Hugging Face's logo

tensorblock
/
Qwen2-VL-7B-Instruct-GGUF

Image-Text-to-Text
Transformers
GGUF
English
multimodal
TensorBlock
GGUF
Inference Endpoints
conversational
Model card Files Community
1
Qwen2-VL-7B-Instruct-GGUF / README.md
morriszms's picture
morriszms
Upload folder using huggingface_hub
e8a77e6 verified
preview code
|
raw
history blame contribute delete
4.95 kB
metadata
license: apache-2.0
language:
  - en
pipeline_tag: image-text-to-text
tags:
  - multimodal
  - TensorBlock
  - GGUF
library_name: transformers
base_model: Qwen/Qwen2-VL-7B-Instruct
TensorBlock

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

Qwen/Qwen2-VL-7B-Instruct - GGUF

This repo contains GGUF format model files for Qwen/Qwen2-VL-7B-Instruct.

The files were quantized using machines provided by TensorBlock, and they are compatible with llama.cpp as of commit b4329.

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-VL-7B-Instruct-Q2_K.gguf Q2_K 3.016 GB smallest, significant quality loss - not recommended for most purposes
Qwen2-VL-7B-Instruct-Q3_K_S.gguf Q3_K_S 3.492 GB very small, high quality loss
Qwen2-VL-7B-Instruct-Q3_K_M.gguf Q3_K_M 3.808 GB very small, high quality loss
Qwen2-VL-7B-Instruct-Q3_K_L.gguf Q3_K_L 4.088 GB small, substantial quality loss
Qwen2-VL-7B-Instruct-Q4_0.gguf Q4_0 4.431 GB legacy; small, very high quality loss - prefer using Q3_K_M
Qwen2-VL-7B-Instruct-Q4_K_S.gguf Q4_K_S 4.458 GB small, greater quality loss
Qwen2-VL-7B-Instruct-Q4_K_M.gguf Q4_K_M 4.683 GB medium, balanced quality - recommended
Qwen2-VL-7B-Instruct-Q5_0.gguf Q5_0 5.315 GB legacy; medium, balanced quality - prefer using Q4_K_M
Qwen2-VL-7B-Instruct-Q5_K_S.gguf Q5_K_S 5.315 GB large, low quality loss - recommended
Qwen2-VL-7B-Instruct-Q5_K_M.gguf Q5_K_M 5.445 GB large, very low quality loss - recommended
Qwen2-VL-7B-Instruct-Q6_K.gguf Q6_K 6.254 GB very large, extremely low quality loss
Qwen2-VL-7B-Instruct-Q8_0.gguf Q8_0 8.099 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-VL-7B-Instruct-GGUF --include "Qwen2-VL-7B-Instruct-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-VL-7B-Instruct-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'