Audio Classification
Transformers
Safetensors
English
qwen2_5_omni_thinker
reward-model
spoken-dialogue
speech
preference
qwen2_5_omni
modality-awareness
colloquialness
Instructions to use MYJOKERML/SDiaReward-3B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use MYJOKERML/SDiaReward-3B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("audio-classification", model="MYJOKERML/SDiaReward-3B")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, QwenOmniThinkerReward tokenizer = AutoTokenizer.from_pretrained("MYJOKERML/SDiaReward-3B") model = QwenOmniThinkerReward.from_pretrained("MYJOKERML/SDiaReward-3B", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download all_results.json from MYJOKERML/SDiaReward-3B: direct link, hf CLI and curl.
- Browser
- Download file 404 Bytes
-
https://huggingface.co/MYJOKERML/SDiaReward-3B/resolve/main/all_results.json
- Command line
-
hf download hf://MYJOKERML/SDiaReward-3B/all_results.json
-
curl -L -o all_results.json https://huggingface.co/MYJOKERML/SDiaReward-3B/resolve/main/all_results.json
404 Bytes
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.9172453703703703, | |
| "eval_loss": 0.418969064950943, | |
| "eval_margin": 0.8687698929398148, | |
| "eval_max_reward": 1.382568359375, | |
| "eval_mean_reward": -0.11189778645833333, | |
| "eval_min_reward": -1.5139612268518519, | |
| "eval_num_tokens": 92427959.0, | |
| "eval_runtime": 403.7554, | |
| "eval_samples_per_second": 4.275, | |
| "eval_steps_per_second": 0.134 | |
| } |