Instructions to use FINWHALE/RiOS-7B-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use FINWHALE/RiOS-7B-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="FINWHALE/RiOS-7B-GGUF",
	filename="RiOS-7B-Q8_0.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": [
				{
					"type": "text",
					"text": "Describe this image in one sentence."
				},
				{
					"type": "image_url",
					"image_url": {
						"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
					}
				}
			]
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use FINWHALE/RiOS-7B-GGUF with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf FINWHALE/RiOS-7B-GGUF:Q8_0
# Run inference directly in the terminal:
llama cli -hf FINWHALE/RiOS-7B-GGUF:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf FINWHALE/RiOS-7B-GGUF:Q8_0
# Run inference directly in the terminal:
llama cli -hf FINWHALE/RiOS-7B-GGUF:Q8_0

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 FINWHALE/RiOS-7B-GGUF:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf FINWHALE/RiOS-7B-GGUF:Q8_0

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 FINWHALE/RiOS-7B-GGUF:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf FINWHALE/RiOS-7B-GGUF:Q8_0

Use Docker

docker model run hf.co/FINWHALE/RiOS-7B-GGUF:Q8_0

LM Studio
Jan

vLLM

How to use FINWHALE/RiOS-7B-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "FINWHALE/RiOS-7B-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "FINWHALE/RiOS-7B-GGUF",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/FINWHALE/RiOS-7B-GGUF:Q8_0

Ollama
How to use FINWHALE/RiOS-7B-GGUF with Ollama:
```
ollama run hf.co/FINWHALE/RiOS-7B-GGUF:Q8_0
```

Unsloth Studio

How to use FINWHALE/RiOS-7B-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 FINWHALE/RiOS-7B-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 FINWHALE/RiOS-7B-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for FINWHALE/RiOS-7B-GGUF to start chatting

Atomic Chat new
Docker Model Runner
How to use FINWHALE/RiOS-7B-GGUF with Docker Model Runner:
```
docker model run hf.co/FINWHALE/RiOS-7B-GGUF:Q8_0
```

Lemonade

How to use FINWHALE/RiOS-7B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull FINWHALE/RiOS-7B-GGUF:Q8_0

Run and chat with the model

lemonade run user.RiOS-7B-GGUF-Q8_0

List all available models

lemonade list

RiOS-7B

版本:v0.0.1(首个公开发布版)

睿思(RiOS) 是一个通用多模态智能助手,支持图文对话, 在金融投资分析(K线、财报图表解读)与艺术鉴赏(流派、构图、色彩分析)方向做了专项强化, 并预留向 VLA(Vision-Language-Action)机器人应用演进的能力。

训练说明

本模型基于 Qwen2.5-VL-7B-Instruct 使用 Unsloth QLoRA 微调并合并权重得到。基座模型遵循 Apache 2.0 许可证,本模型同样以 Apache 2.0 发布。

使用

transformers

from transformers import Qwen2_5_VLForConditionalGeneration, AutoProcessor

model = Qwen2_5_VLForConditionalGeneration.from_pretrained(
    "FINWHALE/RiOS-7B", torch_dtype="auto", device_map="auto")
processor = AutoProcessor.from_pretrained("FINWHALE/RiOS-7B")

vLLM

vllm serve FINWHALE/RiOS-7B --limit-mm-per-prompt image=4

Ollama / llama.cpp

请使用配套的 GGUF 仓库(FINWHALE/RiOS-7B-GGUF),包含 Q8_0 主模型与 mmproj 视觉投影文件。

免责声明

模型输出的金融相关内容仅供参考,不构成投资建议。

Downloads last month: 112

GGUF

Model size

8B params

Architecture

qwen2vl

Hardware compatibility

8-bit

Model tree for FINWHALE/RiOS-7B-GGUF

Base model

Qwen/Qwen2.5-VL-7B-Instruct

Quantized

(144)

this model