payelb
/

aligned_llama32_1b_ultrafeedback_fixed1k_mars

Model card Files Files and versions

aligned_llama32_1b_ultrafeedback_fixed1k_mars

Commit History

Add PPO value head weights (value_head.pt)

180c459
verified

payelb commited on Jan 16

Upload tokenizer

9ef2378
verified

payelb commited on Jan 16

Upload LlamaForCausalLM

59aa4c2
verified

payelb commited on Jan 16

initial commit

09ecf6b
verified

payelb commited on Jan 16