metadata
library_name: transformers
base_model: rasyosef/Mistral-NeMo-Minitron-8B-Chat
datasets:
- teknium/OpenHermes-2.5
pipeline_tag: text-generation
license: other
license_name: nvidia-open-model-license
license_link: >-
https://developer.download.nvidia.com/licenses/nvidia-open-model-license-agreement-june-2024.pdf
tags:
- TensorBlock
- GGUF
Feedback and support: TensorBlock's Twitter/X, Telegram Group and Discord server
rasyosef/Mistral-NeMo-Minitron-8B-Chat - GGUF
This repo contains GGUF format model files for rasyosef/Mistral-NeMo-Minitron-8B-Chat.
The files were quantized using machines provided by TensorBlock, and they are compatible with llama.cpp as of commit b4242.
Prompt template
<|im_start|>system
{system_prompt}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant
Model file specification
| Filename | Quant type | File Size | Description |
|---|---|---|---|
| Mistral-NeMo-Minitron-8B-Chat-Q2_K.gguf | Q2_K | 3.333 GB | smallest, significant quality loss - not recommended for most purposes |
| Mistral-NeMo-Minitron-8B-Chat-Q3_K_S.gguf | Q3_K_S | 3.834 GB | very small, high quality loss |
| Mistral-NeMo-Minitron-8B-Chat-Q3_K_M.gguf | Q3_K_M | 4.209 GB | very small, high quality loss |
| Mistral-NeMo-Minitron-8B-Chat-Q3_K_L.gguf | Q3_K_L | 4.537 GB | small, substantial quality loss |
| Mistral-NeMo-Minitron-8B-Chat-Q4_0.gguf | Q4_0 | 4.880 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| Mistral-NeMo-Minitron-8B-Chat-Q4_K_S.gguf | Q4_K_S | 4.912 GB | small, greater quality loss |
| Mistral-NeMo-Minitron-8B-Chat-Q4_K_M.gguf | Q4_K_M | 5.145 GB | medium, balanced quality - recommended |
| Mistral-NeMo-Minitron-8B-Chat-Q5_0.gguf | Q5_0 | 5.865 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| Mistral-NeMo-Minitron-8B-Chat-Q5_K_S.gguf | Q5_K_S | 5.865 GB | large, low quality loss - recommended |
| Mistral-NeMo-Minitron-8B-Chat-Q5_K_M.gguf | Q5_K_M | 6.001 GB | large, very low quality loss - recommended |
| Mistral-NeMo-Minitron-8B-Chat-Q6_K.gguf | Q6_K | 6.911 GB | very large, extremely low quality loss |
| Mistral-NeMo-Minitron-8B-Chat-Q8_0.gguf | Q8_0 | 8.949 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/Mistral-NeMo-Minitron-8B-Chat-GGUF --include "Mistral-NeMo-Minitron-8B-Chat-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/Mistral-NeMo-Minitron-8B-Chat-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'