metadata
license: apache-2.0
datasets:
- lmsys/lmsys-chat-1m
- PKU-Alignment/BeaverTails
- allenai/WildChat-1M
language:
- en
metrics:
- f1
- accuracy
tags:
- ai-safety
- safetyguard
- safety
- benchmark
- internlm
- evaluation
- judge
- TensorBlock
- GGUF
pipeline_tag: text-generation
base_model: OpenSafetyLab/MD-Judge-v0_2-internlm2_7b
Feedback and support: TensorBlock's Twitter/X, Telegram Group and Discord server
OpenSafetyLab/MD-Judge-v0_2-internlm2_7b - GGUF
This repo contains GGUF format model files for OpenSafetyLab/MD-Judge-v0_2-internlm2_7b.
The files were quantized using machines provided by TensorBlock, and they are compatible with llama.cpp as of commit b4011.
Prompt template
{system_prompt}<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant
Model file specification
| Filename | Quant type | File Size | Description |
|---|---|---|---|
| MD-Judge-v0_2-internlm2_7b-Q2_K.gguf | Q2_K | 3.005 GB | smallest, significant quality loss - not recommended for most purposes |
| MD-Judge-v0_2-internlm2_7b-Q3_K_S.gguf | Q3_K_S | 3.476 GB | very small, high quality loss |
| MD-Judge-v0_2-internlm2_7b-Q3_K_M.gguf | Q3_K_M | 3.830 GB | very small, high quality loss |
| MD-Judge-v0_2-internlm2_7b-Q3_K_L.gguf | Q3_K_L | 4.133 GB | small, substantial quality loss |
| MD-Judge-v0_2-internlm2_7b-Q4_0.gguf | Q4_0 | 4.453 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| MD-Judge-v0_2-internlm2_7b-Q4_K_S.gguf | Q4_K_S | 4.485 GB | small, greater quality loss |
| MD-Judge-v0_2-internlm2_7b-Q4_K_M.gguf | Q4_K_M | 4.713 GB | medium, balanced quality - recommended |
| MD-Judge-v0_2-internlm2_7b-Q5_0.gguf | Q5_0 | 5.373 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| MD-Judge-v0_2-internlm2_7b-Q5_K_S.gguf | Q5_K_S | 5.373 GB | large, low quality loss - recommended |
| MD-Judge-v0_2-internlm2_7b-Q5_K_M.gguf | Q5_K_M | 5.507 GB | large, very low quality loss - recommended |
| MD-Judge-v0_2-internlm2_7b-Q6_K.gguf | Q6_K | 6.350 GB | very large, extremely low quality loss |
| MD-Judge-v0_2-internlm2_7b-Q8_0.gguf | Q8_0 | 8.224 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/MD-Judge-v0_2-internlm2_7b-GGUF --include "MD-Judge-v0_2-internlm2_7b-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/MD-Judge-v0_2-internlm2_7b-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'