payelb
/

aligned_llama32_1b_ultrafeedback_fixed1k_noaug

Model card Files Files and versions

aligned_llama32_1b_ultrafeedback_fixed1k_noaug

Commit History

Add PPO value head weights (value_head.pt)

9f809af
verified

payelb commited on Jan 16

Upload tokenizer

b8c382b
verified

payelb commited on Jan 16

Upload LlamaForCausalLM

4c74b59
verified

payelb commited on Jan 16

initial commit

c020ae7
verified

payelb commited on Jan 16