Create config.json

config.json

@@ -1,34 +1,29 @@
 {
-  "alpha_pattern": {},
-  "auto_mapping": null,
-  "base_model_name_or_path": "unsloth/llama-3-8b-Instruct-bnb-4bit",
-  "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,
-  "megatron_config": null,
-  "megatron_core": "megatron.core",
-  "modules_to_save": null,
-  "peft_type": "LORA",
-  "r": 16,
-  "rank_pattern": {},
-  "revision": "unsloth",
-  "target_modules": [
-    "up_proj",
-    "v_proj",
-    "gate_proj",
-    "down_proj",
-    "k_proj",
-    "q_proj",
-    "o_proj"
+  "_name_or_path": "unsloth/llama-3-8b-Instruct",
+  "architectures": [
+    "LlamaForCausalLM"
   ],
-  "task_type": "CAUSAL_LM",
-  "use_dora": false,
-  "use_rslora": false
+  "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,
+  "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": "4.40.1",
+  "unsloth_version": "2024.5",
+  "use_cache": true,
+  "vocab_size": 128256
 }