minpeter / ko-tiny-exp

huggingface.co
Total runs: 115
24-hour runs: 0
7-day runs: 0
30-day runs: 0
Model's Last Updated: June 06 2025
text-generation

Introduction of ko-tiny-exp

Model Details of ko-tiny-exp

Built with Axolotl

See axolotl config

axolotl version: 0.10.0.dev0

base_model: minpeter/tiny-ko-base

hub_model_id: minpeter/tiny-ko-sft
output_dir: ./outputs/tiny-ko-sft
wandb_project: "axolotl"
wandb_entity: "kasfiekfs-e"

chat_template: chatml
datasets:
  - path: lemon-mint/Korean-FineTome-100k
    type: chat_template
    split: train[:10%]
    field_messages: messages
    message_property_mappings:
      role: role
      content: content

  - path: lemon-mint/smol-koreantalk
    type: chat_template
    split: train[:10%]
    field_messages: messages
    message_property_mappings:
      role: role
      content: content

  - path: heegyu/open-korean-instructions-v20231020
    type: chat_template
    split: train[:10%]
    field_messages: conversations
    message_property_mappings:
      role: from
      content: value
    roles:
      user: ["human", "user"]
      assistant: ["gpt", "assistant", "bot"]
      system: ["system", "input"]

  # NOTE: https://github.com/FreedomIntelligence/MultilingualSIFT
  - path: FreedomIntelligence/evol-instruct-korean
    type: chat_template
    split: train[:10%]
    field_messages: conversations
    message_property_mappings:
      role: from
      content: value

  - path: FreedomIntelligence/alpaca-gpt4-korean
    type: chat_template
    split: train[:10%]
    field_messages: conversations
    message_property_mappings:
      role: from
      content: value

  - path: FreedomIntelligence/sharegpt-korean
    type: chat_template
    split: train[:10%]
    field_messages: conversations
    message_property_mappings:
      role: from
      content: value

  - path: coastral/korean-writing-style-instruct
    type: chat_template
    split: train[:10%]
    field_messages: conversations
    message_property_mappings:
      role: from
      content: value

  - path: devngho/korean-instruction-mix
    type: chat_template
    split: train[:10%]
    field_messages: messages
    message_property_mappings:
      role: from
      content: value

  - path: youjunhyeok/Magpie-Pro-300K-Filtered-ko
    type: chat_template
    split: train[:10%]
    field_messages: conversations
    message_property_mappings:
      role: from
      content: value

  - path: youjunhyeok/smoltalk-ko-translate
    type: chat_template
    name: merge_filtered
    field_messages: conversations
    message_property_mappings:
      role: role
      content: content

dataset_prepared_path: last_run_prepared
val_set_size: 0.05

save_steps: 200
warmup_steps: 20
eval_steps: 200

sequence_len: 4096

# <<<< experimental settings <<<<
sample_packing: true
train_on_inputs: false
# >>>> experimental settings >>>

pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 32

optimizer: paged_adamw_8bit
lr_scheduler: cosine
learning_rate: 1e-3

bf16: auto
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
resume_from_checkpoint:
logging_steps: 1
flash_attention: true

num_epochs: 1
weight_decay: 0.0

tiny-ko-sft

This model is a fine-tuned version of minpeter/tiny-ko-base on the lemon-mint/Korean-FineTome-100k, the lemon-mint/smol-koreantalk, the heegyu/open-korean-instructions-v20231020, the FreedomIntelligence/evol-instruct-korean, the FreedomIntelligence/alpaca-gpt4-korean, the FreedomIntelligence/sharegpt-korean, the coastral/korean-writing-style-instruct, the devngho/korean-instruction-mix, the youjunhyeok/Magpie-Pro-300K-Filtered-ko and the youjunhyeok/smoltalk-ko-translate datasets. It achieves the following results on the evaluation set:

  • Loss: 1.5297
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: 0.001
  • train_batch_size: 32
  • eval_batch_size: 32
  • seed: 42
  • distributed_type: multi-GPU
  • num_devices: 2
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 256
  • total_eval_batch_size: 64
  • optimizer: Use OptimizerNames.PAGED_ADAMW_8BIT with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_steps: 20
  • training_steps: 817
Training results
Training Loss Epoch Step Validation Loss
2.3518 0.0012 1 2.3640
1.6322 0.2446 200 1.6913
1.5903 0.4891 400 1.6003
1.5146 0.7337 600 1.5392
1.5277 0.9783 800 1.5297
Framework versions
  • Transformers 4.52.3
  • Pytorch 2.6.0+cu124
  • Datasets 3.6.0
  • Tokenizers 0.21.1

Runs of minpeter ko-tiny-exp on huggingface.co

115
Total runs
0
24-hour runs
0
3-day runs
0
7-day runs
0
30-day runs

More Information About ko-tiny-exp huggingface.co Model

ko-tiny-exp huggingface.co

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

ko-tiny-exp huggingface.co Url

https://huggingface.co/minpeter/ko-tiny-exp

minpeter ko-tiny-exp online free

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

minpeter ko-tiny-exp online free url in huggingface.co:

https://huggingface.co/minpeter/ko-tiny-exp

ko-tiny-exp install

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

ko-tiny-exp install url in huggingface.co:

https://huggingface.co/minpeter/ko-tiny-exp

Url of ko-tiny-exp

ko-tiny-exp huggingface.co Url

Provider of ko-tiny-exp huggingface.co

minpeter
ORGANIZATIONS

Other API from minpeter

huggingface.co

Total runs: 253
Run Growth: 0
Growth Rate: 0.00%
Updated:April 07 2025
huggingface.co

Total runs: 20
Run Growth: -32
Growth Rate: -160.00%
Updated:July 31 2025
huggingface.co

Total runs: 0
Run Growth: 0
Growth Rate: 0.00%
Updated:September 16 2024