Upload GRPO-refined model from grpo_length_v6

config.json

@@ -34,8 +34,8 @@
   "router_aux_loss_coef": 0.001,
   "sliding_window": null,
   "tie_word_embeddings": false,
-  "transformers_version": "5.2.0",
-  "use_cache": true,
+  "transformers_version": "5.4.0",
+  "use_cache": false,
   "use_sliding_window": false,
   "vocab_size": 151936
 }

generation_config.json

@@ -9,5 +9,5 @@
   "temperature": 0.6,
   "top_k": 20,
   "top_p": 0.95,
-  "transformers_version": "5.2.0"
+  "transformers_version": "5.4.0"
 }

model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:081a47e90b0959571f2c8919ddb085180b28eac3e19048678e23d19e95ed6615
+oid sha256:3b82e8c4092fa75cb7fa69ed749fa744462ed1cd938b25985677cdd76648fede
 size 49849999800

model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5cdee772b8ed8f85f38ec94f745f2bb29e9abd6f64a3226798c734532cf977f3
+oid sha256:47b29fd4f342ea47ef9f4f8b29007544db102f3ff7b7e6c3f84ea53cb69292b1
 size 11216611104