Trained with Unsloth

config.json

@@ -13,20 +13,17 @@
   "hidden_size": 2048,
   "initializer_range": 0.02,
   "intermediate_size": 16384,
-  "max_position_embeddings": 16384,
+  "max_position_embeddings": 8192,
   "model_type": "gemma",
   "num_attention_heads": 8,
   "num_hidden_layers": 18,
   "num_key_value_heads": 1,
   "pad_token_id": 0,
   "rms_norm_eps": 1e-06,
-  "rope_scaling": {
-    "factor": 2.0,
-    "type": "linear"
-  },
+  "rope_scaling": null,
   "rope_theta": 10000.0,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.40.1",
+  "transformers_version": "4.40.2",
   "unsloth_version": "2024.4",
   "use_cache": true,
   "vocab_size": 256000

generation_config.json

@@ -3,5 +3,5 @@
   "bos_token_id": 2,
   "eos_token_id": 1,
   "pad_token_id": 0,
-  "transformers_version": "4.40.1"
+  "transformers_version": "4.40.2"
 }

model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2618a13daff41db5e402115fad63507eccdc8d1cff7d4808131411ffd6d54ac5
+oid sha256:446f2584b42b31617648f27b5a31b9b84c9182e9ae909ca20bcf6a530087a88c
 size 4945242264

model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3fc3854aab075d6c82c8368c4e3555d5656e9dffa2e299eadda5c31359e97487
+oid sha256:495985623530485b1280435c012c2c47ff261eeb0ae17ba87f380b6b7cd913e8
 size 67121608