Model save

README.md

@@ -1,7 +1,7 @@
 ---
 base_model: Qwen/Qwen2.5-3B-Instruct
 library_name: transformers
-model_name: V3_Qwen2.5-3b-query-understandings_prompt_tiny_improved_r_64_epoch_2
+model_name: V3_Qwen2.5-3b-query-understandings_prompt_improved_tiny_r_64_epoch_2
 tags:
 - generated_from_trainer
 - trl
@@ -9,7 +9,7 @@ tags:
 licence: license
 ---
 
-# Model Card for V3_Qwen2.5-3b-query-understandings_prompt_tiny_improved_r_64_epoch_2
+# Model Card for V3_Qwen2.5-3b-query-understandings_prompt_improved_tiny_r_64_epoch_2
 
 This model is a fine-tuned version of [Qwen/Qwen2.5-3B-Instruct](https://huggingface.co/Qwen/Qwen2.5-3B-Instruct).
 It has been trained using [TRL](https://github.com/huggingface/trl).
@@ -20,7 +20,7 @@ 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="sadra-barikbin/V3_Qwen2.5-3b-query-understandings_prompt_tiny_improved_r_64_epoch_2", device="cuda")
+generator = pipeline("text-generation", model="sadra-barikbin/V3_Qwen2.5-3b-query-understandings_prompt_improved_tiny_r_64_epoch_2", device="cuda")
 output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
 print(output["generated_text"])
 ```