TensorBlock

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

meta-llama/Llama-2-13b-chat-hf - GGUF

This repo contains GGUF format model files for meta-llama/Llama-2-13b-chat-hf.

The files were quantized using machines provided by TensorBlock, and they are compatible with llama.cpp as of commit b4011.

Prompt template

<s>[INST] <<SYS>>
{system_prompt}
<</SYS>>

{prompt} [/INST]

Model file specification

Filename Quant type File Size Description
Llama-2-13b-chat-hf-Q2_K.gguf Q2_K 4.854 GB smallest, significant quality loss - not recommended for most purposes
Llama-2-13b-chat-hf-Q3_K_S.gguf Q3_K_S 5.659 GB very small, high quality loss
Llama-2-13b-chat-hf-Q3_K_M.gguf Q3_K_M 6.338 GB very small, high quality loss
Llama-2-13b-chat-hf-Q3_K_L.gguf Q3_K_L 6.930 GB small, substantial quality loss
Llama-2-13b-chat-hf-Q4_0.gguf Q4_0 7.366 GB legacy; small, very high quality loss - prefer using Q3_K_M
Llama-2-13b-chat-hf-Q4_K_S.gguf Q4_K_S 7.423 GB small, greater quality loss
Llama-2-13b-chat-hf-Q4_K_M.gguf Q4_K_M 7.866 GB medium, balanced quality - recommended
Llama-2-13b-chat-hf-Q5_0.gguf Q5_0 8.972 GB legacy; medium, balanced quality - prefer using Q4_K_M
Llama-2-13b-chat-hf-Q5_K_S.gguf Q5_K_S 8.972 GB large, low quality loss - recommended
Llama-2-13b-chat-hf-Q5_K_M.gguf Q5_K_M 9.230 GB large, very low quality loss - recommended
Llama-2-13b-chat-hf-Q6_K.gguf Q6_K 10.679 GB very large, extremely low quality loss
Llama-2-13b-chat-hf-Q8_0.gguf Q8_0 13.831 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-2-13b-chat-hf-GGUF --include "Llama-2-13b-chat-hf-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-2-13b-chat-hf-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
Downloads last month
46
GGUF
Model size
13B params
Architecture
llama

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

Inference Examples
Unable to determine this model's library. Check the docs .

Model tree for tensorblock/Llama-2-13b-chat-hf-GGUF

Quantized
(17)
this model