Llama base models with a chat template that still use eos_token
Zack Ankner
ankner
AI & ML interests
None yet
Recent Activity
published
a model
8 days ago
ankner/llama3.2_1b_instruct
updated
a model
3 months ago
ankner/chat-smol-135m-rm
updated
a model
3 months ago
ankner/chat-smol-360m-rm
Organizations
Base Models With Chat Templates
Llama base models with a chat template that still use eos_token
Hydra Decoding
Paper: https://arxiv.org/abs/2402.05109 | Code: https://github.com/zankner/Hydra
Oracle 2 Proxy Models
Oracle 2 Proxy Data
Multi Judgement Oversight
Critique-out-Loud Reward Models
Paper: https://arxiv.org/abs/2408.11791 | Code: https://github.com/zankner/CLoud