Feedback and support: TensorBlock's Twitter/X, Telegram Group and Discord server
BeastyZ/e5-R-mistral-7b - GGUF
This repo contains GGUF format model files for BeastyZ/e5-R-mistral-7b.
The files were quantized using machines provided by TensorBlock, and they are compatible with llama.cpp as of commit b4011.
Prompt template
Model file specification
Filename | Quant type | File Size | Description |
---|---|---|---|
e5-R-mistral-7b-Q2_K.gguf | Q2_K | 2.719 GB | smallest, significant quality loss - not recommended for most purposes |
e5-R-mistral-7b-Q3_K_S.gguf | Q3_K_S | 3.165 GB | very small, high quality loss |
e5-R-mistral-7b-Q3_K_M.gguf | Q3_K_M | 3.519 GB | very small, high quality loss |
e5-R-mistral-7b-Q3_K_L.gguf | Q3_K_L | 3.822 GB | small, substantial quality loss |
e5-R-mistral-7b-Q4_0.gguf | Q4_0 | 4.109 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
e5-R-mistral-7b-Q4_K_S.gguf | Q4_K_S | 4.140 GB | small, greater quality loss |
e5-R-mistral-7b-Q4_K_M.gguf | Q4_K_M | 4.368 GB | medium, balanced quality - recommended |
e5-R-mistral-7b-Q5_0.gguf | Q5_0 | 4.998 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
e5-R-mistral-7b-Q5_K_S.gguf | Q5_K_S | 4.998 GB | large, low quality loss - recommended |
e5-R-mistral-7b-Q5_K_M.gguf | Q5_K_M | 5.131 GB | large, very low quality loss - recommended |
e5-R-mistral-7b-Q6_K.gguf | Q6_K | 5.942 GB | very large, extremely low quality loss |
e5-R-mistral-7b-Q8_0.gguf | Q8_0 | 7.696 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/e5-R-mistral-7b-GGUF --include "e5-R-mistral-7b-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/e5-R-mistral-7b-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
- Downloads last month
- 181
Model tree for tensorblock/e5-R-mistral-7b-GGUF
Base model
BeastyZ/e5-R-mistral-7bDataset used to train tensorblock/e5-R-mistral-7b-GGUF
Evaluation results
- map_at_1 on MTEB ArguAnatest set self-reported33.570
- map_at_10 on MTEB ArguAnatest set self-reported49.952
- map_at_100 on MTEB ArguAnatest set self-reported50.673
- map_at_1000 on MTEB ArguAnatest set self-reported50.674
- map_at_3 on MTEB ArguAnatest set self-reported44.915
- map_at_5 on MTEB ArguAnatest set self-reported47.877
- mrr_at_1 on MTEB ArguAnatest set self-reported34.211
- mrr_at_10 on MTEB ArguAnatest set self-reported50.190
- mrr_at_100 on MTEB ArguAnatest set self-reported50.905
- mrr_at_1000 on MTEB ArguAnatest set self-reported50.906