Hugging Face's logo

tensorblock
/
open-llama-3b-v2-elmv3-GGUF

GGUF
English
openllama
3b
TensorBlock
GGUF
Inference Endpoints
Model card Files Community
open-llama-3b-v2-elmv3-GGUF / README.md
morriszms's picture
morriszms
Upload folder using huggingface_hub
a5a93dc verified
preview code
|
raw
history blame contribute delete
4.94 kB
metadata
license: apache-2.0
datasets:
  - totally-not-an-llm/EverythingLM-data-V3
language:
  - en
tags:
  - openllama
  - 3b
  - TensorBlock
  - GGUF
base_model: aloobun/open-llama-3b-v2-elmv3
TensorBlock

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

aloobun/open-llama-3b-v2-elmv3 - GGUF

This repo contains GGUF format model files for aloobun/open-llama-3b-v2-elmv3.

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
open-llama-3b-v2-elmv3-Q2_K.gguf Q2_K 1.844 GB smallest, significant quality loss - not recommended for most purposes
open-llama-3b-v2-elmv3-Q3_K_S.gguf Q3_K_S 1.844 GB very small, high quality loss
open-llama-3b-v2-elmv3-Q3_K_M.gguf Q3_K_M 1.992 GB very small, high quality loss
open-llama-3b-v2-elmv3-Q3_K_L.gguf Q3_K_L 2.062 GB small, substantial quality loss
open-llama-3b-v2-elmv3-Q4_0.gguf Q4_0 1.844 GB legacy; small, very high quality loss - prefer using Q3_K_M
open-llama-3b-v2-elmv3-Q4_K_S.gguf Q4_K_S 2.238 GB small, greater quality loss
open-llama-3b-v2-elmv3-Q4_K_M.gguf Q4_K_M 2.403 GB medium, balanced quality - recommended
open-llama-3b-v2-elmv3-Q5_0.gguf Q5_0 2.231 GB legacy; medium, balanced quality - prefer using Q4_K_M
open-llama-3b-v2-elmv3-Q5_K_S.gguf Q5_K_S 2.424 GB large, low quality loss - recommended
open-llama-3b-v2-elmv3-Q5_K_M.gguf Q5_K_M 2.568 GB large, very low quality loss - recommended
open-llama-3b-v2-elmv3-Q6_K.gguf Q6_K 3.392 GB very large, extremely low quality loss
open-llama-3b-v2-elmv3-Q8_0.gguf Q8_0 3.392 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/open-llama-3b-v2-elmv3-GGUF --include "open-llama-3b-v2-elmv3-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/open-llama-3b-v2-elmv3-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'