TensorBlock

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

tifa-benchmark/llama2_tifa_question_generation - GGUF

This repo contains GGUF format model files for tifa-benchmark/llama2_tifa_question_generation.

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

Prompt template


Model file specification

Filename Quant type File Size Description
llama2_tifa_question_generation-Q2_K.gguf Q2_K 2.359 GB smallest, significant quality loss - not recommended for most purposes
llama2_tifa_question_generation-Q3_K_S.gguf Q3_K_S 2.746 GB very small, high quality loss
llama2_tifa_question_generation-Q3_K_M.gguf Q3_K_M 3.072 GB very small, high quality loss
llama2_tifa_question_generation-Q3_K_L.gguf Q3_K_L 3.350 GB small, substantial quality loss
llama2_tifa_question_generation-Q4_0.gguf Q4_0 3.563 GB legacy; small, very high quality loss - prefer using Q3_K_M
llama2_tifa_question_generation-Q4_K_S.gguf Q4_K_S 3.592 GB small, greater quality loss
llama2_tifa_question_generation-Q4_K_M.gguf Q4_K_M 3.801 GB medium, balanced quality - recommended
llama2_tifa_question_generation-Q5_0.gguf Q5_0 4.332 GB legacy; medium, balanced quality - prefer using Q4_K_M
llama2_tifa_question_generation-Q5_K_S.gguf Q5_K_S 4.332 GB large, low quality loss - recommended
llama2_tifa_question_generation-Q5_K_M.gguf Q5_K_M 4.455 GB large, very low quality loss - recommended
llama2_tifa_question_generation-Q6_K.gguf Q6_K 5.149 GB very large, extremely low quality loss
llama2_tifa_question_generation-Q8_0.gguf Q8_0 6.669 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/llama2_tifa_question_generation-GGUF --include "llama2_tifa_question_generation-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/llama2_tifa_question_generation-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
Downloads last month
99
GGUF
Model size
6.74B 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/llama2_tifa_question_generation-GGUF

Quantized
(1)
this model