Instructions to use ERNIE-Community/ERNIE-4.5-VL-28B-A3B-Thinking-F16-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ERNIE-Community/ERNIE-4.5-VL-28B-A3B-Thinking-F16-gguf with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="ERNIE-Community/ERNIE-4.5-VL-28B-A3B-Thinking-F16-gguf",
	filename="ernie-vl-4.5-28b-a3b-text.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use ERNIE-Community/ERNIE-4.5-VL-28B-A3B-Thinking-F16-gguf with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf ERNIE-Community/ERNIE-4.5-VL-28B-A3B-Thinking-F16-gguf
# Run inference directly in the terminal:
llama-cli -hf ERNIE-Community/ERNIE-4.5-VL-28B-A3B-Thinking-F16-gguf

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf ERNIE-Community/ERNIE-4.5-VL-28B-A3B-Thinking-F16-gguf
# Run inference directly in the terminal:
llama-cli -hf ERNIE-Community/ERNIE-4.5-VL-28B-A3B-Thinking-F16-gguf

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf ERNIE-Community/ERNIE-4.5-VL-28B-A3B-Thinking-F16-gguf
# Run inference directly in the terminal:
./llama-cli -hf ERNIE-Community/ERNIE-4.5-VL-28B-A3B-Thinking-F16-gguf

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf ERNIE-Community/ERNIE-4.5-VL-28B-A3B-Thinking-F16-gguf
# Run inference directly in the terminal:
./build/bin/llama-cli -hf ERNIE-Community/ERNIE-4.5-VL-28B-A3B-Thinking-F16-gguf

Use Docker

docker model run hf.co/ERNIE-Community/ERNIE-4.5-VL-28B-A3B-Thinking-F16-gguf

LM Studio
Jan
Ollama
How to use ERNIE-Community/ERNIE-4.5-VL-28B-A3B-Thinking-F16-gguf with Ollama:
```
ollama run hf.co/ERNIE-Community/ERNIE-4.5-VL-28B-A3B-Thinking-F16-gguf
```

Unsloth Studio

How to use ERNIE-Community/ERNIE-4.5-VL-28B-A3B-Thinking-F16-gguf with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for ERNIE-Community/ERNIE-4.5-VL-28B-A3B-Thinking-F16-gguf to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for ERNIE-Community/ERNIE-4.5-VL-28B-A3B-Thinking-F16-gguf to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for ERNIE-Community/ERNIE-4.5-VL-28B-A3B-Thinking-F16-gguf to start chatting

Atomic Chat new
Docker Model Runner
How to use ERNIE-Community/ERNIE-4.5-VL-28B-A3B-Thinking-F16-gguf with Docker Model Runner:
```
docker model run hf.co/ERNIE-Community/ERNIE-4.5-VL-28B-A3B-Thinking-F16-gguf
```

Lemonade

How to use ERNIE-Community/ERNIE-4.5-VL-28B-A3B-Thinking-F16-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull ERNIE-Community/ERNIE-4.5-VL-28B-A3B-Thinking-F16-gguf

Run and chat with the model

lemonade run user.ERNIE-4.5-VL-28B-A3B-Thinking-F16-gguf-{{QUANT_TAG}}

List all available models

lemonade list

dont work with actual lm-studio

by kalle07 - opened 21 days ago

Discussion

kalle07

21 days ago

0.00.127.651 E llama_model_load: error loading model: unknown model architecture: 'ernie4_5-vl-moe'
0.00.127.656 E llama_model_load_from_file_impl: failed to load model
0.00.127.661 E common_init_from_params: failed to load model '...\ernie-vl-4.5-28b-a3b-text.gguf'
0.00.127.833 E srv load_model: failed to load model, ...\ernie-vl-4.5-28b-a3b-text.gguf': error loading model: unknown model architecture: 'ernie4_5-vl-moe'

gatilin

ERNIE Community org 20 days ago

you should install this repo: https://github.com/PFCCLab/llama.cpp-ernie

kalle07

20 days ago

nearly no one does , you see at your only 24 downloads/month ...
It's a shame about all your efforts, but if you're not listed in the official llama

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment