Instructions to use SoumilB7/Moonfinance-Rag-Reasoning with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use SoumilB7/Moonfinance-Rag-Reasoning with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="SoumilB7/Moonfinance-Rag-Reasoning")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("SoumilB7/Moonfinance-Rag-Reasoning", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use SoumilB7/Moonfinance-Rag-Reasoning with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "SoumilB7/Moonfinance-Rag-Reasoning"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SoumilB7/Moonfinance-Rag-Reasoning",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/SoumilB7/Moonfinance-Rag-Reasoning

SGLang

How to use SoumilB7/Moonfinance-Rag-Reasoning with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "SoumilB7/Moonfinance-Rag-Reasoning" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SoumilB7/Moonfinance-Rag-Reasoning",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "SoumilB7/Moonfinance-Rag-Reasoning" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SoumilB7/Moonfinance-Rag-Reasoning",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Studio new

How to use SoumilB7/Moonfinance-Rag-Reasoning 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 SoumilB7/Moonfinance-Rag-Reasoning 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 SoumilB7/Moonfinance-Rag-Reasoning to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for SoumilB7/Moonfinance-Rag-Reasoning to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="SoumilB7/Moonfinance-Rag-Reasoning",
    max_seq_length=2048,
)

Docker Model Runner
How to use SoumilB7/Moonfinance-Rag-Reasoning with Docker Model Runner:
```
docker model run hf.co/SoumilB7/Moonfinance-Rag-Reasoning
```

You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

MoonFinance Reasoning — Version 3 (March 2026)

MoonFinance Reasoning is a domain-adapted financial language model focused on structured analytical thinking, trading logic synthesis, and decision-style reasoning workflows. This Version 3 (March 2026) release improves financial context alignment, reasoning stability, and robustness across complex market narrative prompts.

Model Overview

Model Name: MoonFinance Reasoning
Version: v3.1
Developed by: SoumilB7
Base Model: unsloth/deepseek-r1-0528-qwen3-8b-unsloth-bnb-4bit
Architecture: Quantized reasoning-optimized transformer finetuned for financial analysis tasks
Primary Domain: Financial reasoning, trading decision logic, macro narrative interpretation
License: CC-BY-4.0

This model is designed to assist in:

Step-by-step financial reasoning
Strategy hypothesis generation
Market sentiment and narrative interpretation
Structured analytical response generation
Research experimentation in financial LLM systems

Version 3 Improvements (March 2026)

Expanded financial reasoning dataset aligned with recent market conditions
Improved consistency in multi-step analytical outputs
Better handling of speculative and uncertain market prompts
Enhanced long-context reasoning stability
Optimized performance for efficient 4-bit consumer GPU inference

Downloads last month: -; Downloads are not tracked for this model. How to track

Safetensors

Model size

8B params

Tensor type

BF16