* Support function calling in OpenAI api server * Faster repetition penalty sampling * Support max_new_tokens generation option
0.3.0
* Full functionality of ChatGLM3 including system prompt, function call and code interpreter * Brand new OpenAI-style chat API * Add token usage information in OpenAI api server to be compatible with LangChain frontend * Fix conversion error for chatglm3-6b-32k
0.2.10
* Support ChatGLM3 in conversation mode. * Coming soon: new prompt format for system message and function call.
0.2.9
* Support InternLM 7B & 20B model architectures
0.2.8
* Metal backend support for all models (ChatGLM & ChatGLM2 & Baichuan-7B & Baichuan-13B) * Fix GLM generation on CUDA for long context
0.2.7
* Support Baichuan-7B model architecture (works for both Baichuan v1 & v2). * Minor bug fix and enhancement.