metadata
license: other
tags:
- moe
- DPO
- RL-TUNED
- TensorBlock
- GGUF
base_model: yunconglong/Truthful_DPO_MOE_19B
Feedback and support: TensorBlock's Twitter/X, Telegram Group and Discord server
yunconglong/Truthful_DPO_MOE_19B - GGUF
This repo contains GGUF format model files for yunconglong/Truthful_DPO_MOE_19B.
The files were quantized using machines provided by TensorBlock, and they are compatible with llama.cpp as of commit b4242.
Prompt template
### System:
{system_prompt}
### User:
{prompt}
### Assistant:
Model file specification
| Filename | Quant type | File Size | Description |
|---|---|---|---|
| Truthful_DPO_MOE_19B-Q2_K.gguf | Q2_K | 7.066 GB | smallest, significant quality loss - not recommended for most purposes |
| Truthful_DPO_MOE_19B-Q3_K_S.gguf | Q3_K_S | 8.299 GB | very small, high quality loss |
| Truthful_DPO_MOE_19B-Q3_K_M.gguf | Q3_K_M | 9.227 GB | very small, high quality loss |
| Truthful_DPO_MOE_19B-Q3_K_L.gguf | Q3_K_L | 10.012 GB | small, substantial quality loss |
| Truthful_DPO_MOE_19B-Q4_0.gguf | Q4_0 | 10.830 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| Truthful_DPO_MOE_19B-Q4_K_S.gguf | Q4_K_S | 10.920 GB | small, greater quality loss |
| Truthful_DPO_MOE_19B-Q4_K_M.gguf | Q4_K_M | 11.583 GB | medium, balanced quality - recommended |
| Truthful_DPO_MOE_19B-Q5_0.gguf | Q5_0 | 13.212 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| Truthful_DPO_MOE_19B-Q5_K_S.gguf | Q5_K_S | 13.212 GB | large, low quality loss - recommended |
| Truthful_DPO_MOE_19B-Q5_K_M.gguf | Q5_K_M | 13.600 GB | large, very low quality loss - recommended |
| Truthful_DPO_MOE_19B-Q6_K.gguf | Q6_K | 15.743 GB | very large, extremely low quality loss |
| Truthful_DPO_MOE_19B-Q8_0.gguf | Q8_0 | 20.390 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/Truthful_DPO_MOE_19B-GGUF --include "Truthful_DPO_MOE_19B-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/Truthful_DPO_MOE_19B-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'