Hugging Face's logo

bensondccnqwc
/
tmp-yv08a

Safetensors
Model card Files
xet
Community
bensondccnqwc commited on
Commit
fb9b6ed
·
verified ·
1 Parent(s): ca2bb24

Add files using upload-large-folder tool

Browse files
Files changed (5) hide show
  1. .gitattributes +1 -0
  2. reinforce_pp_deepmath_train_sample_6144_context_4k_Qwen3-8B-Base_max_response4096_batch1024_ppomini256_rollout8_vllm/global_step_30/actor/huggingface/model-00001-of-00004.safetensors +3 -0
  3. reinforce_pp_deepmath_train_sample_6144_context_4k_Qwen3-8B-Base_max_response4096_batch1024_ppomini256_rollout8_vllm/global_step_30/actor/huggingface/model-00002-of-00004.safetensors +3 -0
  4. reinforce_pp_deepmath_train_sample_6144_context_4k_Qwen3-8B-Base_max_response4096_batch1024_ppomini256_rollout8_vllm/global_step_60/actor/huggingface/tokenizer.json +3 -0
  5. reinforce_pp_deepmath_train_sample_6144_context_4k_Qwen3-8B-Base_max_response4096_batch1024_ppomini256_rollout8_vllm/global_step_70/data.pt +3 -0
.gitattributes CHANGED
@@ -69,3 +69,4 @@ reinforce_pp_deepmath_train_sample_6144_context_4k_Qwen3-8B-Base_max_response409
69
  reinforce_pp_deepmath_train_sample_6144_context_4k_Qwen3-8B-Base_max_response4096_batch1024_ppomini256_rollout8_vllm/global_step_30/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
70
  reinforce_pp_deepmath_train_sample_6144_context_4k_Qwen3-8B-Base_max_response4096_batch1024_ppomini256_rollout8_vllm/global_step_40/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
71
  reinforce_pp_deepmath_train_sample_6144_context_4k_Qwen3-8B-Base_max_response4096_batch1024_ppomini256_rollout8_vllm/global_step_50/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 
 
69
  reinforce_pp_deepmath_train_sample_6144_context_4k_Qwen3-8B-Base_max_response4096_batch1024_ppomini256_rollout8_vllm/global_step_30/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
70
  reinforce_pp_deepmath_train_sample_6144_context_4k_Qwen3-8B-Base_max_response4096_batch1024_ppomini256_rollout8_vllm/global_step_40/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
71
  reinforce_pp_deepmath_train_sample_6144_context_4k_Qwen3-8B-Base_max_response4096_batch1024_ppomini256_rollout8_vllm/global_step_50/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
72
+ reinforce_pp_deepmath_train_sample_6144_context_4k_Qwen3-8B-Base_max_response4096_batch1024_ppomini256_rollout8_vllm/global_step_60/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
reinforce_pp_deepmath_train_sample_6144_context_4k_Qwen3-8B-Base_max_response4096_batch1024_ppomini256_rollout8_vllm/global_step_30/actor/huggingface/model-00001-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6902d2df122cc246bc07130bf09506174d9ee78e61790ea9f04716dca4c4d214
3
+ size 4999853592
reinforce_pp_deepmath_train_sample_6144_context_4k_Qwen3-8B-Base_max_response4096_batch1024_ppomini256_rollout8_vllm/global_step_30/actor/huggingface/model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1989f3d557639e78a0449710a7a8e23b5f20bd7ae607920aed4936f009613906
3
+ size 4633794104
reinforce_pp_deepmath_train_sample_6144_context_4k_Qwen3-8B-Base_max_response4096_batch1024_ppomini256_rollout8_vllm/global_step_60/actor/huggingface/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
3
+ size 11422654
reinforce_pp_deepmath_train_sample_6144_context_4k_Qwen3-8B-Base_max_response4096_batch1024_ppomini256_rollout8_vllm/global_step_70/data.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c54ae83b341e1b34e76f7cdaa8cf9ebe3bb202cd08b70027a18de247c48093e
3
+ size 1947