RichardErkhov/Changgil_-_K2S3-Mistral-7b-v1.1-gguf

Quantization made by Richard Erkhov.

Github

Discord

Request more models

K2S3-Mistral-7b-v1.1 - GGUF

• Model creator: https://huggingface.co/Changgil/
• Original model: https://huggingface.co/Changgil/K2S3-Mistral-7b-v1.1/

Name	Quant method	Size
K2S3-Mistral-7b-v1.1.Q2_K.gguf	Q2_K	2.6GB
K2S3-Mistral-7b-v1.1.IQ3_XS.gguf	IQ3_XS	2.89GB
K2S3-Mistral-7b-v1.1.IQ3_S.gguf	IQ3_S	3.04GB
K2S3-Mistral-7b-v1.1.Q3_K_S.gguf	Q3_K_S	3.02GB
K2S3-Mistral-7b-v1.1.IQ3_M.gguf	IQ3_M	3.14GB
K2S3-Mistral-7b-v1.1.Q3_K.gguf	Q3_K	3.35GB
K2S3-Mistral-7b-v1.1.Q3_K_M.gguf	Q3_K_M	3.35GB
K2S3-Mistral-7b-v1.1.Q3_K_L.gguf	Q3_K_L	3.64GB
K2S3-Mistral-7b-v1.1.IQ4_XS.gguf	IQ4_XS	3.76GB
K2S3-Mistral-7b-v1.1.Q4_0.gguf	Q4_0	3.91GB
K2S3-Mistral-7b-v1.1.IQ4_NL.gguf	IQ4_NL	3.95GB
K2S3-Mistral-7b-v1.1.Q4_K_S.gguf	Q4_K_S	3.94GB
K2S3-Mistral-7b-v1.1.Q4_K.gguf	Q4_K	4.15GB
K2S3-Mistral-7b-v1.1.Q4_K_M.gguf	Q4_K_M	4.15GB
K2S3-Mistral-7b-v1.1.Q4_1.gguf	Q4_1	4.33GB
K2S3-Mistral-7b-v1.1.Q5_0.gguf	Q5_0	4.75GB
K2S3-Mistral-7b-v1.1.Q5_K_S.gguf	Q5_K_S	4.75GB
K2S3-Mistral-7b-v1.1.Q5_K.gguf	Q5_K	4.87GB
K2S3-Mistral-7b-v1.1.Q5_K_M.gguf	Q5_K_M	4.87GB
K2S3-Mistral-7b-v1.1.Q5_1.gguf	Q5_1	5.16GB
K2S3-Mistral-7b-v1.1.Q6_K.gguf	Q6_K	5.63GB
K2S3-Mistral-7b-v1.1.Q8_0.gguf	Q8_0	7.3GB

Original model description:

license: cc-by-nc-4.0 language: - en - ko

---

Developed by :

• K2S3

Model Number:

• K2S3-Mistral-7b-v1.1

Base Model :

• mistralai/Mistral-7B-v0.1

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 "mistralai/Mistral-7B-v0.1" base model using a full parameter tuning method with SFT (Supervised Fine-Tuning).
• 이 모델은 "mistralai/Mistral-7B-v0.1" 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.