Upload GemmaForCausalLM

config.json

@@ -5,10 +5,10 @@
   "attention_bias": false,
   "attention_dropout": 0.0,
   "bos_token_id": 2,
+  "dtype": "float32",
   "eos_token_id": 1,
   "head_dim": 256,
-  "hidden_act": "gelu_pytorch_tanh",
-  "hidden_activation": null,
+  "hidden_act": "gelu",
   "hidden_size": 8,
   "initializer_range": 0.02,
   "intermediate_size": 32,
@@ -19,9 +19,9 @@
   "num_key_value_heads": 2,
   "pad_token_id": 0,
   "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
   "rope_theta": 10000.0,
-  "torch_dtype": "float32",
-  "transformers_version": "4.55.0.dev0",
+  "transformers_version": "4.57.0.dev0",
   "use_cache": true,
-  "vocab_size": 256217
+  "vocab_size": 256000
 }

generation_config.json

@@ -3,5 +3,5 @@
   "bos_token_id": 2,
   "eos_token_id": 1,
   "pad_token_id": 0,
-  "transformers_version": "4.55.0.dev0"
+  "transformers_version": "4.57.0.dev0"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6065c3dbea85e914234cd60720dfa321f537816f49a7260cc5ee91d1a4edaae9
-size 8403952
+oid sha256:b7cb5c14766a2086fc1045ba3e5bb05755c337e29c5a39d82d41dbdf92fb6a24
+size 8397008