Trained with Unsloth

config.json

@@ -9,7 +9,7 @@
   "eos_token_id": 1,
   "head_dim": 256,
   "hidden_act": "gelu",
-  "hidden_activation": null,
+  "hidden_activation": "gelu_pytorch_tanh",
   "hidden_size": 2048,
   "initializer_range": 0.02,
   "intermediate_size": 16384,
@@ -23,8 +23,8 @@
   "rope_scaling": null,
   "rope_theta": 10000.0,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.40.2",
-  "unsloth_version": "2024.4",
+  "transformers_version": "4.41.0",
+  "unsloth_version": "2024.5",
   "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": "4.40.2"
+  "transformers_version": "4.41.0"
 }

model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:446f2584b42b31617648f27b5a31b9b84c9182e9ae909ca20bcf6a530087a88c
+oid sha256:de1864fe3f8c54d69440f072abd73542bb1799d919dcc9f397b205e1766cc0eb
 size 4945242264

model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:495985623530485b1280435c012c2c47ff261eeb0ae17ba87f380b6b7cd913e8
+oid sha256:9e8e369418acc143ce93f0f5d2f4465d04c3e96c2ac42985c9c6035c0d998728
 size 67121608