Hugging Face's logo

tensorblock
/
airoboros-33b-gpt4-1.4.1-lxctx-PI-16384-fp16-GGUF

GGUF
TensorBlock
GGUF
Inference Endpoints
Model card Files Community
airoboros-33b-gpt4-1.4.1-lxctx-PI-16384-fp16-GGUF / README.md
morriszms's picture
morriszms
Upload folder using huggingface_hub
eb6d080 verified
preview code
|
raw
history blame
5.85 kB
metadata
datasets:
  - jondurbin/airoboros-gpt4-1.4.1
tags:
  - TensorBlock
  - GGUF
base_model: bhenrym14/airoboros-33b-gpt4-1.4.1-lxctx-PI-16384-fp16
TensorBlock

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

bhenrym14/airoboros-33b-gpt4-1.4.1-lxctx-PI-16384-fp16 - GGUF

This repo contains GGUF format model files for bhenrym14/airoboros-33b-gpt4-1.4.1-lxctx-PI-16384-fp16.

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
airoboros-33b-gpt4-1.4.1-lxctx-PI-16384-fp16-Q2_K.gguf Q2_K 11.221 GB smallest, significant quality loss - not recommended for most purposes
airoboros-33b-gpt4-1.4.1-lxctx-PI-16384-fp16-Q3_K_S.gguf Q3_K_S 13.098 GB very small, high quality loss
airoboros-33b-gpt4-1.4.1-lxctx-PI-16384-fp16-Q3_K_M.gguf Q3_K_M 14.693 GB very small, high quality loss
airoboros-33b-gpt4-1.4.1-lxctx-PI-16384-fp16-Q3_K_L.gguf Q3_K_L 16.093 GB small, substantial quality loss
airoboros-33b-gpt4-1.4.1-lxctx-PI-16384-fp16-Q4_0.gguf Q4_0 17.095 GB legacy; small, very high quality loss - prefer using Q3_K_M
airoboros-33b-gpt4-1.4.1-lxctx-PI-16384-fp16-Q4_K_S.gguf Q4_K_S 17.213 GB small, greater quality loss
airoboros-33b-gpt4-1.4.1-lxctx-PI-16384-fp16-Q4_K_M.gguf Q4_K_M 18.274 GB medium, balanced quality - recommended
airoboros-33b-gpt4-1.4.1-lxctx-PI-16384-fp16-Q5_0.gguf Q5_0 20.857 GB legacy; medium, balanced quality - prefer using Q4_K_M
airoboros-33b-gpt4-1.4.1-lxctx-PI-16384-fp16-Q5_K_S.gguf Q5_K_S 20.857 GB large, low quality loss - recommended
airoboros-33b-gpt4-1.4.1-lxctx-PI-16384-fp16-Q5_K_M.gguf Q5_K_M 21.464 GB large, very low quality loss - recommended
airoboros-33b-gpt4-1.4.1-lxctx-PI-16384-fp16-Q6_K.gguf Q6_K 24.854 GB very large, extremely low quality loss
airoboros-33b-gpt4-1.4.1-lxctx-PI-16384-fp16-Q8_0.gguf Q8_0 32.191 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/airoboros-33b-gpt4-1.4.1-lxctx-PI-16384-fp16-GGUF --include "airoboros-33b-gpt4-1.4.1-lxctx-PI-16384-fp16-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/airoboros-33b-gpt4-1.4.1-lxctx-PI-16384-fp16-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'