metadata
license: mit
base_model: perplexity-ai/r1-1776-distill-llama-70b
tags:
- TensorBlock
- GGUF
Feedback and support: TensorBlock's Twitter/X, Telegram Group and Discord server
perplexity-ai/r1-1776-distill-llama-70b - GGUF
This repo contains GGUF format model files for perplexity-ai/r1-1776-distill-llama-70b.
The files were quantized using machines provided by TensorBlock, and they are compatible with llama.cpp as of commit b4658.
Prompt template
<｜begin▁of▁sentence｜>{system_prompt}<｜User｜>{prompt}<｜Assistant｜>
Model file specification
| Filename | Quant type | File Size | Description |
|---|---|---|---|
| r1-1776-distill-llama-70b-Q2_K.gguf | Q2_K | 26.375 GB | smallest, significant quality loss - not recommended for most purposes |
| r1-1776-distill-llama-70b-Q3_K_S.gguf | Q3_K_S | 30.912 GB | very small, high quality loss |
| r1-1776-distill-llama-70b-Q3_K_M.gguf | Q3_K_M | 34.267 GB | very small, high quality loss |
| r1-1776-distill-llama-70b-Q3_K_L.gguf | Q3_K_L | 37.141 GB | small, substantial quality loss |
| r1-1776-distill-llama-70b-Q4_0.gguf | Q4_0 | 39.970 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| r1-1776-distill-llama-70b-Q4_K_S.gguf | Q4_K_S | 40.347 GB | small, greater quality loss |
| r1-1776-distill-llama-70b-Q4_K_M.gguf | Q4_K_M | 42.520 GB | medium, balanced quality - recommended |
| r1-1776-distill-llama-70b-Q5_0.gguf | Q5_0 | 48.657 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| r1-1776-distill-llama-70b-Q5_K_S.gguf | Q5_K_S | 48.657 GB | large, low quality loss - recommended |
| r1-1776-distill-llama-70b-Q5_K_M.gguf | Q5_K_M | 49.950 GB | large, very low quality loss - recommended |
| r1-1776-distill-llama-70b-Q6_K | Q6_K | 57.888 GB | very large, extremely low quality loss |
| r1-1776-distill-llama-70b-Q8_0 | Q8_0 | 74.975 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/r1-1776-distill-llama-70b-GGUF --include "r1-1776-distill-llama-70b-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/r1-1776-distill-llama-70b-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'