metadata
language:
- zh
- en
- fr
- de
- ja
- ko
- it
- ru
- fi
pipeline_tag: text-generation
inference: false
library_name: transformers
license: other
license_name: deepseek
license_link: >-
https://github.com/deepseek-ai/DeepSeek-LLM/blob/548a39bdd03986297ea4e233a8b7676edd6bec3e/LICENSE-MODEL
base_model: OpenBuddy/openbuddy-deepseek-10b-v17.1-4k
tags:
- TensorBlock
- GGUF
Feedback and support: TensorBlock's Twitter/X, Telegram Group and Discord server
OpenBuddy/openbuddy-deepseek-10b-v17.1-4k - GGUF
This repo contains GGUF format model files for OpenBuddy/openbuddy-deepseek-10b-v17.1-4k.
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 |
|---|---|---|---|
| openbuddy-deepseek-10b-v17.1-4k-Q2_K.gguf | Q2_K | 4.058 GB | smallest, significant quality loss - not recommended for most purposes |
| openbuddy-deepseek-10b-v17.1-4k-Q3_K_S.gguf | Q3_K_S | 4.704 GB | very small, high quality loss |
| openbuddy-deepseek-10b-v17.1-4k-Q3_K_M.gguf | Q3_K_M | 5.226 GB | very small, high quality loss |
| openbuddy-deepseek-10b-v17.1-4k-Q3_K_L.gguf | Q3_K_L | 5.677 GB | small, substantial quality loss |
| openbuddy-deepseek-10b-v17.1-4k-Q4_0.gguf | Q4_0 | 6.050 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| openbuddy-deepseek-10b-v17.1-4k-Q4_K_S.gguf | Q4_K_S | 6.092 GB | small, greater quality loss |
| openbuddy-deepseek-10b-v17.1-4k-Q4_K_M.gguf | Q4_K_M | 6.432 GB | medium, balanced quality - recommended |
| openbuddy-deepseek-10b-v17.1-4k-Q5_0.gguf | Q5_0 | 7.316 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| openbuddy-deepseek-10b-v17.1-4k-Q5_K_S.gguf | Q5_K_S | 7.316 GB | large, low quality loss - recommended |
| openbuddy-deepseek-10b-v17.1-4k-Q5_K_M.gguf | Q5_K_M | 7.514 GB | large, very low quality loss - recommended |
| openbuddy-deepseek-10b-v17.1-4k-Q6_K.gguf | Q6_K | 8.662 GB | very large, extremely low quality loss |
| openbuddy-deepseek-10b-v17.1-4k-Q8_0.gguf | Q8_0 | 11.218 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/openbuddy-deepseek-10b-v17.1-4k-GGUF --include "openbuddy-deepseek-10b-v17.1-4k-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/openbuddy-deepseek-10b-v17.1-4k-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'