Create model_config.json

model_config.json

@@ -0,0 +1,57 @@
+{
+  "model_name": "unsloth/gemma-2-2b",
+  "max_seq_length": 2048,
+  "dtype": null,
+  "load_in_4bit": false,
+  "lora_params": {
+    "r": 16,
+    "target_modules": [
+      "q_proj",
+      "k_proj",
+      "v_proj",
+      "o_proj",
+      "gate_proj",
+      "up_proj",
+      "down_proj"
+    ],
+    "lora_alpha": 16,
+    "lora_dropout": 0,
+    "bias": "none",
+    "use_gradient_checkpointing": "unsloth",
+    "random_state": 3407,
+    "use_rslora": false
+  },
+  "training_args": {
+    "per_device_train_batch_size": 4,
+    "gradient_accumulation_steps": 4,
+    "warmup_steps": 5,
+    "num_train_epochs": 1,
+    "learning_rate": 0.0002,
+    "fp16": true,
+    "bf16": false,
+    "logging_steps": 1,
+    "optim": "adamw_8bit",
+    "weight_decay": 0.01,
+    "lr_scheduler_type": "linear",
+    "seed": 3407,
+    "output_dir": "outputs",
+    "report_to": "none"
+  },
+  "data_config": {
+    "dataset_name": "marmikpandya/mental-health",
+    "dataset_split": "train",
+    "dataset_rows": null,
+    "conversation_format": null,
+    "max_seq_length": 2048,
+    "train_on_responses_only": false
+  },
+  "inference_config": {
+    "temperature": null,
+    "min_p": null,
+    "max_new_tokens": null
+  },
+  "alpaca_prompt": {
+    "template": "Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.\n\n### Instruction:\n{}\n\n### Input:\n{}\n\n### Response:\n{}",
+    "eos_token": true
+  }
+}