RichardErkhov/yuuko-eth_-_Monsoon-7B-exp-1-gguf

Quantization made by Richard Erkhov.

Monsoon-7B-exp-1 - GGUF

Model creator: https://huggingface.co/yuuko-eth/
Original model: https://huggingface.co/yuuko-eth/Monsoon-7B-exp-1/

Name	Quant method	Size
Monsoon-7B-exp-1.Q2_K.gguf	Q2_K	2.66GB
Monsoon-7B-exp-1.Q3_K_S.gguf	Q3_K_S	3.09GB
Monsoon-7B-exp-1.Q3_K.gguf	Q3_K	3.42GB
Monsoon-7B-exp-1.Q3_K_M.gguf	Q3_K_M	3.42GB
Monsoon-7B-exp-1.Q3_K_L.gguf	Q3_K_L	3.7GB
Monsoon-7B-exp-1.IQ4_XS.gguf	IQ4_XS	3.83GB
Monsoon-7B-exp-1.Q4_0.gguf	Q4_0	3.98GB
Monsoon-7B-exp-1.IQ4_NL.gguf	IQ4_NL	4.03GB
Monsoon-7B-exp-1.Q4_K_S.gguf	Q4_K_S	4.01GB
Monsoon-7B-exp-1.Q4_K.gguf	Q4_K	4.23GB
Monsoon-7B-exp-1.Q4_K_M.gguf	Q4_K_M	4.23GB
Monsoon-7B-exp-1.Q4_1.gguf	Q4_1	4.41GB
Monsoon-7B-exp-1.Q5_0.gguf	Q5_0	4.83GB
Monsoon-7B-exp-1.Q5_K_S.gguf	Q5_K_S	4.83GB
Monsoon-7B-exp-1.Q5_K.gguf	Q5_K	4.95GB
Monsoon-7B-exp-1.Q5_K_M.gguf	Q5_K_M	4.95GB
Monsoon-7B-exp-1.Q5_1.gguf	Q5_1	5.25GB
Monsoon-7B-exp-1.Q6_K.gguf	Q6_K	5.72GB
Monsoon-7B-exp-1.Q8_0.gguf	Q8_0	7.41GB

Original model description:

inference: false language: - zh - en license: unknown model_name: Monsoon-7B-exp-1 pipeline_tag: text-generation prompt_template: ' SYS_PROMPT [INST] QUERY1 [/INST] RESPONSE1 [INST] QUERY2 [/INST]' tags: - nlp - chinese - mistral - mixtral - traditional_chinese - merge - mergekit - MediaTek-Research/Breeze-7B-Instruct-v0_1 - SanjiWatsuki/Silicon-Maid-7B

雨季 7B exp-1

Breeze 7B Instruct 與 Silicon-Maid-7B (角扮用) 的 dare-ties merge 試驗性模型。

請用 Silicon-Maid-7B 或是 Breeze-7B-Instruct 所推薦的 Prompt 格式進行操作；以下為模型配置。

Monsoon 7B exp-1

This is an experimental Mistral-architecture DARE-TIES merge model of 2x 7B sized fine-tunes. Breeze and Silicon Maid are used together.

Model configuration is as follows:

Breeze-7B-Instruct as base.

Silicon-Maid-7B as model 1.

To use the model, please use either prompt templates suggested by the base models.

Merge Method

This model was merged using the DARE TIES merge method.