Hugging Face's logo

tensorblock
/
ghost-8b-beta-GGUF

Text Generation
Transformers
GGUF
ghost
tools
chat
unsloth
llama
TensorBlock
GGUF
Inference Endpoints
conversational
Model card Files Community
ghost-8b-beta-GGUF / README.md
morriszms's picture
morriszms
Upload folder using huggingface_hub
2d677b3 verified
preview code
|
raw
history blame contribute delete
4.88 kB
metadata
language:
  - en
  - vi
  - es
  - pt
  - de
  - it
  - fr
  - ko
  - zh
license: other
license_name: ghost-open-llms
license_link: https://ghost-x.org/ghost-open-llms-license
tags:
  - ghost
  - tools
  - chat
  - transformers
  - unsloth
  - llama
  - TensorBlock
  - GGUF
pipeline_tag: text-generation
widget:
  - text: Why is the sky blue ?
base_model: ghost-x/ghost-8b-beta
TensorBlock

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

ghost-x/ghost-8b-beta - GGUF

This repo contains GGUF format model files for ghost-x/ghost-8b-beta.

The files were quantized using machines provided by TensorBlock, and they are compatible with llama.cpp as of commit b4011.

Prompt template 

<|bos|><|role:begin|>system<|role:end|>
{system_prompt}<|cos|>
<|role:begin|>user<|role:end|>
{prompt}<|cos|>
<|role:begin|>assistant<|role:end|>

Model file specification

Filename Quant type File Size Description
ghost-8b-beta-Q2_K.gguf Q2_K 3.179 GB smallest, significant quality loss - not recommended for most purposes
ghost-8b-beta-Q3_K_S.gguf Q3_K_S 3.664 GB very small, high quality loss
ghost-8b-beta-Q3_K_M.gguf Q3_K_M 4.019 GB very small, high quality loss
ghost-8b-beta-Q3_K_L.gguf Q3_K_L 4.322 GB small, substantial quality loss
ghost-8b-beta-Q4_0.gguf Q4_0 4.661 GB legacy; small, very high quality loss - prefer using Q3_K_M
ghost-8b-beta-Q4_K_S.gguf Q4_K_S 4.693 GB small, greater quality loss
ghost-8b-beta-Q4_K_M.gguf Q4_K_M 4.921 GB medium, balanced quality - recommended
ghost-8b-beta-Q5_0.gguf Q5_0 5.599 GB legacy; medium, balanced quality - prefer using Q4_K_M
ghost-8b-beta-Q5_K_S.gguf Q5_K_S 5.599 GB large, low quality loss - recommended
ghost-8b-beta-Q5_K_M.gguf Q5_K_M 5.733 GB large, very low quality loss - recommended
ghost-8b-beta-Q6_K.gguf Q6_K 6.596 GB very large, extremely low quality loss
ghost-8b-beta-Q8_0.gguf Q8_0 8.541 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/ghost-8b-beta-GGUF --include "ghost-8b-beta-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/ghost-8b-beta-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'