metadata
license: apache-2.0
language:
- en
thumbnail: >-
https://cdn-uploads.huggingface.co/production/uploads/645cfe4603fc86c46b3e46d1/EB04vvPdDXGDhB4TsNHG_.jpeg
tags:
- moe
- merge
- TensorBlock
- GGUF
base_model: Kquant03/CognitiveFusion2-4x7B-BF16
Feedback and support: TensorBlock's Twitter/X, Telegram Group and Discord server
Kquant03/CognitiveFusion2-4x7B-BF16 - GGUF
This repo contains GGUF format model files for Kquant03/CognitiveFusion2-4x7B-BF16.
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 |
|---|---|---|---|
| CognitiveFusion2-4x7B-BF16-Q2_K.gguf | Q2_K | 8.236 GB | smallest, significant quality loss - not recommended for most purposes |
| CognitiveFusion2-4x7B-BF16-Q3_K_S.gguf | Q3_K_S | 9.717 GB | very small, high quality loss |
| CognitiveFusion2-4x7B-BF16-Q3_K_M.gguf | Q3_K_M | 10.785 GB | very small, high quality loss |
| CognitiveFusion2-4x7B-BF16-Q3_K_L.gguf | Q3_K_L | 11.683 GB | small, substantial quality loss |
| CognitiveFusion2-4x7B-BF16-Q4_0.gguf | Q4_0 | 12.688 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| CognitiveFusion2-4x7B-BF16-Q4_K_S.gguf | Q4_K_S | 12.799 GB | small, greater quality loss |
| CognitiveFusion2-4x7B-BF16-Q4_K_M.gguf | Q4_K_M | 13.607 GB | medium, balanced quality - recommended |
| CognitiveFusion2-4x7B-BF16-Q5_0.gguf | Q5_0 | 15.485 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| CognitiveFusion2-4x7B-BF16-Q5_K_S.gguf | Q5_K_S | 15.485 GB | large, low quality loss - recommended |
| CognitiveFusion2-4x7B-BF16-Q5_K_M.gguf | Q5_K_M | 15.958 GB | large, very low quality loss - recommended |
| CognitiveFusion2-4x7B-BF16-Q6_K.gguf | Q6_K | 18.456 GB | very large, extremely low quality loss |
| CognitiveFusion2-4x7B-BF16-Q8_0.gguf | Q8_0 | 23.904 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/CognitiveFusion2-4x7B-BF16-GGUF --include "CognitiveFusion2-4x7B-BF16-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/CognitiveFusion2-4x7B-BF16-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'