TensorBlock

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

elvinmarkmv/tinyllama-15M-alpaca-finetuned - GGUF

This repo contains GGUF format model files for elvinmarkmv/tinyllama-15M-alpaca-finetuned.

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
tinyllama-15M-alpaca-finetuned-Q2_K.gguf Q2_K 0.014 GB smallest, significant quality loss - not recommended for most purposes
tinyllama-15M-alpaca-finetuned-Q3_K_S.gguf Q3_K_S 0.014 GB very small, high quality loss
tinyllama-15M-alpaca-finetuned-Q3_K_M.gguf Q3_K_M 0.014 GB very small, high quality loss
tinyllama-15M-alpaca-finetuned-Q3_K_L.gguf Q3_K_L 0.014 GB small, substantial quality loss
tinyllama-15M-alpaca-finetuned-Q4_0.gguf Q4_0 0.014 GB legacy; small, very high quality loss - prefer using Q3_K_M
tinyllama-15M-alpaca-finetuned-Q4_K_S.gguf Q4_K_S 0.014 GB small, greater quality loss
tinyllama-15M-alpaca-finetuned-Q4_K_M.gguf Q4_K_M 0.015 GB medium, balanced quality - recommended
tinyllama-15M-alpaca-finetuned-Q5_0.gguf Q5_0 0.015 GB legacy; medium, balanced quality - prefer using Q4_K_M
tinyllama-15M-alpaca-finetuned-Q5_K_S.gguf Q5_K_S 0.015 GB large, low quality loss - recommended
tinyllama-15M-alpaca-finetuned-Q5_K_M.gguf Q5_K_M 0.015 GB large, very low quality loss - recommended
tinyllama-15M-alpaca-finetuned-Q6_K.gguf Q6_K 0.017 GB very large, extremely low quality loss
tinyllama-15M-alpaca-finetuned-Q8_0.gguf Q8_0 0.017 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/tinyllama-15M-alpaca-finetuned-GGUF --include "tinyllama-15M-alpaca-finetuned-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/tinyllama-15M-alpaca-finetuned-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
Downloads last month
74
GGUF
Model size
15.2M params
Architecture
llama

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

Inference Providers NEW
This model is not currently available via any of the supported Inference Providers.

Model tree for tensorblock/tinyllama-15M-alpaca-finetuned-GGUF

Quantized
(3)
this model

Dataset used to train tensorblock/tinyllama-15M-alpaca-finetuned-GGUF