metadata
language:
- de
- bg
- cs
- da
- el
- en
- es
- et
- fi
- fr
- ga
- hr
- hu
- it
- lt
- lv
- mt
- nl
- pl
- pt
- ro
- sl
- sv
- sk
metrics:
- accuracy
- bleu
pipeline_tag: text-generation
library_name: transformers
base_model: openGPT-X/Teuken-7B-instruct-research-v0.4
license: other
tags:
- TensorBlock
- GGUF
Feedback and support: TensorBlock's Twitter/X, Telegram Group and Discord server
openGPT-X/Teuken-7B-instruct-research-v0.4 - GGUF
This repo contains GGUF format model files for openGPT-X/Teuken-7B-instruct-research-v0.4.
The files were quantized using machines provided by TensorBlock, and they are compatible with llama.cpp as of commit b4242.
Prompt template
System: A chat between a human and an artificial intelligence assistant.The assistant gives helpful and polite answers to the human's questions.
User: {prompt}
Assistant:
Model file specification
| Filename | Quant type | File Size | Description |
|---|---|---|---|
| Teuken-7B-instruct-research-v0.4-Q2_K.gguf | Q2_K | 3.433 GB | smallest, significant quality loss - not recommended for most purposes |
| Teuken-7B-instruct-research-v0.4-Q3_K_S.gguf | Q3_K_S | 3.845 GB | very small, high quality loss |
| Teuken-7B-instruct-research-v0.4-Q3_K_M.gguf | Q3_K_M | 4.148 GB | very small, high quality loss |
| Teuken-7B-instruct-research-v0.4-Q3_K_L.gguf | Q3_K_L | 4.322 GB | small, substantial quality loss |
| Teuken-7B-instruct-research-v0.4-Q4_0.gguf | Q4_0 | 4.464 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| Teuken-7B-instruct-research-v0.4-Q4_K_S.gguf | Q4_K_S | 4.699 GB | small, greater quality loss |
| Teuken-7B-instruct-research-v0.4-Q4_K_M.gguf | Q4_K_M | 5.019 GB | medium, balanced quality - recommended |
| Teuken-7B-instruct-research-v0.4-Q5_0.gguf | Q5_0 | 5.267 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| Teuken-7B-instruct-research-v0.4-Q5_K_S.gguf | Q5_K_S | 5.377 GB | large, low quality loss - recommended |
| Teuken-7B-instruct-research-v0.4-Q5_K_M.gguf | Q5_K_M | 5.655 GB | large, very low quality loss - recommended |
| Teuken-7B-instruct-research-v0.4-Q6_K.gguf | Q6_K | 6.547 GB | very large, extremely low quality loss |
| Teuken-7B-instruct-research-v0.4-Q8_0.gguf | Q8_0 | 7.926 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/Teuken-7B-instruct-research-v0.4-GGUF --include "Teuken-7B-instruct-research-v0.4-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/Teuken-7B-instruct-research-v0.4-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'