Update README.md

README.md

@@ -10,27 +10,23 @@ tags:
 licence: license
 ---
 
-# Model Card for trainer_output
+
+
+Reward model for NLP homework at HSE 
+
 
 This model is a fine-tuned version of [HuggingFaceTB/SmolLM-135M-Instruct](https://huggingface.co/HuggingFaceTB/SmolLM-135M-Instruct) on the [HumanLLMs/Human-Like-DPO-Dataset](https://huggingface.co/datasets/HumanLLMs/Human-Like-DPO-Dataset) dataset.
 It has been trained using [TRL](https://github.com/huggingface/trl).
 
-## Quick start
 
-```python
-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="spankevich/trainer_output", 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/spankevichteam/hw2-rlhf/runs/4b5k1ftd) 
 
 
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/67b0bd703230f308b6a233c4/Sdj-UAXEMW5jl3gAPREED.png)
+
 This model was trained with Reward.
 
 ### Framework versions