GGUF
mteb
gemma3_text

harrier-oss-v1-270m-GGUF

import numpy as np
from llama_cpp import Llama
from sentence_transformers import SentenceTransformer
from sentence_transformers.util import cos_sim


model = SentenceTransformer(
    "microsoft/harrier-oss-v1-270m",
)
llama = Llama.from_pretrained(
    repo_id="mykor/harrier-oss-v1-270m-GGUF",
    filename="harrier-oss-v1-270M-BF16.gguf",
    verbose=False,
    embedding=True,
    n_ctx=0,
)

text = """๊ธฐํƒ€ ์ค„์ด ๊ดœํžˆ ํ˜ผ์ž ์šธ๋ฆฌ๋Š” ์†Œ๋ฆฌ๊ฐ€
๋‚  ์ผ์œผํ‚ค๋Š” ๊ฒƒ ๊ฐ™์•„
์˜ค๋Š˜๋”ฐ๋ผ ๋ถˆ์€ ๊บผ์ ธ ํ–‡์‚ด์„ ๋ฐ›๋Š”
๋ฐฉ์•ˆ์ด ๋ญ”๊ฐ€ ํ—ˆ์ „ํ•ด

๋ฐ”๋žŒ์•„ ๊ธฐ์–ตํ•ด ์ค„๋ž˜
ํฅ์–ผ๊ฑฐ๋ฆด ๋•Œ ์ด ๋ง˜์„ ๋ฐ”๋ผ๋‹ˆ๊นŒ
์กฐ๊ธˆ ๋” ๋ฉ€๋ฆฌ ๋ฉ€๋ฆฌ์— ์–ด๋””๋“  ๋‹ฟ๊ฒŒ
๋‚ด ์ „๋ถ€๋ฅผ ์ „๋ถ€ ๋‹ค ์ค„๊ฒŒ

์•„๋ฌด๊ฒƒ๋„ ๋“ค๋ฆฌ์ง€ ์•Š๋”๋ผ๋„
๋‚ด ์•ˆ์—” ๋„ˆ๋ฅผ ์œ„ํ•œ ์Œ์ด ๋“ค๋ ค
์„ค๋ ˆ์„œ ๋” ๋ฏธ๋ฃจ๊ธฐ ์‹ซ๋‹คํ•ด๋„
์šฐ์„  ๋งˆ์ดํฌ์—๋งŒ ์†์‚ญ์ผ๊ฒŒ
Ooh-oh, ooh-oh

์ข€ ๋ฏธ์•ˆํ•ด ์•„์ง ์ค€๋น„๊ฐ€ ์•ˆ ๋œ ๊ฒƒ ๊ฐ™์•„
๊ฐ€๋”์€ ํ˜ผ์ž ์‰ฌ๊ณค ํ–ˆ์–ด
๋„์–ด๋…ผ ๋ง˜๋“ค์€ ์ด๋ฏธ ์ „๋ถ€ ๋ง๋ผ
๋‚ด๊ฐ€ ๊ฐˆ ๊ณณ์„ ์ •ํ–ˆ์œผ๋‹ˆ๊นŒ

๋‹ฌ๋น›์•„ ๊ธฐ์–ตํ•ด์ค„๋ž˜
๊ฟˆ์—์„œ ๋ชฐ๋ž˜ ๋ถ€๋ฅผ์ง€ ๋ชจ๋ฅด๋‹ˆ๊นŒ
์กฐ๊ธˆ ๋” ๋ฉ€๋ฆฌ ๋ฉ€๋ฆฌ์— ์–ด๋””๋“  ๋‹ฟ๊ฒŒ
๋‚ด ์ „๋ถ€๋ฅผ ์ „๋ถ€ ๋‹ค ์ค„๊ฒŒ

์•„๋ฌด๊ฒƒ๋„ ๋“ค๋ฆฌ์ง€ ์•Š๋”๋ผ๋„
๋‚ด ์•ˆ์—” ๋„ˆ๋ฅผ ์œ„ํ•œ ์Œ์ด ๋“ค๋ ค
์„ค๋ ˆ์„œ ๋” ๋ฏธ๋ฃจ๊ธฐ ์‹ซ๋‹คํ•ด๋„
์šฐ์„  ๋งˆ์ดํฌ์—๋งŒ ์†์‚ญ์ผ๊ฒŒ
Ooh-oh (oh) ooh-oh (oh) ooh-oh"""


embed1 = model.encode(text)
embed2 = np.array(llama.embed(text), dtype=np.float32)
print(cos_sim(embed1, embed2).item())
0.9999479055404663
Downloads last month
1,058
GGUF
Model size
0.3B params
Architecture
gemma3
Hardware compatibility
Log In to add your hardware

3-bit

4-bit

5-bit

6-bit

8-bit

16-bit

Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for mykor/harrier-oss-v1-270m-GGUF

Quantized
(7)
this model