Skip to content
ModelListedExternal
Browse files

MiniCPM Llama3 V 2 5 Int4

This is the int4 quantized version of MiniCPM-Llama3-V 2.5. Running with int4 version would use lower GPU memory (about 9GB).

Sourcehuggingface.co/mgoin/MiniCPM-Llama3-V-2_5-int4/tree/8a7987e8f78a4d34afb5cb557c00c8f29e8d12e2
KindOtherVersionRevision 8a7987eBgrade

Model source

Kind
Other
File size
1.40–4.33 GB
Version
vRevision 8a7987e
Updated
Nov 2, 2026
Downloads
10
Source
Hugging Face

Source description

MiniCPM-Llama3-V 2.5 int4

This is the int4 quantized version of MiniCPM-Llama3-V 2.5.
Running with int4 version would use lower GPU memory (about 9GB).

Usage

Inference using Huggingface transformers on NVIDIA GPUs. Requirements tested on python 3.10:

Pillow==10.1.0
torch==2.1.2
torchvision==0.16.2
transformers==4.40.0
sentencepiece==0.1.99
accelerate==0.30.1
bitsandbytes==0.43.1

# test.py
import torch
from PIL import Image
from transformers import AutoModel, AutoTokenizer

model = AutoModel.from_pretrained('openbmb/MiniCPM-Llama3-V-2_5-int4', trust_remote_code=True)
tokenizer = AutoTokenizer.from_pretrained('openbmb/MiniCPM-Llama3-V-2_5-int4', trust_remote_code=True)
model.eval()

image = Image.open('xx.jpg').convert('RGB')
question = 'What is in the image?'
msgs = [{'role': 'user', 'content': question}]

res = model.chat(
    image=image,
    msgs=msgs,
    tokenizer=tokenizer,
    sampling=True, # if sampling=False, beam_search will be used by default
    temperature=0.7,
    # system_prompt='' # pass system_prompt if needed
)
print(res)

## if you want to use streaming, please make sure sampling=True and stream=True
## the model.chat will return a generator
res = model.chat(
    image=image,
    msgs=msgs,
    tokenizer=tokenizer,
    sampling=True,
    temperature=0.7,
    stream=True
)

generated_text = ""
for new_text in res:
    generated_text += new_text
    print(new_text, flush=True, end='')

Sources

1 source
Hugging FacePrimaryVersion 8a7987e8f78a4d34afb5cb557c00c8f29e8d12e2
huggingface.co/mgoin/MiniCPM-Llama3-V-2_5-int4/tree/8a7987e8f78a4d34afb5cb557c00c8f29e8d12e2

Verified Nov 2

Download files

Model · 2 weight files

All files listed in the provider index are present.

Repository files

File inventory only; completeness is unverified.

Model artifacts

2 artifacts

model-00001-of-00002.safetensors

safetensors · 4.33 GB · SHA-256 5e20e08a758d…b3fc · Hugging Face

Download shard

model-00002-of-00002.safetensors

safetensors · 1.40 GB · SHA-256 8600aa101dcb…95ce · Hugging Face

Download shard

Source excerpts

3 excerpts
ReadmeAug 21huggingface.co/mgoin/MiniCPM-Llama3-V-2_5-int4

--- pipeline_tag: visual-question-answering --- ## MiniCPM-Llama3-V 2.5 int4 This is the int4 quantized version of [MiniCPM-Llama3-V 2.5](https://huggingface.co/openbmb/MiniCPM-Llama3-V-2_5). Running with int4 version would use lower GPU memory (about 9GB). ## Usage Inference using Huggingface transformers on NVIDIA GPUs. Requirements tested on python 3.10： ``` Pillow==10.1.0 torch==2.1.2 torchvision==0.16.2 transformers==4.40.0 sentencepiece==0.1.99 accelerate==0.30.1 bitsandbytes==0.43.1 ``` ```python # test.py import torch from PIL import Image from transformers import AutoModel, AutoTokenizer model = AutoModel.from_pretrained('openbmb/MiniCPM-Llama3-V-2_5-int4', trust_remote_code=True) tokenizer = AutoTokenizer.from_pretrained('openbmb/MiniCPM-Llama3-V-2_5-int4', trust_remote_code=True) model.eval() image = Image.open('xx.jpg').convert('RGB') question = 'What is in the image?' msgs = [{'role': 'user', 'content': question}] res = model.chat( image=image, msgs=msgs, tokenizer=tokenizer, sampling=True, # if sampling=False, beam_search will be used by default temperature=0.7, # system_prompt='' # pass system_prompt if needed ) print(res) ## if you want to use streaming, please make sure sampling=True and stream=True ## the model.chat will return a generator res = model.chat( image=image, msgs=msgs, tokenizer=tokenizer, sampling=True, temperature=0.7, stream=True ) generated_text = "" for new_text in res: generated_text += new_text print(new_text, flush=True, end='') ```

NoteNov 2huggingface.co/mgoin/MiniCPM-Llama3-V-2_5-int4

Source context: 10 downloads · 0 likes · Pipeline visual-question-answering · Repo mgoin/MiniCPM-Llama3-V-2_5-int4

NoteAug 21huggingface.co/mgoin/MiniCPM-Llama3-V-2_5-int4

Source context: 8 downloads · 0 likes · Pipeline visual-question-answering · Repo mgoin/MiniCPM-Llama3-V-2_5-int4