Update README.md

README.md

@@ -32,25 +32,34 @@ This model and its related LoRA was fine-tuned on [https://huggingface.co/failsp
 
 ### - PEFT Parameters
 
-- lora_alpha=64,
-- lora_dropout=0.05,
-- r=128,
-- bias="none",
+- lora_alpha=64
+- lora_dropout=0.05
+- r=128
+- bias="none"
 
 ### - Training Arguments
 
-- num_train_epochs=1,
-- per_device_train_batch_size=1,
-- gradient_accumulation_steps=4,
-- optim="adamw_bnb_8bit",
-- save_steps=25,
-- logging_steps=25,
-- learning_rate=2e-4,
-- weight_decay=0.001,
-- fp16=False,
-- bf16=False,
-- max_grad_norm=0.3,
-- max_steps=-1,
-- warmup_ratio=0.03,
-- group_by_length=True,
-- lr_scheduler_type="constant",
+- num_train_epochs=1
+- per_device_train_batch_size=1
+- gradient_accumulation_steps=4
+- optim="adamw_bnb_8bit"
+- save_steps=25
+- logging_steps=25
+- learning_rate=2e-4
+- weight_decay=0.001
+- fp16=False
+- bf16=False
+- max_grad_norm=0.3
+- max_steps=-1
+- warmup_ratio=0.03
+- group_by_length=True
+- lr_scheduler_type="constant"
+
+## Credits
+
+- Meta ([https://huggingface.co/meta-llama](https://huggingface.co/meta-llama)): for the original Llama-3;
+- failspy ([https://huggingface.co/failspy](https://huggingface.co/failspy)): for the base model and the orthogonalization implementation;
+- NobodyExistsOnTheInternet ([https://huggingface.co/NobodyExistsOnTheInternet](https://huggingface.co/NobodyExistsOnTheInternet)): for the incredible dataset;
+- Undi95 ([https://huggingface.co/Undi95](https://huggingface.co/Undi95)) and Sao10k ([https://huggingface.co/Sao10K](https://huggingface.co/Sao10K)): my main inspirations for doing these models =]
+
+A huge thank you to all of them ☺️