Hugging Face's logo

bensondccnqwc
/
tmp-yv08a

Safetensors
Model card Files
xet
Community
bensondccnqwc commited on
Commit
4576fb4
·
verified ·
1 Parent(s): 2d45ea7

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_40/actor/huggingface/model-00004-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_50/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_70/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_80/data.pt +3 -0
.gitattributes CHANGED
@@ -70,3 +70,4 @@ reinforce_pp_deepmath_train_sample_6144_context_4k_Qwen3-8B-Base_max_response409
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
 
 
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
73
+ reinforce_pp_deepmath_train_sample_6144_context_4k_Qwen3-8B-Base_max_response4096_batch1024_ppomini256_rollout8_vllm/global_step_70/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_40/actor/huggingface/model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8bdbcbce7a2f78a3201f0388feedc99e494f613c0b612285a5372a91ca41db4a
3
+ size 1996625536
reinforce_pp_deepmath_train_sample_6144_context_4k_Qwen3-8B-Base_max_response4096_batch1024_ppomini256_rollout8_vllm/global_step_50/actor/huggingface/model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c78231ed882b7c617352249f897213c8d51cecaf4154d5406229e67ca7f0d9e0
3
+ size 1535162288
reinforce_pp_deepmath_train_sample_6144_context_4k_Qwen3-8B-Base_max_response4096_batch1024_ppomini256_rollout8_vllm/global_step_70/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_80/data.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:12f0f10d745278f0254d457d803c33e2700899032f8bf78123773b19734eb9d7
3
+ size 1947