Hugging Face's logo

bensondccnqwc
/
tmp-yv08a

Safetensors
Model card Files
xet
Community
bensondccnqwc commited on
Commit
dc98175
·
verified ·
1 Parent(s): f49e965

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_0/actor/huggingface/model-00004-of-00005.safetensors +3 -0
  3. reinforce_pp_deepmath_train_sample_6144_context_4k_Qwen3-8B-Base_max_response4096_batch1024_ppomini256_rollout8_vllm/global_step_20/actor/huggingface/model-00004-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_30/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_40/data.pt +3 -0
.gitattributes CHANGED
@@ -66,3 +66,4 @@ reinforce_pp_deepmath_train_sample_6144_context_4k_Qwen3-8B-Base_max_response409
66
  reinforce_pp_deepmath_train_sample_6144_context_4k_Qwen3-8B-Base_max_response4096_batch1024_ppomini256_rollout8_vllm/global_step_10/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
67
  reinforce_pp_deepmath_train_sample_6144_context_4k_Qwen3-8B-Base_max_response4096_batch1024_ppomini256_rollout8_vllm/global_step_100/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
68
  reinforce_pp_deepmath_train_sample_6144_context_4k_Qwen3-8B-Base_max_response4096_batch1024_ppomini256_rollout8_vllm/global_step_20/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 
 
66
  reinforce_pp_deepmath_train_sample_6144_context_4k_Qwen3-8B-Base_max_response4096_batch1024_ppomini256_rollout8_vllm/global_step_10/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
67
  reinforce_pp_deepmath_train_sample_6144_context_4k_Qwen3-8B-Base_max_response4096_batch1024_ppomini256_rollout8_vllm/global_step_100/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
68
  reinforce_pp_deepmath_train_sample_6144_context_4k_Qwen3-8B-Base_max_response4096_batch1024_ppomini256_rollout8_vllm/global_step_20/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
reinforce_pp_deepmath_train_sample_6144_context_4k_Qwen3-8B-Base_max_response4096_batch1024_ppomini256_rollout8_vllm/global_step_0/actor/huggingface/model-00004-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad8b708792105133e03fe19e2d56c89c709f677f01285f8b3ede8947d59fd9fe
3
+ size 3187841392
reinforce_pp_deepmath_train_sample_6144_context_4k_Qwen3-8B-Base_max_response4096_batch1024_ppomini256_rollout8_vllm/global_step_20/actor/huggingface/model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c49f9bbe04c01f7a749d30d19552915b24b051a0c0648af06ea51437f58a6e6d
3
+ size 1543566512
reinforce_pp_deepmath_train_sample_6144_context_4k_Qwen3-8B-Base_max_response4096_batch1024_ppomini256_rollout8_vllm/global_step_30/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_40/data.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2c67c094e601552a71b7e00780d12bfcac30dd607f0d4bcda4bbc1615cac947
3
+ size 1947