAIEmbedding The code I run is as follows ``` text_embedder = OpenAIEmbedding( # ollama本地嵌入模型 api_key="ollama", api_base="http://localhost:11434/v1", model="bge:m3", deployment_name="bge:m3", api_type=OpenaiApiType.OpenAI, max_retries=20, ) ``` The...
``` llama-server -m E:\models\gguf\THUDM_GLM-Z1-32B-0414-Q8_0.gguf --port 8080 -ngl 64 --temp 0.5 -c 32768 --override-kv tokenizer.ggml.eos_token_id=int:151336 --override-kv glm4.rope.dimension_count=int:64 --chat-template chatglm4 ``` You can run the THUDM_GLM-Z1-32B model normally with the above command.
> I got it to work correctly now. > > 1. We need to fix the conversion code to take care of `partial_rotary_factor`. I'll leave it to the experts here....
会支持微软的graphrag吗
 Running /api/embeddings for a single file only requests embedding every two seconds, which is very slow
我尝试在openai.py里面加上以下代码但是没起作用，估计是加错地方了 ``` response = re.sub(r'.*?', '', response, flags=re.DOTALL).strip() ```
> 换缓存目录没用，关掉“启动流式相应”解决的 是的llama server api需要关闭流式回答才能正常使用
难道是全局搜索只能用训练数据的模型来提问吗