rasyosef / Mistral-NeMo-Minitron-8B-SFT

huggingface.co
Total runs: 9
24-hour runs: 0
7-day runs: 0
30-day runs: 0
Model's Last Updated: August 26 2024

Introduction of Mistral-NeMo-Minitron-8B-SFT

Model Details of Mistral-NeMo-Minitron-8B-SFT

Mistral-NeMo-Minitron-8B-SFT

This model is a fine-tuned version of nvidia/Mistral-NeMo-Minitron-8B-Base on the generator dataset. It achieves the following results on the evaluation set:

  • Loss: 0.9376
  • Model Preparation Time: 0.0383
Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure
Training hyperparameters

The following hyperparameters were used during training:

  • learning_rate: 2e-05
  • train_batch_size: 1
  • eval_batch_size: 1
  • seed: 42
  • gradient_accumulation_steps: 8
  • total_train_batch_size: 8
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_steps: 200
  • num_epochs: 2
  • mixed_precision_training: Native AMP
Training results
Training Loss Epoch Step Validation Loss Model Preparation Time
1.7646 0.0535 100 1.4435 0.0383
1.2543 0.1071 200 1.1306 0.0383
1.1595 0.1606 300 1.0799 0.0383
1.0965 0.2142 400 1.0476 0.0383
1.0708 0.2677 500 1.0298 0.0383
1.0522 0.3213 600 1.0128 0.0383
1.0419 0.3748 700 1.0000 0.0383
1.0266 0.4284 800 0.9918 0.0383
1.0288 0.4819 900 0.9826 0.0383
0.9962 0.5355 1000 0.9762 0.0383
1.0103 0.5890 1100 0.9736 0.0383
1.0335 0.6426 1200 0.9695 0.0383
0.9976 0.6961 1300 0.9646 0.0383
1.0102 0.7497 1400 0.9608 0.0383
1.0049 0.8032 1500 0.9569 0.0383
1.0049 0.8568 1600 0.9530 0.0383
0.9974 0.9103 1700 0.9511 0.0383
0.99 0.9639 1800 0.9506 0.0383
0.9748 1.0174 1900 0.9458 0.0383
0.9721 1.0710 2000 0.9460 0.0383
0.9739 1.1245 2100 0.9456 0.0383
0.9675 1.1780 2200 0.9438 0.0383
0.9771 1.2316 2300 0.9434 0.0383
0.965 1.2851 2400 0.9425 0.0383
0.9651 1.3387 2500 0.9413 0.0383
0.9666 1.3922 2600 0.9410 0.0383
0.9587 1.4458 2700 0.9401 0.0383
0.955 1.4993 2800 0.9389 0.0383
0.9521 1.5529 2900 0.9385 0.0383
0.9377 1.6064 3000 0.9385 0.0383
0.9617 1.6600 3100 0.9381 0.0383
0.9316 1.7135 3200 0.9377 0.0383
0.9535 1.7671 3300 0.9376 0.0383
0.9561 1.8206 3400 0.9377 0.0383
0.9496 1.8742 3500 0.9376 0.0383
0.962 1.9277 3600 0.9376 0.0383
0.9354 1.9813 3700 0.9376 0.0383
Framework versions
  • PEFT 0.12.0
  • Transformers 4.44.2
  • Pytorch 2.4.0+cu121
  • Datasets 2.21.0
  • Tokenizers 0.19.1

Runs of rasyosef Mistral-NeMo-Minitron-8B-SFT on huggingface.co

9
Total runs
0
24-hour runs
0
3-day runs
0
7-day runs
0
30-day runs

More Information About Mistral-NeMo-Minitron-8B-SFT huggingface.co Model

More Mistral-NeMo-Minitron-8B-SFT license Visit here:

https://choosealicense.com/licenses/other

Mistral-NeMo-Minitron-8B-SFT huggingface.co

Mistral-NeMo-Minitron-8B-SFT huggingface.co is an AI model on huggingface.co that provides Mistral-NeMo-Minitron-8B-SFT's model effect (), which can be used instantly with this rasyosef Mistral-NeMo-Minitron-8B-SFT model. huggingface.co supports a free trial of the Mistral-NeMo-Minitron-8B-SFT model, and also provides paid use of the Mistral-NeMo-Minitron-8B-SFT. Support call Mistral-NeMo-Minitron-8B-SFT model through api, including Node.js, Python, http.

Mistral-NeMo-Minitron-8B-SFT huggingface.co Url

https://huggingface.co/rasyosef/Mistral-NeMo-Minitron-8B-SFT

rasyosef Mistral-NeMo-Minitron-8B-SFT online free

Mistral-NeMo-Minitron-8B-SFT huggingface.co is an online trial and call api platform, which integrates Mistral-NeMo-Minitron-8B-SFT's modeling effects, including api services, and provides a free online trial of Mistral-NeMo-Minitron-8B-SFT, you can try Mistral-NeMo-Minitron-8B-SFT online for free by clicking the link below.

rasyosef Mistral-NeMo-Minitron-8B-SFT online free url in huggingface.co:

https://huggingface.co/rasyosef/Mistral-NeMo-Minitron-8B-SFT

Mistral-NeMo-Minitron-8B-SFT install

Mistral-NeMo-Minitron-8B-SFT is an open source model from GitHub that offers a free installation service, and any user can find Mistral-NeMo-Minitron-8B-SFT on GitHub to install. At the same time, huggingface.co provides the effect of Mistral-NeMo-Minitron-8B-SFT install, users can directly use Mistral-NeMo-Minitron-8B-SFT installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

Mistral-NeMo-Minitron-8B-SFT install url in huggingface.co:

https://huggingface.co/rasyosef/Mistral-NeMo-Minitron-8B-SFT

Url of Mistral-NeMo-Minitron-8B-SFT

Mistral-NeMo-Minitron-8B-SFT huggingface.co Url

Provider of Mistral-NeMo-Minitron-8B-SFT huggingface.co

rasyosef
ORGANIZATIONS

Other API from rasyosef

huggingface.co

Total runs: 5.1K
Run Growth: 794
Growth Rate: 15.69%
Updated:October 07 2025
huggingface.co

Total runs: 659
Run Growth: 598
Growth Rate: 90.74%
Updated:October 07 2025
huggingface.co

Total runs: 7
Run Growth: -1
Growth Rate: -14.29%
Updated:September 16 2024