RichardErkhov
/

Changgil_-_K2S3-Mistral-7b-v1.3-gguf

GGUF

Model card Files Files and versions Community

Changgil_-_K2S3-Mistral-7b-v1.3-gguf / README.md

RichardErkhov

uploaded readme

19e5d5f verified 25 days ago

preview code

raw

history blame contribute delete

No virus

5.29 kB

	Quantization made by Richard Erkhov.

	[Github](https://github.com/RichardErkhov)

	[Discord](https://discord.gg/pvy7H8DZMG)

	[Request more models](https://github.com/RichardErkhov/quant_request)


	K2S3-Mistral-7b-v1.3 - GGUF
	- Model creator: https://huggingface.co/Changgil/
	- Original model: https://huggingface.co/Changgil/K2S3-Mistral-7b-v1.3/


	\| Name \| Quant method \| Size \|
	\| ---- \| ---- \| ---- \|
	\| [K2S3-Mistral-7b-v1.3.Q2_K.gguf](https://huggingface.co/RichardErkhov/Changgil_-_K2S3-Mistral-7b-v1.3-gguf/blob/main/K2S3-Mistral-7b-v1.3.Q2_K.gguf) \| Q2_K \| 2.6GB \|
	\| [K2S3-Mistral-7b-v1.3.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/Changgil_-_K2S3-Mistral-7b-v1.3-gguf/blob/main/K2S3-Mistral-7b-v1.3.IQ3_XS.gguf) \| IQ3_XS \| 2.89GB \|
	\| [K2S3-Mistral-7b-v1.3.IQ3_S.gguf](https://huggingface.co/RichardErkhov/Changgil_-_K2S3-Mistral-7b-v1.3-gguf/blob/main/K2S3-Mistral-7b-v1.3.IQ3_S.gguf) \| IQ3_S \| 3.04GB \|
	\| [K2S3-Mistral-7b-v1.3.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/Changgil_-_K2S3-Mistral-7b-v1.3-gguf/blob/main/K2S3-Mistral-7b-v1.3.Q3_K_S.gguf) \| Q3_K_S \| 3.02GB \|
	\| [K2S3-Mistral-7b-v1.3.IQ3_M.gguf](https://huggingface.co/RichardErkhov/Changgil_-_K2S3-Mistral-7b-v1.3-gguf/blob/main/K2S3-Mistral-7b-v1.3.IQ3_M.gguf) \| IQ3_M \| 3.14GB \|
	\| [K2S3-Mistral-7b-v1.3.Q3_K.gguf](https://huggingface.co/RichardErkhov/Changgil_-_K2S3-Mistral-7b-v1.3-gguf/blob/main/K2S3-Mistral-7b-v1.3.Q3_K.gguf) \| Q3_K \| 3.35GB \|
	\| [K2S3-Mistral-7b-v1.3.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/Changgil_-_K2S3-Mistral-7b-v1.3-gguf/blob/main/K2S3-Mistral-7b-v1.3.Q3_K_M.gguf) \| Q3_K_M \| 3.35GB \|
	\| [K2S3-Mistral-7b-v1.3.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/Changgil_-_K2S3-Mistral-7b-v1.3-gguf/blob/main/K2S3-Mistral-7b-v1.3.Q3_K_L.gguf) \| Q3_K_L \| 3.64GB \|
	\| [K2S3-Mistral-7b-v1.3.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/Changgil_-_K2S3-Mistral-7b-v1.3-gguf/blob/main/K2S3-Mistral-7b-v1.3.IQ4_XS.gguf) \| IQ4_XS \| 3.76GB \|
	\| [K2S3-Mistral-7b-v1.3.Q4_0.gguf](https://huggingface.co/RichardErkhov/Changgil_-_K2S3-Mistral-7b-v1.3-gguf/blob/main/K2S3-Mistral-7b-v1.3.Q4_0.gguf) \| Q4_0 \| 3.91GB \|
	\| [K2S3-Mistral-7b-v1.3.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/Changgil_-_K2S3-Mistral-7b-v1.3-gguf/blob/main/K2S3-Mistral-7b-v1.3.IQ4_NL.gguf) \| IQ4_NL \| 3.95GB \|
	\| [K2S3-Mistral-7b-v1.3.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/Changgil_-_K2S3-Mistral-7b-v1.3-gguf/blob/main/K2S3-Mistral-7b-v1.3.Q4_K_S.gguf) \| Q4_K_S \| 3.94GB \|
	\| [K2S3-Mistral-7b-v1.3.Q4_K.gguf](https://huggingface.co/RichardErkhov/Changgil_-_K2S3-Mistral-7b-v1.3-gguf/blob/main/K2S3-Mistral-7b-v1.3.Q4_K.gguf) \| Q4_K \| 4.15GB \|
	\| [K2S3-Mistral-7b-v1.3.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/Changgil_-_K2S3-Mistral-7b-v1.3-gguf/blob/main/K2S3-Mistral-7b-v1.3.Q4_K_M.gguf) \| Q4_K_M \| 2.62GB \|
	\| [K2S3-Mistral-7b-v1.3.Q4_1.gguf](https://huggingface.co/RichardErkhov/Changgil_-_K2S3-Mistral-7b-v1.3-gguf/blob/main/K2S3-Mistral-7b-v1.3.Q4_1.gguf) \| Q4_1 \| 3.13GB \|
	\| [K2S3-Mistral-7b-v1.3.Q5_0.gguf](https://huggingface.co/RichardErkhov/Changgil_-_K2S3-Mistral-7b-v1.3-gguf/blob/main/K2S3-Mistral-7b-v1.3.Q5_0.gguf) \| Q5_0 \| 4.75GB \|
	\| [K2S3-Mistral-7b-v1.3.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/Changgil_-_K2S3-Mistral-7b-v1.3-gguf/blob/main/K2S3-Mistral-7b-v1.3.Q5_K_S.gguf) \| Q5_K_S \| 4.75GB \|
	\| [K2S3-Mistral-7b-v1.3.Q5_K.gguf](https://huggingface.co/RichardErkhov/Changgil_-_K2S3-Mistral-7b-v1.3-gguf/blob/main/K2S3-Mistral-7b-v1.3.Q5_K.gguf) \| Q5_K \| 4.87GB \|
	\| [K2S3-Mistral-7b-v1.3.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/Changgil_-_K2S3-Mistral-7b-v1.3-gguf/blob/main/K2S3-Mistral-7b-v1.3.Q5_K_M.gguf) \| Q5_K_M \| 4.87GB \|
	\| [K2S3-Mistral-7b-v1.3.Q5_1.gguf](https://huggingface.co/RichardErkhov/Changgil_-_K2S3-Mistral-7b-v1.3-gguf/blob/main/K2S3-Mistral-7b-v1.3.Q5_1.gguf) \| Q5_1 \| 5.16GB \|
	\| [K2S3-Mistral-7b-v1.3.Q6_K.gguf](https://huggingface.co/RichardErkhov/Changgil_-_K2S3-Mistral-7b-v1.3-gguf/blob/main/K2S3-Mistral-7b-v1.3.Q6_K.gguf) \| Q6_K \| 5.63GB \|
	\| [K2S3-Mistral-7b-v1.3.Q8_0.gguf](https://huggingface.co/RichardErkhov/Changgil_-_K2S3-Mistral-7b-v1.3-gguf/blob/main/K2S3-Mistral-7b-v1.3.Q8_0.gguf) \| Q8_0 \| 5.73GB \|




	Original model description:
	---
	license: cc-by-nc-4.0
	language:
	- en
	- ko
	---

	---
	## Developed by :
	* K2S3

	## Model Number:
	* K2S3-Mistral-7b-v1.3

	## Base Model :
	* mistralai/Mistral-7B-v0.1
	* Changgil/K2S3-Mistral-7b-v1.2

	### Training Data
	* The training data for this model includes alpaca-gpt4-data, and samples from The OpenOrca Dataset.
	* 이 모델의 훈련 데이터에는 alpaca-gpt4-data, 그리고 OpenOrca Dataset에서 제공한 샘플들이 포함됩니다.

	### Training Method
	* This model was fine-tuned on the "Changgil/K2S3-Mistral-7b-v1.2" base model using a full parameter tuning method with SFT (Supervised Fine-Tuning).
	* 이 모델은 "Changgil/K2S3-Mistral-7b-v1.2" 기반 모델을 SFT를 사용하여 전체 파라미터 조정 방법으로 미세조정되었습니다.

	### Hardware
	* Hardware: Utilized two A100 (80G*2EA) GPUs for training.
	* Training Factors: This model was fine-tuned with SFT, using the HuggingFace SFTtrainer and applied fsdp.
	* 이 모델은 SFT를 사용하여 HuggingFace SFTtrainer와 fsdp를 적용하여 미세조정되었습니다.