metadata
license: other
license_name: yi-license
license_link: https://huggingface.co/01-ai/Yi-34B/blob/main/LICENSE
language:
- en
library_name: transformers
pipeline_tag: text-generation
tags:
- text-generation-inference
- merge
- TensorBlock
- GGUF
base_model: brucethemoose/CapyTessBorosYi-34B-200K-DARE-Ties
Feedback and support: TensorBlock's Twitter/X, Telegram Group and Discord server
brucethemoose/CapyTessBorosYi-34B-200K-DARE-Ties - GGUF
This repo contains GGUF format model files for brucethemoose/CapyTessBorosYi-34B-200K-DARE-Ties.
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 |
|---|---|---|---|
| CapyTessBorosYi-34B-200K-DARE-Ties-Q2_K.gguf | Q2_K | 12.825 GB | smallest, significant quality loss - not recommended for most purposes |
| CapyTessBorosYi-34B-200K-DARE-Ties-Q3_K_S.gguf | Q3_K_S | 14.960 GB | very small, high quality loss |
| CapyTessBorosYi-34B-200K-DARE-Ties-Q3_K_M.gguf | Q3_K_M | 16.655 GB | very small, high quality loss |
| CapyTessBorosYi-34B-200K-DARE-Ties-Q3_K_L.gguf | Q3_K_L | 18.139 GB | small, substantial quality loss |
| CapyTessBorosYi-34B-200K-DARE-Ties-Q4_0.gguf | Q4_0 | 19.467 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| CapyTessBorosYi-34B-200K-DARE-Ties-Q4_K_S.gguf | Q4_K_S | 19.599 GB | small, greater quality loss |
| CapyTessBorosYi-34B-200K-DARE-Ties-Q4_K_M.gguf | Q4_K_M | 20.659 GB | medium, balanced quality - recommended |
| CapyTessBorosYi-34B-200K-DARE-Ties-Q5_0.gguf | Q5_0 | 23.708 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| CapyTessBorosYi-34B-200K-DARE-Ties-Q5_K_S.gguf | Q5_K_S | 23.708 GB | large, low quality loss - recommended |
| CapyTessBorosYi-34B-200K-DARE-Ties-Q5_K_M.gguf | Q5_K_M | 24.322 GB | large, very low quality loss - recommended |
| CapyTessBorosYi-34B-200K-DARE-Ties-Q6_K.gguf | Q6_K | 28.214 GB | very large, extremely low quality loss |
| CapyTessBorosYi-34B-200K-DARE-Ties-Q8_0.gguf | Q8_0 | 36.542 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/CapyTessBorosYi-34B-200K-DARE-Ties-GGUF --include "CapyTessBorosYi-34B-200K-DARE-Ties-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/CapyTessBorosYi-34B-200K-DARE-Ties-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'