Hugging Face's logo

tensorblock
/
SummLlama3.2-3B-GGUF

Summarization
Transformers
GGUF
TensorBlock
GGUF
Inference Endpoints
conversational
Model card Files Community
SummLlama3.2-3B-GGUF / README.md
morriszms's picture
morriszms
Upload folder using huggingface_hub
0184e65 verified
preview code
|
raw
history blame contribute delete
4.84 kB
metadata
library_name: transformers
base_model: DISLab/SummLlama3.2-3B
pipeline_tag: summarization
tags:
  - TensorBlock
  - GGUF
TensorBlock

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

DISLab/SummLlama3.2-3B - GGUF

This repo contains GGUF format model files for DISLab/SummLlama3.2-3B.

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|>

Cutting Knowledge Date: December 2023
Today Date: 20 Nov 2024

{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
SummLlama3.2-3B-Q2_K.gguf Q2_K 1.364 GB smallest, significant quality loss - not recommended for most purposes
SummLlama3.2-3B-Q3_K_S.gguf Q3_K_S 1.543 GB very small, high quality loss
SummLlama3.2-3B-Q3_K_M.gguf Q3_K_M 1.687 GB very small, high quality loss
SummLlama3.2-3B-Q3_K_L.gguf Q3_K_L 1.815 GB small, substantial quality loss
SummLlama3.2-3B-Q4_0.gguf Q4_0 1.917 GB legacy; small, very high quality loss - prefer using Q3_K_M
SummLlama3.2-3B-Q4_K_S.gguf Q4_K_S 1.928 GB small, greater quality loss
SummLlama3.2-3B-Q4_K_M.gguf Q4_K_M 2.019 GB medium, balanced quality - recommended
SummLlama3.2-3B-Q5_0.gguf Q5_0 2.270 GB legacy; medium, balanced quality - prefer using Q4_K_M
SummLlama3.2-3B-Q5_K_S.gguf Q5_K_S 2.270 GB large, low quality loss - recommended
SummLlama3.2-3B-Q5_K_M.gguf Q5_K_M 2.322 GB large, very low quality loss - recommended
SummLlama3.2-3B-Q6_K.gguf Q6_K 2.644 GB very large, extremely low quality loss
SummLlama3.2-3B-Q8_0.gguf Q8_0 3.422 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/SummLlama3.2-3B-GGUF --include "SummLlama3.2-3B-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/SummLlama3.2-3B-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'