Upload config.json

config.json

@@ -0,0 +1,49 @@
+{
+  "_name_or_path": "/root/.cache/huggingface/hub/models--hymmmm--exaone-3.5-7.8b-emt-chatbot/snapshots/f76e818019c199bf4bfc8eff7a8e864692ce4a56",
+  "activation_function": "silu",
+  "architectures": [
+    "ExaoneForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "auto_map": {
+    "AutoConfig": "configuration_exaone.ExaoneConfig",
+    "AutoModelForCausalLM": "modeling_exaone.ExaoneForCausalLM",
+    "AutoModelForSequenceClassification": "modeling_exaone.ExaoneForSequenceClassification"
+  },
+  "bos_token_id": 1,
+  "dtype": "bfloat16",
+  "embed_dropout": 0.0,
+  "eos_token_id": 361,
+  "head_dim": 128,
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "layer_norm_epsilon": 1e-05,
+  "max_position_embeddings": 32768,
+  "model_type": "exaone",
+  "num_attention_heads": 32,
+  "num_key_value_heads": 8,
+  "num_layers": 32,
+  "pad_token_id": 0,
+  "quantization_config": {
+    "bits": 4,
+    "group_size": 128,
+    "modules_to_not_convert": null,
+    "quant_method": "awq",
+    "version": "gemm",
+    "zero_point": true
+  },
+  "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": 1000000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.47.0.dev0",
+  "use_cache": true,
+  "vocab_size": 102400
+}