Upload Gemma2ForCausalLM

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "google/gemma-2-2b-jpn-it",
+  "_name_or_path": "google/gemma-2-2b",
   "architectures": [
     "Gemma2ForCausalLM"
   ],
@@ -8,10 +8,10 @@
   "attn_logit_softcapping": 50.0,
   "bos_token_id": 2,
   "cache_implementation": "hybrid",
-  "dtype": "bfloat16",
   "eos_token_id": 1,
   "final_logit_softcapping": 30.0,
   "head_dim": 256,
+  "hidden_act": "gelu_pytorch_tanh",
   "hidden_activation": "gelu_pytorch_tanh",
   "hidden_size": 2304,
   "initializer_range": 0.02,
@@ -22,7 +22,7 @@
   "num_hidden_layers": 26,
   "num_key_value_heads": 4,
   "pad_token_id": 0,
-  "query_pre_attn_scalar": 224,
+  "query_pre_attn_scalar": 256,
   "rms_norm_eps": 1e-06,
   "rope_theta": 10000.0,
   "sliding_window": 4096,

model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7de8aff7aeb2401ac5a42bf65e89b565d2901bc70b29e52390abf389932d43e
+oid sha256:82a5bc33193e61c1c64a795c0b17b15c28f93e18c134b371f16293a5ec495852
 size 4988025760

model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:863fda3ed5abd0eb0b1e52993b921a76f04729c55fed375a7944691b913f74ac
+oid sha256:e31aca622b1bd6d7ebc4ef99da705182d1599ade85af78ca956e21c7f9f43b67
 size 240691728