Upload config.json

config.json

@@ -0,0 +1,59 @@
+{
+    "_name_or_path": "meta-llama/Llama-3.1-8B-Instruct",
+    "architectures": [
+        "LlamaForCausalLM"
+    ],
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "bos_token_id": 128000,
+    "eos_token_id": 128001,
+    "hidden_act": "silu",
+    "hidden_size": 4096,
+    "initializer_range": 0.02,
+    "intermediate_size": 14336,
+    "max_position_embeddings": 131072,
+    "model_type": "llama",
+    "num_attention_heads": 32,
+    "num_hidden_layers": 32,
+    "num_key_value_heads": 8,
+    "pretraining_tp": 1,
+    "rms_norm_eps": 1e-05,
+    "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": 500000.0,
+    "tie_word_embeddings": false,
+    "torch_dtype": "bfloat16",
+    "transformers_version": "4.43.0",
+    "use_cache": true,
+    "vocab_size": 128256,
+    "task_type": "CAUSAL_LM",
+    "peft_type": "LORA",
+    "base_model_name_or_path": "meta-llama/Llama-3.1-8B-Instruct",
+    "inference_mode": false,
+    "r": 16,
+    "lora_alpha": 32,
+    "lora_dropout": 0.1,
+    "target_modules": [
+        "q_proj",
+        "k_proj",
+        "v_proj",
+        "o_proj",
+        "gate_proj",
+        "up_proj",
+        "down_proj"
+    ],
+    "bias": "none",
+    "fan_in_fan_out": false,
+    "init_lora_weights": true,
+    "layers_pattern": null,
+    "layers_to_transform": null,
+    "modules_to_save": null,
+    "revision": null,
+    "use_dora": false,
+    "use_rslora": false
+}