Instructions to use jjinkoo/test with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use jjinkoo/test with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("MLP-KTLim/llama-3-Korean-Bllossom-8B") model = PeftModel.from_pretrained(base_model, "jjinkoo/test") - Notebooks
- Google Colab
- Kaggle
|
Download README.md from jjinkoo/test: direct link, hf CLI and curl.
- Browser
- Download file 1.7 kB
-
https://huggingface.co/jjinkoo/test/resolve/main/README.md
- Command line
-
hf download hf://jjinkoo/test/README.md
-
curl -L -o README.md https://huggingface.co/jjinkoo/test/resolve/main/README.md
1.7 kB
metadata
license: llama3
base_model: MLP-KTLim/llama-3-Korean-Bllossom-8B
tags:
- trl
- sft
- generated_from_trainer
model-index:
- name: MyDrive
results: []
library_name: peft
MyDrive
This model is a fine-tuned version of MLP-KTLim/llama-3-Korean-Bllossom-8B on the None dataset.
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
The following bitsandbytes quantization config was used during training:
- quant_method: bitsandbytes
- _load_in_8bit: False
- _load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: True
- bnb_4bit_compute_dtype: bfloat16
- bnb_4bit_quant_storage: uint8
- load_in_4bit: True
- load_in_8bit: False
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0002
- train_batch_size: 1
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 4
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- training_steps: 5000
- mixed_precision_training: Native AMP
Training results
Framework versions
- PEFT 0.4.0.dev0
- Transformers 4.43.3
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1