Model save

README.md

@@ -1,17 +1,18 @@
 ---
-base_model: Qwen/Qwen3-1.7B
+base_model: unsloth/qwen3-0.6b-unsloth-bnb-4bit
 library_name: transformers
-model_name: sft_full_1.7
+model_name: sft_unsloth
 tags:
 - generated_from_trainer
+- unsloth
 - trl
 - sft
 licence: license
 ---
 
-# Model Card for sft_full_1.7
+# Model Card for sft_unsloth
 
-This model is a fine-tuned version of [Qwen/Qwen3-1.7B](https://huggingface.co/Qwen/Qwen3-1.7B).
+This model is a fine-tuned version of [unsloth/qwen3-0.6b-unsloth-bnb-4bit](https://huggingface.co/unsloth/qwen3-0.6b-unsloth-bnb-4bit).
 It has been trained using [TRL](https://github.com/huggingface/trl).
 
 ## Quick start
@@ -20,14 +21,14 @@ 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_full_1.7", device="cuda")
+generator = pipeline("text-generation", model="SaminSkyfall/sft_unsloth", 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/6qpf8i76) 
+[<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/sgfy3zkh) 
 
 
 This model was trained with SFT.

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dabe2b9c4232d5a44feba50a065e2a33d3c5b6eafb89ea94be1868ea4a55e82a
+oid sha256:749a5445c63f1a8981715382882e9dcc033594a80e4e7b584f99797c696918ba
 size 80792456