Hugging Face's logo

tensorblock
/
Qwen2.5-7B-Instruct-abliterated-v2-GGUF

Text Generation
Transformers
GGUF
English
chat
abliterated
uncensored
TensorBlock
GGUF
Inference Endpoints
conversational
Model card Files Community
Qwen2.5-7B-Instruct-abliterated-v2-GGUF / README.md
morriszms's picture
morriszms
Upload folder using huggingface_hub
a821489 verified
preview code
|
raw
history blame contribute delete
5.69 kB
metadata
library_name: transformers
license: apache-2.0
license_link: >-
  https://huggingface.co/huihui-ai/Qwen2.5-7B-Instruct-abliterated-v2/blob/main/LICENSE
language:
  - en
pipeline_tag: text-generation
base_model: huihui-ai/Qwen2.5-7B-Instruct-abliterated-v2
tags:
  - chat
  - abliterated
  - uncensored
  - TensorBlock
  - GGUF
TensorBlock

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

huihui-ai/Qwen2.5-7B-Instruct-abliterated-v2 - GGUF

This repo contains GGUF format model files for huihui-ai/Qwen2.5-7B-Instruct-abliterated-v2.

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

Prompt template 

<|im_start|>system
{system_prompt}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant

Model file specification

Filename Quant type File Size Description
Qwen2.5-7B-Instruct-abliterated-v2-Q2_K.gguf Q2_K 2.809 GB smallest, significant quality loss - not recommended for most purposes
Qwen2.5-7B-Instruct-abliterated-v2-Q3_K_S.gguf Q3_K_S 3.253 GB very small, high quality loss
Qwen2.5-7B-Instruct-abliterated-v2-Q3_K_M.gguf Q3_K_M 3.547 GB very small, high quality loss
Qwen2.5-7B-Instruct-abliterated-v2-Q3_K_L.gguf Q3_K_L 3.808 GB small, substantial quality loss
Qwen2.5-7B-Instruct-abliterated-v2-Q4_0.gguf Q4_0 4.127 GB legacy; small, very high quality loss - prefer using Q3_K_M
Qwen2.5-7B-Instruct-abliterated-v2-Q4_K_S.gguf Q4_K_S 4.152 GB small, greater quality loss
Qwen2.5-7B-Instruct-abliterated-v2-Q4_K_M.gguf Q4_K_M 4.361 GB medium, balanced quality - recommended
Qwen2.5-7B-Instruct-abliterated-v2-Q5_0.gguf Q5_0 4.950 GB legacy; medium, balanced quality - prefer using Q4_K_M
Qwen2.5-7B-Instruct-abliterated-v2-Q5_K_S.gguf Q5_K_S 4.950 GB large, low quality loss - recommended
Qwen2.5-7B-Instruct-abliterated-v2-Q5_K_M.gguf Q5_K_M 5.071 GB large, very low quality loss - recommended
Qwen2.5-7B-Instruct-abliterated-v2-Q6_K.gguf Q6_K 5.825 GB very large, extremely low quality loss
Qwen2.5-7B-Instruct-abliterated-v2-Q8_0.gguf Q8_0 7.542 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/Qwen2.5-7B-Instruct-abliterated-v2-GGUF --include "Qwen2.5-7B-Instruct-abliterated-v2-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/Qwen2.5-7B-Instruct-abliterated-v2-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'