TensorBlock

Feedback and support: TensorBlock's Twitter/X, Telegram Group and Discord server

RoyJoy/llama_dec27 - GGUF

This repo contains GGUF format model files for RoyJoy/llama_dec27.

The files were quantized using machines provided by TensorBlock, and they are compatible with llama.cpp as of commit b4242.

Prompt template

<|im_start|>system
{system_prompt}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant

Model file specification

Filename Quant type File Size Description
llama_dec27-Q2_K.gguf Q2_K 3.778 GB smallest, significant quality loss - not recommended for most purposes
llama_dec27-Q3_K_S.gguf Q3_K_S 4.335 GB very small, high quality loss
llama_dec27-Q3_K_M.gguf Q3_K_M 4.712 GB very small, high quality loss
llama_dec27-Q3_K_L.gguf Q3_K_L 4.929 GB small, substantial quality loss
llama_dec27-Q4_0.gguf Q4_0 5.169 GB legacy; small, very high quality loss - prefer using Q3_K_M
llama_dec27-Q4_K_S.gguf Q4_K_S 5.473 GB small, greater quality loss
llama_dec27-Q4_K_M.gguf Q4_K_M 5.875 GB medium, balanced quality - recommended
llama_dec27-Q5_0.gguf Q5_0 6.242 GB legacy; medium, balanced quality - prefer using Q4_K_M
llama_dec27-Q5_K_S.gguf Q5_K_S 6.386 GB large, low quality loss - recommended
llama_dec27-Q5_K_M.gguf Q5_K_M 6.729 GB large, very low quality loss - recommended
llama_dec27-Q6_K.gguf Q6_K 7.939 GB very large, extremely low quality loss
llama_dec27-Q8_0.gguf Q8_0 9.559 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/llama_dec27-GGUF --include "llama_dec27-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/llama_dec27-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
Downloads last month
252
GGUF
Model size
8.99B params
Architecture
llama

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

Inference API
Unable to determine this model’s pipeline type. Check the docs .

Model tree for tensorblock/llama_dec27-GGUF

Base model

RoyJoy/llama_dec27
Quantized
(1)
this model