Update README.md

README.md

@@ -59,11 +59,37 @@ While I'm a strong supporter for fully open-source community, I have to respect
 
 ## Training Parameters
 
-[TO BE FILLED]
-
-## Recommended Settings
-
-[TO BE FILLED]
+-    r = 256
+-    target_modules = ["q_proj", "k_proj", "v_proj", "o_proj",
+-                      "gate_proj", "up_proj", "down_proj",
+-                      "lm_head", "embed_tokens",]
+-    lora_alpha = 32
+-    lora_dropout = 0
+-    bias = "none"
+-    use_gradient_checkpointing = "unsloth"
+-    random_state = 3407
+-    use_rslora = True
+-    use_dora = False
+-    loftq_config = None
+
+-    per_device_train_batch_size = 1
+-    gradient_accumulation_steps = 16
+-    warmup_ratio = 0.1
+-    num_train_epochs = 3
+-    learning_rate = 5e-5
+-    embedding_learning_rate = 5e-6
+-    max_steps = 0
+-    group_by_length = False
+-    bf16 = true
+-    weight_decay = 0.01
+-    max_grad_norm = 8.0
+-    lr_scheduler_type = "cosine"
+-    optim = "paged_adamw_8bit"
+-    seed = 3407
+
+## Recommended Hyperparameters
+
+All samplers neutralised, with min_p set to 0.1. Make sure the temperature is applied last.
 
 ## Limitations