Hugging Face's logo

tensorblock
/
h2o-danube3-500m-base-GGUF

Text Generation
Transformers
GGUF
English
gpt
llm
large language model
h2o-llmstudio
TensorBlock
GGUF
Inference Endpoints
Model card Files Community
h2o-danube3-500m-base-GGUF / README.md
morriszms's picture
morriszms
Update README.md
823163d verified
preview code
|
raw
history blame contribute delete
5.03 kB
metadata
language:
  - en
library_name: transformers
license: apache-2.0
tags:
  - gpt
  - llm
  - large language model
  - h2o-llmstudio
  - TensorBlock
  - GGUF
thumbnail: >-
  https://h2o.ai/etc.clientlibs/h2o/clientlibs/clientlib-site/resources/images/favicon.ico
pipeline_tag: text-generation
base_model: h2oai/h2o-danube3-500m-base
TensorBlock

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

h2oai/h2o-danube3-500m-base - GGUF

This repo contains GGUF format model files for h2oai/h2o-danube3-500m-base.

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
h2o-danube3-500m-base-Q2_K.gguf Q2_K 0.195 GB smallest, significant quality loss - not recommended for most purposes
h2o-danube3-500m-base-Q3_K_S.gguf Q3_K_S 0.224 GB very small, high quality loss
h2o-danube3-500m-base-Q3_K_M.gguf Q3_K_M 0.245 GB very small, high quality loss
h2o-danube3-500m-base-Q3_K_L.gguf Q3_K_L 0.262 GB small, substantial quality loss
h2o-danube3-500m-base-Q4_0.gguf Q4_0 0.282 GB legacy; small, very high quality loss - prefer using Q3_K_M
h2o-danube3-500m-base-Q4_K_S.gguf Q4_K_S 0.284 GB small, greater quality loss
h2o-danube3-500m-base-Q4_K_M.gguf Q4_K_M 0.296 GB medium, balanced quality - recommended
h2o-danube3-500m-base-Q5_0.gguf Q5_0 0.336 GB legacy; medium, balanced quality - prefer using Q4_K_M
h2o-danube3-500m-base-Q5_K_S.gguf Q5_K_S 0.336 GB large, low quality loss - recommended
h2o-danube3-500m-base-Q5_K_M.gguf Q5_K_M 0.343 GB large, very low quality loss - recommended
h2o-danube3-500m-base-Q6_K.gguf Q6_K 0.393 GB very large, extremely low quality loss
h2o-danube3-500m-base-Q8_0.gguf Q8_0 0.509 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/h2o-danube3-500m-base-GGUF --include "h2o-danube3-500m-base-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/h2o-danube3-500m-base-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'