metadata
license: llama3
tags:
- moe
- merge
- llama-3
- TensorBlock
- GGUF
language:
- en
- tr
pipeline_tag: text-generation
library_name: transformers
base_model: Eurdem/Defne_llama3_2x8B
Feedback and support: TensorBlock's Twitter/X, Telegram Group and Discord server
Eurdem/Defne_llama3_2x8B - GGUF
This repo contains GGUF format model files for Eurdem/Defne_llama3_2x8B.
The files were quantized using machines provided by TensorBlock, and they are compatible with llama.cpp as of commit b4011.
Prompt template
<|begin_of_text|><|start_header_id|>system<|end_header_id|>
{system_prompt}<|eot_id|><|start_header_id|>user<|end_header_id|>
{prompt}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
Model file specification
| Filename | Quant type | File Size | Description |
|---|---|---|---|
| Defne_llama3_2x8B-Q2_K.gguf | Q2_K | 4.862 GB | smallest, significant quality loss - not recommended for most purposes |
| Defne_llama3_2x8B-Q3_K_S.gguf | Q3_K_S | 5.670 GB | very small, high quality loss |
| Defne_llama3_2x8B-Q3_K_M.gguf | Q3_K_M | 6.246 GB | very small, high quality loss |
| Defne_llama3_2x8B-Q3_K_L.gguf | Q3_K_L | 6.733 GB | small, substantial quality loss |
| Defne_llama3_2x8B-Q4_0.gguf | Q4_0 | 7.295 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| Defne_llama3_2x8B-Q4_K_S.gguf | Q4_K_S | 7.352 GB | small, greater quality loss |
| Defne_llama3_2x8B-Q4_K_M.gguf | Q4_K_M | 7.762 GB | medium, balanced quality - recommended |
| Defne_llama3_2x8B-Q5_0.gguf | Q5_0 | 8.825 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| Defne_llama3_2x8B-Q5_K_S.gguf | Q5_K_S | 8.825 GB | large, low quality loss - recommended |
| Defne_llama3_2x8B-Q5_K_M.gguf | Q5_K_M | 9.066 GB | large, very low quality loss - recommended |
| Defne_llama3_2x8B-Q6_K.gguf | Q6_K | 10.451 GB | very large, extremely low quality loss |
| Defne_llama3_2x8B-Q8_0.gguf | Q8_0 | 13.533 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/Defne_llama3_2x8B-GGUF --include "Defne_llama3_2x8B-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/Defne_llama3_2x8B-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'