Initial commit of fine-tuned model

config.json

@@ -1,30 +1,29 @@
 {
-    "_name_or_path": "meta-llama/Meta-Llama-3-8B-Instruct",
-    "architectures": [
-      "LlamaForCausalLM"
-    ],
-    "attention_bias": false,
-    "attention_dropout": 0.0,
-    "bos_token_id": 128000,
-    "eos_token_id": 128009,
-    "hidden_act": "silu",
-    "hidden_size": 4096,
-    "initializer_range": 0.02,
-    "intermediate_size": 14336,
-    "max_position_embeddings": 8192,
-    "mlp_bias": false,
-    "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": null,
-    "rope_theta": 500000.0,
-    "tie_word_embeddings": false,
-    "torch_dtype": "bfloat16",
-    "transformers_version": "4.44.1",
-    "use_cache": false,
-    "vocab_size": 128256
-  }
-  
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "meta-llama/Meta-Llama-3-8B-Instruct",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}