Edit model card

Pexels 이미지

Merged below called "gx thinking Groove Feeling X-mas"

There is no such thing as a flawless system. It's about using it appropriately and reasonably without pushing it to its limits.

Test

Test GGUF : llama-3.2-koen-gx-3b-instruct-Q5_K_M.gguf

(.venv) jaylee@lees-MacBook-Pro-2 hf_hub % ollama create asisansoul -f Modelfile_3b 
transferring model data 100% 
using existing layer sha256:c7e60df75175e0bfe4bad1c7715247f122a03893d8eb45f052613ffeca193af1 
using existing layer sha256:966de95ca8a62200913e3f8bfbf84c8494536f1b94b49166851e76644e966396 
using existing layer sha256:56bb8bd477a519ffa694fc449c2413c6f0e1d3b1c88fa7e3c9d88d3ae49d4dcb 
creating new layer sha256:8e696b7f0a7623172de768d864ce4586f0951ffc5411bd7ba7ed1f25f5917b57 
writing manifest 
success 


(.venv) jaylee@lees-MacBook-Pro-2 hf_hub % ollama run asisansoul:latest
>>> λŒ€ν•œλ―Όκ΅­ μˆ˜λ„λŠ”
λŒ€ν•œλ―Όκ΅­μ˜ μˆ˜λ„λŠ” μ„œμšΈμž…λ‹ˆλ‹€.

>>> λŒ€ν•œλ―Όκ΅­ ν˜„μž¬ λŒ€ν†΅λ Ήμ€
ν•œκ΅­ λŒ€ν†΅λ Ήμ€ μœ€μ„μ—΄μž…λ‹ˆλ‹€. 2022λ…„ 5μ›” 10일뢀터 ν•œκ΅­μ˜ 제35λŒ€ λŒ€ν†΅λ ΉμœΌλ‘œ μž„λͺ…λ˜μ—ˆμŠ΅λ‹ˆλ‹€.

>>> μ² μˆ˜κ°€ 20개의 연필을 가지고 μžˆμ—ˆλŠ”λ° μ˜ν¬κ°€ μ ˆλ°˜μ„ κ°€μ Έκ°€κ³  λ―Όμˆ˜κ°€ 남은 5개λ₯Ό κ°€μ Έκ°”μœΌλ©΄ μ² μˆ˜μ—κ²Œ 남은 μ—°ν•„μ˜ κ°―μˆ˜λŠ” λͺ‡κ°œμΈκ°€μš”?
μ˜ν¬κ°€ 절반의 연필을 κ°€μ Έκ°„λ‹€λ©΄, 20 / 2 = 10개의 연필이 λ‚¨μ•˜μŠ΅λ‹ˆλ‹€.

이제 λ―Όμˆ˜κ°€ 5개의 연필을 κ°€μ Έκ°”μœΌλ‹ˆ, 철수의 남은 연필은 10 - 5 = 5κ°œμž…λ‹ˆλ‹€.

>>> μ˜μ–΄λ‘œ
If Yoon has 20 pens and half of them (10) are taken by Eun, then Yoon will have 10 pens left.

Then, Min takes 5 pens away from him. So, Yoon is left with:

10 - 5 = 5

Yoon now has 5 pens remaining.
@article{Llama3.2KoEnMerged3BInstruct,
  title={asiansoul/llama-3.2-koen-merged-3b-instruct-GGUF Card},
  author={Asiansoul},
  merged={Asiansoul},
  year={2024},
  url = {https://huggingface.co/asiansoul/llama-3.2-koen-merged-3b-instruct-GGUF}
}
Downloads last month
166
GGUF
Model size
3.21B params
Architecture
llama

3-bit

4-bit

5-bit

6-bit

8-bit

Inference Examples
Unable to determine this model's library. Check the docs .

Model tree for asiansoul/llama-3.2-koen-merged-3b-instruct-GGUF

Quantized
(137)
this model