edbeeching / dpo_tldr_1b

huggingface.co
Total runs: 9
24-hour runs: 0
7-day runs: 1
30-day runs: 0
Model's Last Updated: August 01 2024
text-generation

Introduction of dpo_tldr_1b

Model Details of dpo_tldr_1b

Visualize in Weights & Biases

dpo_tldr_1b

This model is a fine-tuned version of cleanrl/EleutherAI_pythia-1b-deduped__sft__tldr on an unknown dataset.

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: 3e-06
  • train_batch_size: 4
  • eval_batch_size: 8
  • seed: 42
  • distributed_type: multi-GPU
  • num_devices: 8
  • gradient_accumulation_steps: 16
  • total_train_batch_size: 512
  • total_eval_batch_size: 64
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 1.0
Training results
Framework versions
  • Transformers 4.42.4
  • Pytorch 2.3.1+cu121
  • Datasets 2.20.0
  • Tokenizers 0.19.1

Runs of edbeeching dpo_tldr_1b on huggingface.co

9
Total runs
0
24-hour runs
1
3-day runs
1
7-day runs
0
30-day runs

More Information About dpo_tldr_1b huggingface.co Model

dpo_tldr_1b huggingface.co

dpo_tldr_1b huggingface.co is an AI model on huggingface.co that provides dpo_tldr_1b's model effect (), which can be used instantly with this edbeeching dpo_tldr_1b model. huggingface.co supports a free trial of the dpo_tldr_1b model, and also provides paid use of the dpo_tldr_1b. Support call dpo_tldr_1b model through api, including Node.js, Python, http.

edbeeching dpo_tldr_1b online free

dpo_tldr_1b huggingface.co is an online trial and call api platform, which integrates dpo_tldr_1b's modeling effects, including api services, and provides a free online trial of dpo_tldr_1b, you can try dpo_tldr_1b online for free by clicking the link below.

edbeeching dpo_tldr_1b online free url in huggingface.co:

https://huggingface.co/edbeeching/dpo_tldr_1b

dpo_tldr_1b install

dpo_tldr_1b is an open source model from GitHub that offers a free installation service, and any user can find dpo_tldr_1b on GitHub to install. At the same time, huggingface.co provides the effect of dpo_tldr_1b install, users can directly use dpo_tldr_1b installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

dpo_tldr_1b install url in huggingface.co:

https://huggingface.co/edbeeching/dpo_tldr_1b

Url of dpo_tldr_1b

Provider of dpo_tldr_1b huggingface.co

edbeeching
ORGANIZATIONS

Other API from edbeeching

huggingface.co

Total runs: 15
Run Growth: 0
Growth Rate: 0.00%
Updated:February 14 2023