Upload GemmaForCausalLM

config.json

@@ -5,8 +5,8 @@
   ],
   "attention_bias": false,
   "attention_dropout": 0.0,
-  "bos_token_id": 2,
-  "eos_token_id": 1,
+  "bos_token_id": 1,
+  "eos_token_id": 7,
   "head_dim": 256,
   "hidden_act": "gelu_pytorch_tanh",
   "hidden_activation": "gelu_pytorch_tanh",
@@ -19,8 +19,9 @@
   "num_hidden_layers": 2,
   "num_key_value_heads": 1,
   "pad_token_id": 0,
-  "rms_norm_eps": 1e-06,
+  "rms_norm_eps": 1e-05,
   "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
   "torch_dtype": "float32",
   "transformers_version": "4.41.2",
   "use_cache": true,

generation_config.json

@@ -1,7 +1,7 @@
 {
   "_from_model_config": true,
-  "bos_token_id": 2,
-  "eos_token_id": 1,
+  "bos_token_id": 1,
+  "eos_token_id": 7,
   "pad_token_id": 0,
   "transformers_version": "4.41.2"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e87c978bfe7d5573ac9859aa84c72821b5d161831f32aeaaf6e7f9fccc0ed957
-size 518543560
+oid sha256:f866cc26894c437b19db09c661623352997b05d689b7a34edc945d05978da586
+size 915429664