llama-3-8b-base-new-dpo-ultrafeedback-4xh200-batch-128-q_t-0.43-s_star-0.4-20260429-230725/step_0000356.npy at e8efbe1ca94d7d9b0117b88956970ed487913eed - llama-3-8b-base-new-dpo-ultrafeedback-4xh200-batch-128-q_t-0.43-s_star-0.4-20260429-230725 - Gitea: Git with a cup of tea

W-61/llama-3-8b-base-new-dpo-ultrafeedback-4xh200-batch-128-q_t-0.43-s_star-0.4-20260429-230725

Files

ModelHub XC e8efbe1ca9 初始化项目，由ModelHub XC社区提供模型

Model: W-61/llama-3-8b-base-new-dpo-ultrafeedback-4xh200-batch-128-q_t-0.43-s_star-0.4-20260429-230725
Source: Original Platform

2026-05-20 08:27:04 +08:00

4 lines

128 B

Plaintext

Raw Blame History

	`version https://git-lfs.github.com/spec/v1`
	`oid sha256:5c06b66cf434b9dab4ba11df07156e262251c7d855a59e75c0ff68a6aa74ad3b`
	`size 640`