Update README.md

README.md

@@ -126,6 +126,8 @@ generated_ids = [
 response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
 ```
 
+For a better experience, we recommend using [the following default generation parameters](https://huggingface.co/IIC/RigoChat-7b-v2/blob/main/generation_config.json).
+
 ## Training Details
 
 ### Training Data
@@ -139,7 +141,45 @@ We use the [Transformer Reinforcement Learning](https://huggingface.co/docs/trl/
 
 #### Training Hyperparameters
 
-- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+```shell
+LORA_CONFIG = {
+    "r": 64,
+    "lora_alpha": 16,
+    "lora_dropout": 0.1,
+    "bias": "none",
+    "task_type": "CAUSAL_LM",
+    "target_modules": [
+        "q_proj",
+        "k_proj",
+        "v_proj",
+        "o_proj",
+        "up_proj",
+        "gate_proj",
+        "down_proj",
+    ],
+    "use_rslora": True,
+}
+
+DPO_CONFIG = {
+    "num_train_epochs": 2,
+    "logging_steps": 25,
+    "eval_steps": 500,
+    "save_steps": 100,
+    "save_total_limit": 5,
+    "per_device_train_batch_size": 1,
+    "per_device_eval_batch_size": 1,
+    "gradient_accumulation_steps": 16,
+    "learning_rate": 5e-6,
+    "max_length": 8192,
+    "max_prompt_length": 6656,
+    "gradient_checkpointing": True,
+    "weight_decay": 0.001,
+    "optim": "rmsprop",
+    "evaluation_strategy": "steps",
+    "lr_scheduler_type": "cosine",
+    "bf16": True,
+}
+```
 
 #### Speeds, Sizes, Times [optional]