Hugging Face's logo

tensorblock
/
llama2.c-stories110M-pruned50-GGUF

GGUF
nm-vllm
sparse
TensorBlock
GGUF
Inference Endpoints
Model card Files Community
llama2.c-stories110M-pruned50-GGUF / README.md
morriszms's picture
morriszms
Upload folder using huggingface_hub
5bb6eca verified
preview code
|
raw
history blame contribute delete
5.23 kB
metadata
base_model: neuralmagic/llama2.c-stories110M-pruned50
inference: true
model_type: llama
quantized_by: mgoin
tags:
  - nm-vllm
  - sparse
  - TensorBlock
  - GGUF
TensorBlock

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

neuralmagic/llama2.c-stories110M-pruned50 - GGUF

This repo contains GGUF format model files for neuralmagic/llama2.c-stories110M-pruned50.

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

Prompt template

Model file specification

Filename Quant type File Size Description
llama2.c-stories110M-pruned50-Q2_K.gguf Q2_K 0.060 GB smallest, significant quality loss - not recommended for most purposes
llama2.c-stories110M-pruned50-Q3_K_S.gguf Q3_K_S 0.068 GB very small, high quality loss
llama2.c-stories110M-pruned50-Q3_K_M.gguf Q3_K_M 0.073 GB very small, high quality loss
llama2.c-stories110M-pruned50-Q3_K_L.gguf Q3_K_L 0.077 GB small, substantial quality loss
llama2.c-stories110M-pruned50-Q4_0.gguf Q4_0 0.083 GB legacy; small, very high quality loss - prefer using Q3_K_M
llama2.c-stories110M-pruned50-Q4_K_S.gguf Q4_K_S 0.083 GB small, greater quality loss
llama2.c-stories110M-pruned50-Q4_K_M.gguf Q4_K_M 0.086 GB medium, balanced quality - recommended
llama2.c-stories110M-pruned50-Q5_0.gguf Q5_0 0.096 GB legacy; medium, balanced quality - prefer using Q4_K_M
llama2.c-stories110M-pruned50-Q5_K_S.gguf Q5_K_S 0.096 GB large, low quality loss - recommended
llama2.c-stories110M-pruned50-Q5_K_M.gguf Q5_K_M 0.098 GB large, very low quality loss - recommended
llama2.c-stories110M-pruned50-Q6_K.gguf Q6_K 0.111 GB very large, extremely low quality loss
llama2.c-stories110M-pruned50-Q8_0.gguf Q8_0 0.143 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.c-stories110M-pruned50-GGUF --include "llama2.c-stories110M-pruned50-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.c-stories110M-pruned50-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'