metadata
license: gemma
base_model: tanliboy/zephyr-gemma-2-9b-sft
tags:
- alignment-handbook
- trl
- sft
- generated_from_trainer
- TensorBlock
- GGUF
datasets:
- HuggingFaceH4/ultrachat_200k
model-index:
- name: zephyr-gemma-2-9b-sft
results: []
Feedback and support: TensorBlock's Twitter/X, Telegram Group and Discord server
tanliboy/zephyr-gemma-2-9b-sft - GGUF
This repo contains GGUF format model files for tanliboy/zephyr-gemma-2-9b-sft.
The files were quantized using machines provided by TensorBlock, and they are compatible with llama.cpp as of commit b4011.
Prompt template
<bos><start_of_turn>system
{system_prompt}<end_of_turn>
<start_of_turn>user
{prompt}<end_of_turn>
<start_of_turn>model
Model file specification
| Filename | Quant type | File Size | Description |
|---|---|---|---|
| zephyr-gemma-2-9b-sft-Q2_K.gguf | Q2_K | 3.805 GB | smallest, significant quality loss - not recommended for most purposes |
| zephyr-gemma-2-9b-sft-Q3_K_S.gguf | Q3_K_S | 4.338 GB | very small, high quality loss |
| zephyr-gemma-2-9b-sft-Q3_K_M.gguf | Q3_K_M | 4.762 GB | very small, high quality loss |
| zephyr-gemma-2-9b-sft-Q3_K_L.gguf | Q3_K_L | 5.132 GB | small, substantial quality loss |
| zephyr-gemma-2-9b-sft-Q4_0.gguf | Q4_0 | 5.443 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| zephyr-gemma-2-9b-sft-Q4_K_S.gguf | Q4_K_S | 5.479 GB | small, greater quality loss |
| zephyr-gemma-2-9b-sft-Q4_K_M.gguf | Q4_K_M | 5.761 GB | medium, balanced quality - recommended |
| zephyr-gemma-2-9b-sft-Q5_0.gguf | Q5_0 | 6.484 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| zephyr-gemma-2-9b-sft-Q5_K_S.gguf | Q5_K_S | 6.484 GB | large, low quality loss - recommended |
| zephyr-gemma-2-9b-sft-Q5_K_M.gguf | Q5_K_M | 6.647 GB | large, very low quality loss - recommended |
| zephyr-gemma-2-9b-sft-Q6_K.gguf | Q6_K | 7.589 GB | very large, extremely low quality loss |
| zephyr-gemma-2-9b-sft-Q8_0.gguf | Q8_0 | 9.827 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/zephyr-gemma-2-9b-sft-GGUF --include "zephyr-gemma-2-9b-sft-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/zephyr-gemma-2-9b-sft-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'