Trained with Unsloth

config.json

@@ -18,7 +18,7 @@
   "hidden_size": 3584,
   "initializer_range": 0.02,
   "intermediate_size": 14336,
-  "max_position_embeddings": 8192,
+  "max_position_embeddings": 20000,
   "model_type": "gemma2",
   "num_attention_heads": 16,
   "num_hidden_layers": 42,
@@ -26,12 +26,15 @@
   "pad_token_id": 0,
   "query_pre_attn_scalar": 256,
   "rms_norm_eps": 1e-06,
-  "rope_scaling": null,
+  "rope_scaling": {
+    "factor": 2.0,
+    "type": "linear"
+  },
   "rope_theta": 10000.0,
   "sliding_window": 4096,
   "sliding_window_size": 4096,
   "torch_dtype": "float16",
-  "transformers_version": "4.50.3",
+  "transformers_version": "4.51.0",
   "unsloth_version": "2025.3.19",
   "use_cache": true,
   "vocab_size": 256000

generation_config.json

@@ -6,7 +6,7 @@
     1,
     107
   ],
-  "max_length": 8192,
+  "max_length": 20000,
   "pad_token_id": 0,
-  "transformers_version": "4.50.3"
+  "transformers_version": "4.51.0"
 }

model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f7f20f5b85ade5813e32e9303e581d687c7f3d7c14be739b28a7d5627b0bf85
+oid sha256:35bee6f5e48a50392c3d73dc0af91508c756fb67a88a604768659da6697010fe
 size 4903351824

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d1bd7b2e67e4ec437788de35de02eee72a48fe049514177704b42d5c00018d34
+oid sha256:2517d5d7fce7cecb80be7cae127f8c36e1265d6db3ed82e0d457f12b35ffaa18
 size 4947570728

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b53ed02c09f523752e4608415f084b2a5918d0b09cd97b45b54dc577b590f27
+oid sha256:b63ec077bc27a8f0ea0cbbd80176b0acfb8b750e0860a39a54752e5466fef14e
 size 4962221328

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c820d80f93d186a675d102fe04dcd0bcbf1448656c9f8529f21507519e7b7acb
+oid sha256:2251161a07f923203632153ec296ade679f247c32d179efb909e95549e30e403
 size 3670322096