Hugging Face's logo

ABaroian
/
Apertus-8B-RLVR-GSM

Reinforcement Learning
rlvr
grpo
gsm8k
apertus
Model card Files
xet
Community
1
ABaroian commited on
Commit
c2c1bb9
·
verified ·
1 Parent(s): 253d78c

Upload folder using huggingface_hub

Browse files
Files changed (6) hide show
  1. bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +3 -0
  2. bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +3 -0
  3. bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +3 -0
  4. zero_pp_rank_0_mp_rank_00_model_states.pt +3 -0
  5. zero_pp_rank_1_mp_rank_00_model_states.pt +3 -0
  6. zero_pp_rank_2_mp_rank_00_model_states.pt +3 -0
bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:35d08dec893ceabc1c210ffa7c8c56a41ca2469a701241a641c7e95afa8519e3
3
+ size 32213363463
bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f23e462db4439840dff858263aee75d54d78409d760901a1098c4b8df66382b
3
+ size 32213363463
bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7376c57648ba982f2038b1c63afd73660d0907c7d8debe3e3488c27dbe7a6ca6
3
+ size 32213363463
zero_pp_rank_0_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce60f75d50d50b48be0bed5f36d8ee16ead211f52526f7dd6a2a19c05d1b65e4
3
+ size 294119
zero_pp_rank_1_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c58351fc85a5dc9756a36a714ef05295f23c30c7a721310fcd2f9b18493a61c
3
+ size 294119
zero_pp_rank_2_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d45840fc7e11479aa095332476d4f4108310b9607f66c42fd0c51ba117df696d
3
+ size 294119