metadata
license: apache-2.0
extra_gated_description: >-
If you want to learn more about how we process your personal data, please read
our <a href="https://mistral.ai/terms/">Privacy Policy</a>.
base_model: mistralai/Mathstral-7B-v0.1
tags:
- TensorBlock
- GGUF
Feedback and support: TensorBlock's Twitter/X, Telegram Group and Discord server
mistralai/Mathstral-7B-v0.1 - GGUF
This repo contains GGUF format model files for mistralai/Mathstral-7B-v0.1.
The files were quantized using machines provided by TensorBlock, and they are compatible with llama.cpp as of commit b4011.
Prompt template
<s>[INST] {system_prompt}
{prompt}[/INST]
Model file specification
| Filename | Quant type | File Size | Description |
|---|---|---|---|
| Mathstral-7B-v0.1-Q2_K.gguf | Q2_K | 2.723 GB | smallest, significant quality loss - not recommended for most purposes |
| Mathstral-7B-v0.1-Q3_K_S.gguf | Q3_K_S | 3.169 GB | very small, high quality loss |
| Mathstral-7B-v0.1-Q3_K_M.gguf | Q3_K_M | 3.523 GB | very small, high quality loss |
| Mathstral-7B-v0.1-Q3_K_L.gguf | Q3_K_L | 3.826 GB | small, substantial quality loss |
| Mathstral-7B-v0.1-Q4_0.gguf | Q4_0 | 4.113 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| Mathstral-7B-v0.1-Q4_K_S.gguf | Q4_K_S | 4.145 GB | small, greater quality loss |
| Mathstral-7B-v0.1-Q4_K_M.gguf | Q4_K_M | 4.373 GB | medium, balanced quality - recommended |
| Mathstral-7B-v0.1-Q5_0.gguf | Q5_0 | 5.002 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| Mathstral-7B-v0.1-Q5_K_S.gguf | Q5_K_S | 5.002 GB | large, low quality loss - recommended |
| Mathstral-7B-v0.1-Q5_K_M.gguf | Q5_K_M | 5.136 GB | large, very low quality loss - recommended |
| Mathstral-7B-v0.1-Q6_K.gguf | Q6_K | 5.947 GB | very large, extremely low quality loss |
| Mathstral-7B-v0.1-Q8_0.gguf | Q8_0 | 7.703 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/Mathstral-7B-v0.1-GGUF --include "Mathstral-7B-v0.1-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/Mathstral-7B-v0.1-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'