Hugging Face's logo

tensorblock
/
HelpingAI-Lite-2x1B-GGUF

Transformers
GGUF
English
HelpingAI
coder
lite
Fine-tuned
Mixture of Experts
nlp
TensorBlock
GGUF
Inference Endpoints
conversational
Model card Files Community
HelpingAI-Lite-2x1B-GGUF / README.md
morriszms's picture
morriszms
Upload folder using huggingface_hub
6511244 verified
preview code
|
raw
history blame contribute delete
5 kB
metadata
language:
  - en
metrics:
  - accuracy
library_name: transformers
base_model: OEvortex/HelpingAI-Lite-2x1B
tags:
  - HelpingAI
  - coder
  - lite
  - Fine-tuned
  - moe
  - nlp
  - TensorBlock
  - GGUF
license: other
license_name: hsul
license_link: https://huggingface.co/OEvortex/vortex-3b/raw/main/LICENSE.md
TensorBlock

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

OEvortex/HelpingAI-Lite-2x1B - GGUF

This repo contains GGUF format model files for OEvortex/HelpingAI-Lite-2x1B.

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>
<|user|>
{prompt}</s>
<|assistant|>

Model file specification

Filename Quant type File Size Description
HelpingAI-Lite-2x1B-Q2_K.gguf Q2_K 0.708 GB smallest, significant quality loss - not recommended for most purposes
HelpingAI-Lite-2x1B-Q3_K_S.gguf Q3_K_S 0.827 GB very small, high quality loss
HelpingAI-Lite-2x1B-Q3_K_M.gguf Q3_K_M 0.911 GB very small, high quality loss
HelpingAI-Lite-2x1B-Q3_K_L.gguf Q3_K_L 0.984 GB small, substantial quality loss
HelpingAI-Lite-2x1B-Q4_0.gguf Q4_0 1.065 GB legacy; small, very high quality loss - prefer using Q3_K_M
HelpingAI-Lite-2x1B-Q4_K_S.gguf Q4_K_S 1.071 GB small, greater quality loss
HelpingAI-Lite-2x1B-Q4_K_M.gguf Q4_K_M 1.126 GB medium, balanced quality - recommended
HelpingAI-Lite-2x1B-Q5_0.gguf Q5_0 1.290 GB legacy; medium, balanced quality - prefer using Q4_K_M
HelpingAI-Lite-2x1B-Q5_K_S.gguf Q5_K_S 1.290 GB large, low quality loss - recommended
HelpingAI-Lite-2x1B-Q5_K_M.gguf Q5_K_M 1.321 GB large, very low quality loss - recommended
HelpingAI-Lite-2x1B-Q6_K.gguf Q6_K 1.528 GB very large, extremely low quality loss
HelpingAI-Lite-2x1B-Q8_0.gguf Q8_0 1.979 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/HelpingAI-Lite-2x1B-GGUF --include "HelpingAI-Lite-2x1B-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/HelpingAI-Lite-2x1B-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'