Star179
224
代码介绍
代码
Issues55
Pull Requests52
流水线
Actions
讨论
Wiki
项目成员54
分析
项目设置
Star179
224
  1. MindSpeed-LLM
  2. /
  3. tests
  4. /
  5. poc
  6. /
  7. deepseek3
ascend-robotascend-robotfeat(pytorch): add deepseek3 8p and 64p scripts in A5
c796a1cd创建于 9 天前历史提交
文件最后提交记录最后更新时间
pretrain_deepseek3_60b_4k_128die_A3_ptd.sh
[pytorch][sh]add deepseek3_60b A+X in poc2 个月前
pretrain_deepseek3_671b_4k_512die_A2_ptd.sh
fix(pytorch):add ckpt-format argument to scripts2 个月前
pretrain_deepseek3_671b_4k_512die_A3_ptd.sh
fix(pytorch):add ckpt-format argument to scripts2 个月前
pretrain_deepseek3_671b_4k_drop_512die_A3_ptd.sh
fix(pytorch):add ckpt-format argument to scripts2 个月前
pretrain_deepsekk3_60b_4k_128die_A+X_ptd.sh
[pytorch][sh]add deepseek3_60b A+X in poc2 个月前