--- license: apache-2.0 --- This is a experimental model, yet it is the Most powerful RNN model in the world. # Mobius RWKV r6 chat 12B 16k Mobius is a RWKV v6 arch chat model, benifit from [Matrix-Valued States and Dynamic Recurrence](https://arxiv.org/abs/2404.05892) ## Introduction Mobius is a RWKV v6 arch model, a state based RNN+CNN+Transformer Mixed language model pretrained on a certain amount of data. In comparison with the previous released Mobius, the improvements include: * Only 24G Vram to run this model locally with fp16; * Significant performance improvement in chinese; * Stable support of 16K context length. * function call support ; ## Usage Chat format: User: xxxx\n\nAssistant: xxx\n\n Recommend Temp and topp: 1 0.3 function call format example: ``` System: You are a helpful assistant with access to the following functions. Use them if required -{ "name": "get_exchange_rate", "description": "Get the exchange rate between two currencies", "parameters": { "type": "object", "properties": { "base_currency": { "type": "string", "description": "The currency to convert from" }, "target_currency": { "type": "string", "description": "The currency to convert to" } }, "required": [ "base_currency", "target_currency" ] } } User: Hi, I need to know the exchange rate from USD to EUR Assistant: xxxx Obersavtion: xxxx Assistant: xxxx ``` ## More details Mobius 12B 16k based on RWKV v6 arch, which is leading state based RNN+CNN+Transformer Mixed large language model which focus opensouce community * 10~100 trainning/inference cost reduce; * state based,selected memory, which mean good at grok; * community support. ## requirements 21.9G vram to run fp16, 13.7G for int8, 7.2 for nf4 with Ai00 server. * [RWKV Runner](https://github.com/josStorer/RWKV-Runner) * [Ai00 server](https://github.com/cgisky1980/ai00_rwkv_server) ## Benchmark ceval 63.53 cmmlu 76.07