Hugging Face's logo

tensorblock
/
h2o-danube-1.8b-sft-GGUF

Text Generation
Transformers
GGUF
English
gpt
llm
large language model
h2o-llmstudio
TensorBlock
GGUF
Inference Endpoints
conversational
Model card Files Community
h2o-danube-1.8b-sft-GGUF / README.md
morriszms's picture
morriszms
Upload folder using huggingface_hub
2f04cb0 verified
preview code
|
raw
history blame contribute delete
5.19 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
datasets:
  - Open-Orca/OpenOrca
  - OpenAssistant/oasst2
  - HuggingFaceH4/ultrachat_200k
  - meta-math/MetaMathQA
widget:
  - messages:
      - role: user
        content: Why is drinking water so healthy?
pipeline_tag: text-generation
base_model: h2oai/h2o-danube-1.8b-sft
TensorBlock

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

h2oai/h2o-danube-1.8b-sft - GGUF

This repo contains GGUF format model files for h2oai/h2o-danube-1.8b-sft.

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

Prompt template 

<|system|>{system_prompt}</s><|prompt|>{prompt}</s><|answer|>

Model file specification

Filename Quant type File Size Description
h2o-danube-1.8b-sft-Q2_K.gguf Q2_K 0.711 GB smallest, significant quality loss - not recommended for most purposes
h2o-danube-1.8b-sft-Q3_K_S.gguf Q3_K_S 0.820 GB very small, high quality loss
h2o-danube-1.8b-sft-Q3_K_M.gguf Q3_K_M 0.905 GB very small, high quality loss
h2o-danube-1.8b-sft-Q3_K_L.gguf Q3_K_L 0.980 GB small, substantial quality loss
h2o-danube-1.8b-sft-Q4_0.gguf Q4_0 1.052 GB legacy; small, very high quality loss - prefer using Q3_K_M
h2o-danube-1.8b-sft-Q4_K_S.gguf Q4_K_S 1.060 GB small, greater quality loss
h2o-danube-1.8b-sft-Q4_K_M.gguf Q4_K_M 1.112 GB medium, balanced quality - recommended
h2o-danube-1.8b-sft-Q5_0.gguf Q5_0 1.271 GB legacy; medium, balanced quality - prefer using Q4_K_M
h2o-danube-1.8b-sft-Q5_K_S.gguf Q5_K_S 1.271 GB large, low quality loss - recommended
h2o-danube-1.8b-sft-Q5_K_M.gguf Q5_K_M 1.302 GB large, very low quality loss - recommended
h2o-danube-1.8b-sft-Q6_K.gguf Q6_K 1.503 GB very large, extremely low quality loss
h2o-danube-1.8b-sft-Q8_0.gguf Q8_0 1.947 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-danube-1.8b-sft-GGUF --include "h2o-danube-1.8b-sft-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-danube-1.8b-sft-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'