aripos1/gorani_dataset
Viewer โข Updated โข 27.1k โข 13
How to use taeyoon12321421/gorani-gemma-model-2b with PEFT:
from peft import PeftModel
from transformers import AutoModelForCausalLM
base_model = AutoModelForCausalLM.from_pretrained("unsloth/gemma-2b-it-bnb-4bit")
model = PeftModel.from_pretrained(base_model, "taeyoon12321421/gorani-gemma-model-2b")How to use taeyoon12321421/gorani-gemma-model-2b with Unsloth Studio:
curl -fsSL https://unsloth.ai/install.sh | sh # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for taeyoon12321421/gorani-gemma-model-2b to start chatting
irm https://unsloth.ai/install.ps1 | iex # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for taeyoon12321421/gorani-gemma-model-2b to start chatting
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for taeyoon12321421/gorani-gemma-model-2b to start chatting
pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
model_name="taeyoon12321421/gorani-gemma-model-2b",
max_seq_length=2048,
)์ด ๋ชจ๋ธ์ ๋ฒ์ญ์ ์ํ ๋ชจ๋ธ์
๋๋ค. ํ๊ตญ ๊ณ ์ ์ด์ ์ ํํ ๋ฒ์ญ์ ์์ฑํ๊ธฐ ์ํด ํ๊ตญ์ด, ์์ด, ์ผ๋ณธ์ด์ ์ธ์ด ๋ฐ์ดํฐ๋ฅผ ํผํฉํ์ฌ unsloth/gemma-2b-it-bnb-4bit์ ํ์ต์์ผ ์์ฑ๋ gorani-2B ์
๋๋ค.
gorani๋ ํ์ฌ ํ๊ตญ์ด, ์์ด, ์ผ๋ณธ์ด๋ง ๋ฒ์ญ์ ์ง์ํฉ๋๋ค.
not is_bfloat16_supported() | Step | Training Loss | Validation Loss |
|---|---|---|
| 50 | 0.856900 | 1.243296 |
| 100 | 0.637300 | 1.080636 |
| 150 | 0.561300 | 1.015324 |
| 200 | 0.523100 | 0.972539 |
| 250 | 0.491600 | 0.951547 |
| 300 | 0.485000 | 0.942520 |
| 350 | 0.457100 | 0.928466 |
| 400 | 0.482600 | 0.913566 |
| 450 | 0.445000 | 0.915080 |
| 500 | 0.447300 | 0.900509 |
| 550 | 0.443200 | 0.896823 |
| 600 | 0.420800 | 0.898253 |
| 650 | 0.430200 | 0.888035 |
| 700 | 0.428700 | 0.884415 |
| 750 | 0.416400 | 0.875832 |
| 800 | 0.397400 | 0.877212 |
| 850 | 0.403800 | 0.878696 |
| 900 | 0.410400 | 0.873603 |
| 950 | 0.423900 | 0.876391 |
| 1000 | 0.412100 | 0.874712 |
| 1050 | 0.404000 | 0.878219 |
| 1100 | 0.391000 | 0.868475 |
| 1150 | 0.383800 | 0.867502 |
| 1200 | 0.388800 | 0.877054 |
| 1250 | 0.382200 | 0.864894 |
| 1300 | 0.389500 | 0.862716 |
| 1350 | 0.401100 | 0.857156 |
| 1400 | 0.364600 | 0.865956 |
| 1450 | 0.386700 | 0.858560 |
| 1500 | 0.379200 | 0.860608 |
| 1550 | 0.370000 | 0.864580 |
| 1600 | 0.367900 | 0.863778 |
| 1650 | 0.360100 | 0.866951 |
| 1700 | 0.372300 | 0.867361 |
| 1750 | 0.378400 | 0.867690 |
| 1800 | 0.371100 | 0.863734 |
| 1850 | 0.376400 | 0.862673 |
| 1900 | 0.364200 | 0.862987 |
| 1950 | 0.368000 | 0.865702 |
| 2000 | 0.374900 | 0.865652 |
Base model
unsloth/gemma-2b-it-bnb-4bit