Model save

README.md

@@ -1,19 +1,15 @@
 ---
 base_model: google/gemma-2-9b-it
 library_name: transformers
-model_name: gemma-2-9b-it-honest_lying-sft_to_honest-lora_True
+model_name: gemma-2-9b-it_honest_lying_sft_to_honest_lora_True
 tags:
 - generated_from_trainer
-- gemma-2-9b-it
-- honest_lying
-- sft_to_honest
-- lora_True
 - trl
 - sft
 licence: license
 ---
 
-# Model Card for gemma-2-9b-it-honest_lying-sft_to_honest-lora_True
+# Model Card for gemma-2-9b-it_honest_lying_sft_to_honest_lora_True
 
 This model is a fine-tuned version of [google/gemma-2-9b-it](https://huggingface.co/google/gemma-2-9b-it).
 It has been trained using [TRL](https://github.com/huggingface/trl).
@@ -24,14 +20,14 @@ It has been trained using [TRL](https://github.com/huggingface/trl).
 from transformers import pipeline
 
 question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
-generator = pipeline("text-generation", model="winnieyangwannan/gemma-2-9b-it-honest_lying-sft_to_honest-lora_True", device="cuda")
+generator = pipeline("text-generation", model="winnieyangwannan/gemma-2-9b-it_honest_lying_sft_to_honest_lora_True", device="cuda")
 output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
 print(output["generated_text"])
 ```
 
 ## Training procedure
 
-[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/winnie96/huggingface/runs/kw2y3464) 
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/winnie96/huggingface/runs/6xk1r0mc) 
 
 
 This model was trained with SFT.