Upload ExaoneForCausalLM

config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "LGAI-EXAONE/EXAONE-3.5-2.4B-Instruct",
+  "activation_function": "silu",
+  "architectures": [
+    "ExaoneForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "auto_map": {
+    "AutoConfig": "LGAI-EXAONE/EXAONE-3.5-2.4B-Instruct--configuration_exaone.ExaoneConfig",
+    "AutoModelForCausalLM": "LGAI-EXAONE/EXAONE-3.5-2.4B-Instruct--modeling_exaone.ExaoneForCausalLM",
+    "AutoModelForSequenceClassification": "LGAI-EXAONE/EXAONE-3.5-2.4B-Instruct--modeling_exaone.ExaoneForSequenceClassification"
+  },
+  "bos_token_id": 1,
+  "embed_dropout": 0.0,
+  "eos_token_id": 361,
+  "head_dim": 80,
+  "hidden_size": 2560,
+  "initializer_range": 0.02,
+  "intermediate_size": 7168,
+  "layer_norm_epsilon": 1e-05,
+  "max_position_embeddings": 32768,
+  "model_type": "exaone",
+  "num_attention_heads": 32,
+  "num_key_value_heads": 8,
+  "num_layers": 30,
+  "pad_token_id": 0,
+  "rope_scaling": {
+    "factor": 8.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 1000000,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.44.2",
+  "use_cache": false,
+  "vocab_size": 102400
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 361,
+  "pad_token_id": 0,
+  "transformers_version": "4.44.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe0dd5860c0e72ed3816b60949c2048ef6faf951793f5878431b3cc1b626a7aa
+size 4810685896