Open bigcat26 opened 9 months ago
https://pypi.org/project/rwkv/ Try: temperature = 1.0, top_p = 0.3, top_k = 0, alpha_frequency = 1, alpha_presence = 0, alpha_decay = 0.996 For alpha_frequency and alpha_presence, see "Frequency and presence penalties": https://platform.openai.com/docs/api-reference/parameter-details
我在跑chatRWKV的时候也经常碰到循环的问题,这是主要跟采样策略有关系吗?
model是RWKV-4-World-0.1B-v1-20230520-ctx4096。
比如这种
还有这种
后面试了,RWKV-4-Raven-1B5-v12-Eng98%-Other2%-20230520-ctx4096
好像会稍微好点。参数量太低就会有这种问题?