Upload GemmaForCausalLM

config.json

@@ -1,7 +1,7 @@
 {
   "_name_or_path": "gemcy_v2",
   "architectures": [
-    "LlamaForCausalLM"
+    "GemmaForCausalLM"
   ],
   "attention_bias": false,
   "attention_dropout": 0.0,
@@ -13,16 +13,14 @@
   "initializer_range": 0.02,
   "intermediate_size": 16384,
   "max_position_embeddings": 8192,
-  "model_type": "llama",
+  "model_type": "gemma",
   "num_attention_heads": 8,
   "num_hidden_layers": 18,
   "num_key_value_heads": 1,
   "pad_token_id": 0,
-  "pretraining_tp": 1,
   "rms_norm_eps": 1e-06,
   "rope_scaling": null,
   "rope_theta": 10000.0,
-  "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.38.1",
   "use_cache": false,

model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90fb45f150b310fe562a67279e12837b07083205c48783c75119a00eadadd0ca
-size 1115697720
+oid sha256:01eedac83e4049f0f25a2eab432c9acba2926a73da853cd4987ff9043a23e3ce
+size 67121608

model.safetensors.index.json

@@ -1,9 +1,8 @@
 {
   "metadata": {
-    "total_size": 6060920832
+    "total_size": 5012344832
   },
   "weight_map": {
-    "lm_head.weight": "model-00002-of-00002.safetensors",
     "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
     "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",