maywell_-_Mistral-ko-7B-v0.1-gguf

RichardErkhov/maywell_-_Mistral-ko-7B-v0.1-gguf

maywell_-_Mistral-ko-7B-v0.1-gguf is a machine learning model from RichardErkhov. Use it for the machine learning task on the model card, and read the license before you ship it in a product.

Downloads · 30 days

471

4% of all-time downloads

All-time downloads

11.3K

Public

Repo size

7.4 GB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.gguf7.4 GB · 100%

At a glance

Access: Public
Created: Jun 7, 2024
Updated: Jun 7, 2024
SHA: a34bb231

Model card

From the Hugging Face model README

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Mistral-ko-7B-v0.1 - GGUF

Model creator: https://huggingface.co/maywell/
Original model: https://huggingface.co/maywell/Mistral-ko-7B-v0.1/

Name	Quant method	Size
Mistral-ko-7B-v0.1.Q2_K.gguf	Q2_K	2.59GB
Mistral-ko-7B-v0.1.IQ3_XS.gguf	IQ3_XS	2.88GB
Mistral-ko-7B-v0.1.IQ3_S.gguf	IQ3_S	0.63GB
Mistral-ko-7B-v0.1.Q3_K_S.gguf	Q3_K_S	0.53GB
Mistral-ko-7B-v0.1.IQ3_M.gguf	IQ3_M	0.16GB
Mistral-ko-7B-v0.1.Q3_K.gguf	Q3_K	0.09GB
Mistral-ko-7B-v0.1.Q3_K_M.gguf	Q3_K_M	0.0GB
Mistral-ko-7B-v0.1.Q3_K_L.gguf	Q3_K_L	0.0GB
Mistral-ko-7B-v0.1.IQ4_XS.gguf	IQ4_XS	0.0GB
Mistral-ko-7B-v0.1.Q4_0.gguf	Q4_0	0.0GB
Mistral-ko-7B-v0.1.IQ4_NL.gguf	IQ4_NL	0.0GB
Mistral-ko-7B-v0.1.Q4_K_S.gguf	Q4_K_S	0.0GB
Mistral-ko-7B-v0.1.Q4_K.gguf	Q4_K	0.0GB
Mistral-ko-7B-v0.1.Q4_K_M.gguf	Q4_K_M	0.0GB
Mistral-ko-7B-v0.1.Q4_1.gguf	Q4_1	0.0GB
Mistral-ko-7B-v0.1.Q5_0.gguf	Q5_0	0.0GB
Mistral-ko-7B-v0.1.Q5_K_S.gguf	Q5_K_S	0.0GB
Mistral-ko-7B-v0.1.Q5_K.gguf	Q5_K	0.0GB
Mistral-ko-7B-v0.1.Q5_K_M.gguf	Q5_K_M	0.0GB
Mistral-ko-7B-v0.1.Q5_1.gguf	Q5_1	0.0GB
Mistral-ko-7B-v0.1.Q6_K.gguf	Q6_K	0.0GB
Mistral-ko-7B-v0.1.Q8_0.gguf	Q8_0	0.0GB

Original model description:

license: cc-by-nc-4.0 language:

ko pipeline_tag: text-generation

해당 모델은 오래된 실험용입니다. 실 사용을 권장하지 않습니다.

Mistral-ko-7B-v0.1

Model Details

Description

Mistral-ko-7B-v0.1는 미스트랄에 한국어에 최적화 된 토크나이저를 적용한 모델입니다. Raw Data로 어느정도 형성된 모델에 시나트라에 사용 된 데이터셋으로 2 Epoch 훈련되었습니다.

-- Further Description After Evaluation --

Comment

토크나이저는 @beomi님의 라마2 한국어 버전을 기반으로 제작되었습니다.

기반 모델을 제공해주신 @jin05102518님께 감사드립니다.

Follow me on twitter: https://twitter.com/stablefluffy

Consider Support me making these model alone: https://www.buymeacoffee.com/mwell or with Runpod Credit Gift 💕

Contact me on Telegram: https://t.me/AlzarTakkarsen

Created: Jun 7, 2024
Updated: Jun 7, 2024