dmis-lab / mistral-7b-olaph

huggingface.co
Total runs: 13
24-hour runs: 1
7-day runs: 4
30-day runs: -6
Model's Last Updated: 5월 22 2024
text-generation

Introduction of mistral-7b-olaph

Model Details of mistral-7b-olaph

mistral-7b-wo-kqa_golden-iter-dpo-step2

This model is a fine-tuned version of Minbyul/mistral-7b-wo-kqa_golden-iter-sft-step1 on the HuggingFaceH4/ultrafeedback_binarized dataset. It achieves the following results on the evaluation set:

  • Loss: 0.5463
  • Rewards/chosen: -0.5234
  • Rewards/rejected: -1.3980
  • Rewards/accuracies: 0.8125
  • Rewards/margins: 0.8746
  • Logps/rejected: -518.7740
  • Logps/chosen: -233.3091
  • Logits/rejected: -3.7466
  • Logits/chosen: -3.9181
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-07
  • train_batch_size: 8
  • eval_batch_size: 8
  • seed: 42
  • distributed_type: multi-GPU
  • num_devices: 4
  • gradient_accumulation_steps: 2
  • total_train_batch_size: 64
  • total_eval_batch_size: 32
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_ratio: 0.1
  • num_epochs: 1
Training results
Framework versions
  • Transformers 4.39.0.dev0
  • Pytorch 2.1.2
  • Datasets 2.14.6
  • Tokenizers 0.15.2

Runs of dmis-lab mistral-7b-olaph on huggingface.co

13
Total runs
1
24-hour runs
2
3-day runs
4
7-day runs
-6
30-day runs

More Information About mistral-7b-olaph huggingface.co Model

More mistral-7b-olaph license Visit here:

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

mistral-7b-olaph huggingface.co

mistral-7b-olaph huggingface.co is an AI model on huggingface.co that provides mistral-7b-olaph's model effect (), which can be used instantly with this dmis-lab mistral-7b-olaph model. huggingface.co supports a free trial of the mistral-7b-olaph model, and also provides paid use of the mistral-7b-olaph. Support call mistral-7b-olaph model through api, including Node.js, Python, http.

mistral-7b-olaph huggingface.co Url

https://huggingface.co/dmis-lab/mistral-7b-olaph

dmis-lab mistral-7b-olaph online free

mistral-7b-olaph huggingface.co is an online trial and call api platform, which integrates mistral-7b-olaph's modeling effects, including api services, and provides a free online trial of mistral-7b-olaph, you can try mistral-7b-olaph online for free by clicking the link below.

dmis-lab mistral-7b-olaph online free url in huggingface.co:

https://huggingface.co/dmis-lab/mistral-7b-olaph

mistral-7b-olaph install

mistral-7b-olaph is an open source model from GitHub that offers a free installation service, and any user can find mistral-7b-olaph on GitHub to install. At the same time, huggingface.co provides the effect of mistral-7b-olaph install, users can directly use mistral-7b-olaph installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

mistral-7b-olaph install url in huggingface.co:

https://huggingface.co/dmis-lab/mistral-7b-olaph

Url of mistral-7b-olaph

mistral-7b-olaph huggingface.co Url

Provider of mistral-7b-olaph huggingface.co

dmis-lab
ORGANIZATIONS

Other API from dmis-lab

huggingface.co

Total runs: 1.3M
Run Growth: -138.0K
Growth Rate: -10.89%
Updated: 5월 20 2021
huggingface.co

Total runs: 1.4K
Run Growth: 389
Growth Rate: 29.76%
Updated: 10월 27 2021