Jul 4, 2025 09:24 Adding `safetensors` variant of this model This is an automated PR created with https://huggingface.co/spaces/safetensors/convert
This new file is equivalent to `pytorch_model.bin` but safe in the sense that
no arbitrary code can be put into it.
These files also happen to load much faster than their pytorch counterpart:
https://colab.research.google.com/github/huggingface/notebooks/blob/main/safetensors_doc/en/speed.ipynb
The widgets on your model page will run using this model even if this is not merged
making sure the file actually works.
If you find any issues: please report here: https://huggingface.co/spaces/safetensors/convert/discussions
Feel free to ignore this PR. Jun 30, 2025 22:51 Añadiendo README.md 22:51 Improved model (processor): step 250 22:51 Improved model: step 250 (eval_loss=3.1117) 21:46 Improved model: step 500 (eval_loss=0.7476) 21:44 Improved model (processor): step 250 21:44 Improved model: step 250 (eval_loss=0.9108) 21:39 Improved model: step 2000 (eval_loss=0.7864) 21:35 Improved model: step 1000 (eval_loss=1.0689) 21:16 Improved model: step 500 (eval_loss=3.0999) 21:15 Improved model: step 250 (eval_loss=3.6604) 12:58 Improved model: step 10000 (eval_loss=0.0001) 12:56 Improved model: step 9750 (eval_loss=0.0001) 12:55 Improved model: step 9500 (eval_loss=0.0001) 12:54 Improved model: step 9250 (eval_loss=0.0001) 12:52 Improved model: step 9000 (eval_loss=0.0001) 12:51 Improved model: step 8750 (eval_loss=0.0001) 12:49 Improved model: step 8500 (eval_loss=0.0001) 12:48 Improved model: step 8250 (eval_loss=0.0001) 12:47 Improved model: step 8000 (eval_loss=0.0001) 12:45 Improved model: step 7750 (eval_loss=0.0001) 12:44 Improved model: step 7500 (eval_loss=0.0001) 12:43 Improved model: step 7250 (eval_loss=0.0001) 12:41 Improved model: step 7000 (eval_loss=0.0001) 12:40 Improved model: step 6750 (eval_loss=0.0001) 12:39 Improved model: step 6500 (eval_loss=0.0001) 12:37 Improved model: step 6250 (eval_loss=0.0002) 12:36 Improved model: step 6000 (eval_loss=0.0002) 12:35 Improved model: step 5750 (eval_loss=0.0002) 12:33 Improved model: step 5500 (eval_loss=0.0002) 12:32 Improved model: step 5250 (eval_loss=0.0003) 12:31 Improved model: step 5000 (eval_loss=0.0003) 12:29 Improved model: step 4750 (eval_loss=0.0003) 12:28 Improved model: step 4500 (eval_loss=0.0004) 12:27 Improved model: step 4250 (eval_loss=0.0004) 12:25 Improved model: step 4000 (eval_loss=0.0005) 12:24 Improved model: step 3750 (eval_loss=0.0006) 12:23 Improved model: step 3500 (eval_loss=0.0007) 12:21 Improved model: step 3250 (eval_loss=0.0008) 12:20 Improved model: step 3000 (eval_loss=0.0010) 12:18 Improved model: step 2750 (eval_loss=0.0012) 12:17 Improved model: step 2500 (eval_loss=0.0014) 12:16 Improved model: step 2250 (eval_loss=0.0018) 12:15 Improved model: step 2000 (eval_loss=0.0022) 12:13 Improved model: step 1750 (eval_loss=0.0030) 12:12 Improved model: step 1500 (eval_loss=0.0041) 12:11 Improved model: step 1250 (eval_loss=0.0060) 12:09 Improved model: step 1000 (eval_loss=0.0098) 12:08 Improved model: step 750 (eval_loss=0.0201) 12:07 Improved model: step 500 (eval_loss=0.0878) 
