You can deploy this model and start earning money today!

RichardErkhov/
ifuseok_-_yi-ko-playtus-instruct-v0.2-gguf

Name: ifuseok_-_yi-ko-playtus-instruct-v0.2-gguf
Availability: InStock

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

yi-ko-playtus-instruct-v0.2 - GGUF

Model creator: https://huggingface.co/ifuseok/
Original model: https://huggingface.co/ifuseok/yi-ko-playtus-instruct-v0.2/

Name	Quant method	Size
yi-ko-playtus-instruct-v0.2.Q2_K.gguf	Q2_K	2.24GB
yi-ko-playtus-instruct-v0.2.IQ3_XS.gguf	IQ3_XS	2.48GB
yi-ko-playtus-instruct-v0.2.IQ3_S.gguf	IQ3_S	2.6GB
yi-ko-playtus-instruct-v0.2.Q3_K_S.gguf	Q3_K_S	2.59GB
yi-ko-playtus-instruct-v0.2.IQ3_M.gguf	IQ3_M	2.69GB
yi-ko-playtus-instruct-v0.2.Q3_K.gguf	Q3_K	2.86GB
yi-ko-playtus-instruct-v0.2.Q3_K_M.gguf	Q3_K_M	2.86GB
yi-ko-playtus-instruct-v0.2.Q3_K_L.gguf	Q3_K_L	3.08GB
yi-ko-playtus-instruct-v0.2.IQ4_XS.gguf	IQ4_XS	3.18GB
yi-ko-playtus-instruct-v0.2.Q4_0.gguf	Q4_0	3.32GB
yi-ko-playtus-instruct-v0.2.IQ4_NL.gguf	IQ4_NL	3.35GB
yi-ko-playtus-instruct-v0.2.Q4_K_S.gguf	Q4_K_S	3.34GB
yi-ko-playtus-instruct-v0.2.Q4_K.gguf	Q4_K	3.5GB
yi-ko-playtus-instruct-v0.2.Q4_K_M.gguf	Q4_K_M	3.5GB
yi-ko-playtus-instruct-v0.2.Q4_1.gguf	Q4_1	3.66GB
yi-ko-playtus-instruct-v0.2.Q5_0.gguf	Q5_0	4.0GB
yi-ko-playtus-instruct-v0.2.Q5_K_S.gguf	Q5_K_S	4.0GB
yi-ko-playtus-instruct-v0.2.Q5_K.gguf	Q5_K	4.09GB
yi-ko-playtus-instruct-v0.2.Q5_K_M.gguf	Q5_K_M	4.09GB
yi-ko-playtus-instruct-v0.2.Q5_1.gguf	Q5_1	4.34GB
yi-ko-playtus-instruct-v0.2.Q6_K.gguf	Q6_K	4.72GB
yi-ko-playtus-instruct-v0.2.Q8_0.gguf	Q8_0	6.12GB

Original model description:

language:

en pipeline_tag: text-generation license: cc-by-nc-sa-4.0 datasets:
nlpai-lab/databricks-dolly-15k-ko
kyujinpy/KOR-OpenOrca-Platypus-v3

Input Models input text only.

Output Models generate text only.

Base Model beomi/Yi-Ko-6B

Training Dataset

Implementation Code

python

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch
repo = "ifuseok/yi-ko-playtus-instruct-v0.2"
OpenOrca = AutoModelForCausalLM.from_pretrained(
        repo,
        return_dict=True,
        torch_dtype=torch.float16,
        device_map='auto'
)
OpenOrca_tokenizer = AutoTokenizer.from_pretrained(repo)

Prompt Example

<|system|>
시스템 메시지 입니다. <|endoftext|>
<|user|>
유저  입니다.<|endoftext|>
<|assistant|>
어시스턴트 입니다.<|endoftext|>

RichardErkhov/ifuseok_-_yi-ko-playtus-instruct-v0.2-gguf

Original model description:

Implementation Code

Prompt Example

RichardErkhov/
ifuseok_-_yi-ko-playtus-instruct-v0.2-gguf