Hugging Face's logo

kangdawei
/
MMR-Sigmoid-DAPO-8B

Text Generation
Transformers
Safetensors
llama
Generated from Trainer
open-r1
dapo
trl
conversational
text-generation-inference
Model card Files
xet
 Community
kangdawei commited on
Commit
ec8cc52
·
verified ·
1 Parent(s): c64f931

Add merged model for training step 250 (adapter revision: d2dd08a6)

Browse files
Files changed (7) hide show
  1. config.json +0 -1
  2. generation_config.json +1 -4
  3. model-00001-of-00004.safetensors +1 -1
  4. model-00002-of-00004.safetensors +1 -1
  5. model-00003-of-00004.safetensors +1 -1
  6. model-00004-of-00004.safetensors +1 -1
  7. tokenizer.json +2 -2
config.json CHANGED
@@ -18,7 +18,6 @@
18
  "num_attention_heads": 32,
19
  "num_hidden_layers": 32,
20
  "num_key_value_heads": 8,
21
- "pad_token_id": 128001,
22
  "pretraining_tp": 1,
23
  "rms_norm_eps": 1e-05,
24
  "rope_scaling": {
 
18
  "num_attention_heads": 32,
19
  "num_hidden_layers": 32,
20
  "num_key_value_heads": 8,
 
21
  "pretraining_tp": 1,
22
  "rms_norm_eps": 1e-05,
23
  "rope_scaling": {
generation_config.json CHANGED
@@ -2,10 +2,7 @@
2
  "_from_model_config": true,
3
  "bos_token_id": 128000,
4
  "do_sample": true,
5
- "eos_token_id": [
6
- 128001
7
- ],
8
- "pad_token_id": 128001,
9
  "temperature": 0.6,
10
  "top_p": 0.95,
11
  "transformers_version": "4.57.1"
 
2
  "_from_model_config": true,
3
  "bos_token_id": 128000,
4
  "do_sample": true,
5
+ "eos_token_id": 128001,
 
 
 
6
  "temperature": 0.6,
7
  "top_p": 0.95,
8
  "transformers_version": "4.57.1"
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:63d1fdcdab551fe71e69ee6be90301345c949ddbf01be38a51850d44f4f57d33
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa49cc4f7111889f59a52fcc06f3b734295ca7d6464fab59a59820a2ce221273
3
  size 4976698672
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:441de42a9af109064dd08da14a5b88a83d348188bb62c32370c74023e3d77859
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:45b061d69bac9a9ac9e8bd1d01ce8a422186bebe3c715c224397c223bca94294
3
  size 4999802720
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:16d3694cb1385b31d210932eec8ef9ad679956e5b69048c1545da9c42ff0e33d
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2afcba0838891b3e0e85d8a8696653392f1698cd18875de7e7440da590bb3ade
3
  size 4915916176
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a0b66334ab63b60587dccde2fe8e8d898475d2c1245447e8598d43905cef8846
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:04d3276a0a3e3fbaf0e68dcd2a99523ed48f8f338c23265bd848c6e9c58dcab8
3
  size 1168138808
tokenizer.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:26c881aaf4ef935b1516ec79ad6405dd2a459f2b5d431a8a4a1399c92f3ba022
3
- size 17209711
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d91915040cfac999d8c55f4b5bc6e67367c065e3a7a4e4b9438ce1f256addd86
3
+ size 17209530