dmis-lab / meditron-7b-olaph

huggingface.co
Total runs: 11
24-hour runs: 1
7-day runs: -2
30-day runs: 1
Model's Last Updated: May 22 2024
text-generation

Introduction of meditron-7b-olaph

Model Details of meditron-7b-olaph

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

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

  • Loss: 0.6808
  • Rewards/chosen: 0.0082
  • Rewards/rejected: 0.0077
  • Rewards/accuracies: 0.5625
  • Rewards/margins: 0.0005
  • Logps/rejected: -631.7355
  • Logps/chosen: -407.7206
  • Logits/rejected: -1.1718
  • Logits/chosen: -1.2239
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 meditron-7b-olaph on huggingface.co

11
Total runs
1
24-hour runs
0
3-day runs
-2
7-day runs
1
30-day runs

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

More meditron-7b-olaph license Visit here:

https://choosealicense.com/licenses/llama2

meditron-7b-olaph huggingface.co

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

meditron-7b-olaph huggingface.co Url

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

dmis-lab meditron-7b-olaph online free

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

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

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

meditron-7b-olaph install

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

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

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

Url of meditron-7b-olaph

meditron-7b-olaph huggingface.co Url

Provider of meditron-7b-olaph huggingface.co

dmis-lab
ORGANIZATIONS

Other API from dmis-lab

huggingface.co

Total runs: 101.6K
Run Growth: -43.7K
Growth Rate: -43.00%
Updated:May 20 2021
huggingface.co

Total runs: 79
Run Growth: -75
Growth Rate: -94.94%
Updated:October 27 2021
huggingface.co

Total runs: 31
Run Growth: 14
Growth Rate: 45.16%
Updated:September 11 2024
huggingface.co

Total runs: 22
Run Growth: 12
Growth Rate: 54.55%
Updated:September 11 2024
huggingface.co

Total runs: 0
Run Growth: 0
Growth Rate: 0.00%
Updated:May 02 2025