Quantization made by Richard Erkhov.

Github

Discord

Request more models

S-SOLAR-10.7B-SFT-v1.2 - GGUF

• Model creator: https://huggingface.co/hwkwon/
• Original model: https://huggingface.co/hwkwon/S-SOLAR-10.7B-SFT-v1.2/

Name	Quant method	Size
S-SOLAR-10.7B-SFT-v1.2.Q2_K.gguf	Q2_K	3.8GB
S-SOLAR-10.7B-SFT-v1.2.IQ3_XS.gguf	IQ3_XS	4.22GB
S-SOLAR-10.7B-SFT-v1.2.IQ3_S.gguf	IQ3_S	4.45GB
S-SOLAR-10.7B-SFT-v1.2.Q3_K_S.gguf	Q3_K_S	4.42GB
S-SOLAR-10.7B-SFT-v1.2.IQ3_M.gguf	IQ3_M	4.59GB
S-SOLAR-10.7B-SFT-v1.2.Q3_K.gguf	Q3_K	4.92GB
S-SOLAR-10.7B-SFT-v1.2.Q3_K_M.gguf	Q3_K_M	4.92GB
S-SOLAR-10.7B-SFT-v1.2.Q3_K_L.gguf	Q3_K_L	5.34GB
S-SOLAR-10.7B-SFT-v1.2.IQ4_XS.gguf	IQ4_XS	5.51GB
S-SOLAR-10.7B-SFT-v1.2.Q4_0.gguf	Q4_0	5.74GB
S-SOLAR-10.7B-SFT-v1.2.IQ4_NL.gguf	IQ4_NL	5.8GB
S-SOLAR-10.7B-SFT-v1.2.Q4_K_S.gguf	Q4_K_S	5.78GB
S-SOLAR-10.7B-SFT-v1.2.Q4_K.gguf	Q4_K	6.1GB
S-SOLAR-10.7B-SFT-v1.2.Q4_K_M.gguf	Q4_K_M	6.1GB
S-SOLAR-10.7B-SFT-v1.2.Q4_1.gguf	Q4_1	6.36GB
S-SOLAR-10.7B-SFT-v1.2.Q5_0.gguf	Q5_0	6.98GB
S-SOLAR-10.7B-SFT-v1.2.Q5_K_S.gguf	Q5_K_S	6.98GB
S-SOLAR-10.7B-SFT-v1.2.Q5_K.gguf	Q5_K	7.17GB
S-SOLAR-10.7B-SFT-v1.2.Q5_K_M.gguf	Q5_K_M	7.17GB
S-SOLAR-10.7B-SFT-v1.2.Q5_1.gguf	Q5_1	7.6GB
S-SOLAR-10.7B-SFT-v1.2.Q6_K.gguf	Q6_K	8.3GB
S-SOLAR-10.7B-SFT-v1.2.Q8_0.gguf	Q8_0	10.75GB

Original model description:

license: cc-by-nc-4.0 language:

• ko

---

S-SOLAR-10.7B

Model Description

This model is a fine-tuned version of Edentns/DataVortexS-10.7B-dpo-v1.11 with DeepSpeed.

Trained Data

TBA

Prompt Template

### User: User query input

### Assistant:

License

This model is licensed under the cc-by-nc-4.0. which allows others to share and adapt the model for non-commercial purposes.