chchen / Mistral-Nemo-12B-Instruct-SAA-Half

huggingface.co
Total runs: 8
24-hour runs: 0
7-day runs: -1
30-day runs: 2
Model's Last Updated: October 11 2024

Introduction of Mistral-Nemo-12B-Instruct-SAA-Half

Model Details of Mistral-Nemo-12B-Instruct-SAA-Half

Mistral-Nemo-12B-Instruct-SAA-Half

This model is a fine-tuned version of mistralai/Mistral-Nemo-Instruct-2407 on the bct_non_cot_dpo_500 dataset. It achieves the following results on the evaluation set:

  • Loss: 0.5932
  • Rewards/chosen: -0.0554
  • Rewards/rejected: -0.0900
  • Rewards/accuracies: 0.7800
  • Rewards/margins: 0.0346
  • Logps/rejected: -0.9001
  • Logps/chosen: -0.5538
  • Logits/rejected: -2.3124
  • Logits/chosen: -2.2862
  • Sft Loss: 0.0563
  • Odds Ratio Loss: 5.3690
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: 5e-06
  • train_batch_size: 2
  • eval_batch_size: 2
  • seed: 42
  • gradient_accumulation_steps: 8
  • total_train_batch_size: 16
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_ratio: 0.1
  • num_epochs: 3.0
Training results
Framework versions
  • PEFT 0.12.0
  • Transformers 4.45.2
  • Pytorch 2.3.0
  • Datasets 2.19.0
  • Tokenizers 0.20.0

Runs of chchen Mistral-Nemo-12B-Instruct-SAA-Half on huggingface.co

8
Total runs
0
24-hour runs
0
3-day runs
-1
7-day runs
2
30-day runs

More Information About Mistral-Nemo-12B-Instruct-SAA-Half huggingface.co Model

More Mistral-Nemo-12B-Instruct-SAA-Half license Visit here:

https://choosealicense.com/licenses/apache-2.0

Mistral-Nemo-12B-Instruct-SAA-Half huggingface.co

Mistral-Nemo-12B-Instruct-SAA-Half huggingface.co is an AI model on huggingface.co that provides Mistral-Nemo-12B-Instruct-SAA-Half's model effect (), which can be used instantly with this chchen Mistral-Nemo-12B-Instruct-SAA-Half model. huggingface.co supports a free trial of the Mistral-Nemo-12B-Instruct-SAA-Half model, and also provides paid use of the Mistral-Nemo-12B-Instruct-SAA-Half. Support call Mistral-Nemo-12B-Instruct-SAA-Half model through api, including Node.js, Python, http.

Mistral-Nemo-12B-Instruct-SAA-Half huggingface.co Url

https://huggingface.co/chchen/Mistral-Nemo-12B-Instruct-SAA-Half

chchen Mistral-Nemo-12B-Instruct-SAA-Half online free

Mistral-Nemo-12B-Instruct-SAA-Half huggingface.co is an online trial and call api platform, which integrates Mistral-Nemo-12B-Instruct-SAA-Half's modeling effects, including api services, and provides a free online trial of Mistral-Nemo-12B-Instruct-SAA-Half, you can try Mistral-Nemo-12B-Instruct-SAA-Half online for free by clicking the link below.

chchen Mistral-Nemo-12B-Instruct-SAA-Half online free url in huggingface.co:

https://huggingface.co/chchen/Mistral-Nemo-12B-Instruct-SAA-Half

Mistral-Nemo-12B-Instruct-SAA-Half install

Mistral-Nemo-12B-Instruct-SAA-Half is an open source model from GitHub that offers a free installation service, and any user can find Mistral-Nemo-12B-Instruct-SAA-Half on GitHub to install. At the same time, huggingface.co provides the effect of Mistral-Nemo-12B-Instruct-SAA-Half install, users can directly use Mistral-Nemo-12B-Instruct-SAA-Half installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

Mistral-Nemo-12B-Instruct-SAA-Half install url in huggingface.co:

https://huggingface.co/chchen/Mistral-Nemo-12B-Instruct-SAA-Half

Url of Mistral-Nemo-12B-Instruct-SAA-Half

Mistral-Nemo-12B-Instruct-SAA-Half huggingface.co Url

Provider of Mistral-Nemo-12B-Instruct-SAA-Half huggingface.co

chchen
ORGANIZATIONS

Other API from chchen