metadata
inference: false
language:
- zh
- en
license: unknown
model_name: Monsoon-7B-exp-1
pipeline_tag: text-generation
prompt_template: <s> 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
- TensorBlock
- GGUF
base_model: yuuko-eth/Monsoon-7B-exp-1
Feedback and support: TensorBlock's Twitter/X, Telegram Group and Discord server
yuuko-eth/Monsoon-7B-exp-1 - GGUF
This repo contains GGUF format model files for yuuko-eth/Monsoon-7B-exp-1.
The files were quantized using machines provided by TensorBlock, and they are compatible with llama.cpp as of commit b4242.
Prompt template
Model file specification
| Filename | Quant type | File Size | Description |
|---|---|---|---|
| Monsoon-7B-exp-1-Q2_K.gguf | Q2_K | 2.860 GB | smallest, significant quality loss - not recommended for most purposes |
| Monsoon-7B-exp-1-Q3_K_S.gguf | Q3_K_S | 3.318 GB | very small, high quality loss |
| Monsoon-7B-exp-1-Q3_K_M.gguf | Q3_K_M | 3.673 GB | very small, high quality loss |
| Monsoon-7B-exp-1-Q3_K_L.gguf | Q3_K_L | 3.976 GB | small, substantial quality loss |
| Monsoon-7B-exp-1-Q4_0.gguf | Q4_0 | 4.279 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| Monsoon-7B-exp-1-Q4_K_S.gguf | Q4_K_S | 4.310 GB | small, greater quality loss |
| Monsoon-7B-exp-1-Q4_K_M.gguf | Q4_K_M | 4.538 GB | medium, balanced quality - recommended |
| Monsoon-7B-exp-1-Q5_0.gguf | Q5_0 | 5.183 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| Monsoon-7B-exp-1-Q5_K_S.gguf | Q5_K_S | 5.183 GB | large, low quality loss - recommended |
| Monsoon-7B-exp-1-Q5_K_M.gguf | Q5_K_M | 5.317 GB | large, very low quality loss - recommended |
| Monsoon-7B-exp-1-Q6_K.gguf | Q6_K | 6.143 GB | very large, extremely low quality loss |
| Monsoon-7B-exp-1-Q8_0.gguf | Q8_0 | 7.957 GB | very large, extremely low quality loss - not recommended |
Downloading instruction
Command line
Firstly, install Huggingface Client
pip install -U "huggingface_hub[cli]"
Then, downoad the individual model file the a local directory
huggingface-cli download tensorblock/Monsoon-7B-exp-1-GGUF --include "Monsoon-7B-exp-1-Q2_K.gguf" --local-dir MY_LOCAL_DIR
If you wanna download multiple model files with a pattern (e.g., *Q4_K*gguf), you can try:
huggingface-cli download tensorblock/Monsoon-7B-exp-1-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'