Model save

README.md

@@ -1,7 +1,7 @@
 ---
-base_model: Qwen/Qwen3-0.6B
+base_model: microsoft/Phi-3-mini-4k-instruct
 library_name: transformers
-model_name: sft
+model_name: sft_phi3
 tags:
 - generated_from_trainer
 - trl
@@ -9,9 +9,9 @@ tags:
 licence: license
 ---
 
-# Model Card for sft
+# Model Card for sft_phi3
 
-This model is a fine-tuned version of [Qwen/Qwen3-0.6B](https://huggingface.co/Qwen/Qwen3-0.6B).
+This model is a fine-tuned version of [microsoft/Phi-3-mini-4k-instruct](https://huggingface.co/microsoft/Phi-3-mini-4k-instruct).
 It has been trained using [TRL](https://github.com/huggingface/trl).
 
 ## Quick start
@@ -20,14 +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="SaminSkyfall/sft", device="cuda")
+generator = pipeline("text-generation", model="SaminSkyfall/sft_phi3", 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/samin-skyfall-ai/huggingface/runs/5obf7lq0) 
+[<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/samin-skyfall-ai/huggingface/runs/4pwjt53v) 
 
 
 This model was trained with SFT.

generation_config.json

@@ -1,13 +1,11 @@
 {
-  "bos_token_id": 151643,
-  "do_sample": true,
+  "_from_model_config": true,
+  "bos_token_id": 1,
   "eos_token_id": [
-    151645,
-    151643
+    32000,
+    32001,
+    32007
   ],
-  "pad_token_id": 151643,
-  "temperature": 0.6,
-  "top_k": 20,
-  "top_p": 0.95,
+  "pad_token_id": 32000,
   "transformers_version": "4.51.3"
 }