quantized DRXD1000/Phoenix - which was trained with german dpo (ultrachat_200k & ultrafeedback_binarized transl. by haoranxu/ALMA-13B) based on LeoLM/leo-mistral-hessianai-7b

7B

287 Pulls Updated 4 months ago

935571f5de1c · 98B
{ "stop": [ "<|assistant|>", "</s>", "<|system|>", "<|user|>" ] }