An experimental fine-tune of Yi 34b 200k using bagel(opens in new tab). This is the version of the fine-tune before direct preference optimization (DPO) has been applied. DPO performs better on benchmarks, but this version is likely better for creative writing, roleplay, etc.
Modalities
Context
200K
Released
Jan 5, 2024
Knowledge Cutoff
Jun 2023
Token volume and request traffic to this model over time.
An experimental fine-tune of Yi 34b 200k using bagel. This is the version of the fine-tune before direct preference optimization (DPO) has been applied. DPO performs better on benchmarks, but this version is likely better for creative writing, roleplay, etc.
Bagel 34B v0.2 has a 200,000 token context window.
Bagel 34B v0.2 was released on January 5, 2024. Its knowledge cutoff is June 30, 2023.