Hugging Face's logo

MoeReward
/
rl_checkpoints

Safetensors
Model card Files Community
shengyi-qian commited on
Commit
eaa1e52
·
1 Parent(s): 54cb21f

upload diffdomain1

Browse files
Files changed (15) hide show
  1. qwen1.5_base_rule_base_nq_heavy_diffdomain1_reward_func/added_tokens.json +3 -0
  2. qwen1.5_base_rule_base_nq_heavy_diffdomain1_reward_func/config.json +3 -0
  3. qwen1.5_base_rule_base_nq_heavy_diffdomain1_reward_func/generation_config.json +3 -0
  4. qwen1.5_base_rule_base_nq_heavy_diffdomain1_reward_func/merges.txt +0 -0
  5. qwen1.5_base_rule_base_nq_heavy_diffdomain1_reward_func/model-00001-of-00006.safetensors +3 -0
  6. qwen1.5_base_rule_base_nq_heavy_diffdomain1_reward_func/model-00002-of-00006.safetensors +3 -0
  7. qwen1.5_base_rule_base_nq_heavy_diffdomain1_reward_func/model-00003-of-00006.safetensors +3 -0
  8. qwen1.5_base_rule_base_nq_heavy_diffdomain1_reward_func/model-00004-of-00006.safetensors +3 -0
  9. qwen1.5_base_rule_base_nq_heavy_diffdomain1_reward_func/model-00005-of-00006.safetensors +3 -0
  10. qwen1.5_base_rule_base_nq_heavy_diffdomain1_reward_func/model-00006-of-00006.safetensors +3 -0
  11. qwen1.5_base_rule_base_nq_heavy_diffdomain1_reward_func/model.safetensors.index.json +3 -0
  12. qwen1.5_base_rule_base_nq_heavy_diffdomain1_reward_func/special_tokens_map.json +3 -0
  13. qwen1.5_base_rule_base_nq_heavy_diffdomain1_reward_func/tokenizer.json +3 -0
  14. qwen1.5_base_rule_base_nq_heavy_diffdomain1_reward_func/tokenizer_config.json +3 -0
  15. qwen1.5_base_rule_base_nq_heavy_diffdomain1_reward_func/vocab.json +3 -0
qwen1.5_base_rule_base_nq_heavy_diffdomain1_reward_func/added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a475432c61f8d6154d10d28c37671a36e5717daf3d15002a988968fee54a500
3
+ size 80
qwen1.5_base_rule_base_nq_heavy_diffdomain1_reward_func/config.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:528d3faa3d28fe193cae05b08cd0c15e6c173fe3ed86ca4382d22ad120232280
3
+ size 1008
qwen1.5_base_rule_base_nq_heavy_diffdomain1_reward_func/generation_config.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:64249e16a9efa9b4b2560bd2c0b3c44dd0eee067c5792b646bafe09f4676bce8
3
+ size 139
qwen1.5_base_rule_base_nq_heavy_diffdomain1_reward_func/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
qwen1.5_base_rule_base_nq_heavy_diffdomain1_reward_func/model-00001-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d3b589e52005733293893bdec4c8c89e5e79ddaa2031576fc48e0800552ca5c
3
+ size 4996577736
qwen1.5_base_rule_base_nq_heavy_diffdomain1_reward_func/model-00002-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d5857e6909e9818b1c7df252da31f797454504c1978685bc3d05be49f61f59d
3
+ size 4996347752
qwen1.5_base_rule_base_nq_heavy_diffdomain1_reward_func/model-00003-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c852b575a3ad9aaf93e152a8ee794ad8b65697973ab270a03460d47dbd95c2c2
3
+ size 4997127120
qwen1.5_base_rule_base_nq_heavy_diffdomain1_reward_func/model-00004-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d00acf35c2c5ec31bcf2684b24e6d22d8a71a6f96fe03a0f9aee0eb4951e14af
3
+ size 4985592520
qwen1.5_base_rule_base_nq_heavy_diffdomain1_reward_func/model-00005-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c09725d09f117a820871af2be23767d6901ff435f907ea1a6efecbea79f5e5d2
3
+ size 4996348976
qwen1.5_base_rule_base_nq_heavy_diffdomain1_reward_func/model-00006-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:753bbf18b2031fe8878a1f7360a1a8ccf5e2a68a7b22d3793119b2837b424037
3
+ size 3660151400
qwen1.5_base_rule_base_nq_heavy_diffdomain1_reward_func/model.safetensors.index.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:406d3a66074ba34fa2be1c70f976607e4eab4c192dbba1d9f066db2cf6531a42
3
+ size 416452
qwen1.5_base_rule_base_nq_heavy_diffdomain1_reward_func/special_tokens_map.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:daf48284de8f4779b1dbf20963a68180002fba2a34a5da72292380c5d9fb6af2
3
+ size 370
qwen1.5_base_rule_base_nq_heavy_diffdomain1_reward_func/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e49bebc2336dd0896ee055aa24e6bb65d80539b16751bb9798d6829db3ac4ea3
3
+ size 11418365
qwen1.5_base_rule_base_nq_heavy_diffdomain1_reward_func/tokenizer_config.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6eb94faf6d8d2be1485bba6ceb83a7f0c6885357867f2f662e6f3a6783b927c4
3
+ size 1331
qwen1.5_base_rule_base_nq_heavy_diffdomain1_reward_func/vocab.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca10d7e9fb3ed18575dd1e277a2579c16d108e32f27439684afa0e10b1440910
3
+ size 2776833