A newer version of this model is available:
unsloth/Llama-3.1-8B-Instruct-unsloth-bnb-4bit
Gorani Model Card
์๊ฐ (Introduce)
์ด ๋ชจ๋ธ์ ๋ฒ์ญ์ ์ํ ๋ชจ๋ธ์
๋๋ค. ํ๊ตญ ๊ณ ์ ์ด์ ์ ํํ ๋ฒ์ญ์ ์์ฑํ๊ธฐ ์ํด ํ๊ตญ์ด, ์์ด, ์ผ๋ณธ์ด์ ์ธ์ด ๋ฐ์ดํฐ๋ฅผ ํผํฉํ์ฌ unsloth/Llama-3.1-8B-Instruct-unsloth-bnb-4bit์ ํ์ต์์ผ ์์ฑ๋ gorani-8b-new ์
๋๋ค.
gorani๋ ํ์ฌ ํ๊ตญ์ด, ์์ด, ์ผ๋ณธ์ด๋ง ๋ฒ์ญ์ ์ง์ํฉ๋๋ค.
๋ชจ๋ธ ์ ๋ณด
- ๊ฐ๋ฐ์: taeyoon0620
- ๋ชจ๋ธ ์ ํ: llama๋ฅผ ๊ธฐ๋ฐ์ผ๋ก ํ๋ 8B ๋งค๊ฐ๋ณ์ ๋ชจ๋ธ์ธ gorani-8B
- ์ง์ ์ธ์ด: ํ๊ตญ์ด, ์์ด, ์ผ๋ณธ์ด
- ๋ผ์ด์ผ์ค: llama
Training Hyperparameters
- per_device_train_batch_size: 8
- gradient_accumulation_steps: 4
- warmup_steps: 5
- learning_rate: 2e-5
- fp16:
not is_bfloat16_supported()
- num_train_epochs: 3
- weight_decay: 0.01
- lr_scheduler_type: "linear"
ํ์ต ๋ฐ์ดํฐ
ํ์ต ์ฑ๋ฅ ๋น๊ต
- Downloads last month
- 0
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
๐
Ask for provider support
HF Inference deployability: The model has no pipeline_tag.
Model tree for taeyoon12321421/gorani-8b-merged-16bit
Base model
meta-llama/Llama-3.1-8B
Finetuned
meta-llama/Llama-3.1-8B-Instruct