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

Libraries

How to use SoumilB7/Moonfinance_Fundamental with Transformers:

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

pipe = pipeline("text-generation", model="SoumilB7/Moonfinance_Fundamental")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("SoumilB7/Moonfinance_Fundamental", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use SoumilB7/Moonfinance_Fundamental with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "SoumilB7/Moonfinance_Fundamental"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SoumilB7/Moonfinance_Fundamental",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/SoumilB7/Moonfinance_Fundamental

SGLang

How to use SoumilB7/Moonfinance_Fundamental 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_Fundamental" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SoumilB7/Moonfinance_Fundamental",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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_Fundamental" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SoumilB7/Moonfinance_Fundamental",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Unsloth Desktop
Docker Model Runner
How to use SoumilB7/Moonfinance_Fundamental with Docker Model Runner:
```
docker model run hf.co/SoumilB7/Moonfinance_Fundamental
```

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 — Version 3 (March 2026)

MoonFinance is a specialized financial reasoning model suite developed as part of an independent startup research initiative. This release represents Version 3 (March 2026) of the MoonFinance model line, incorporating improved domain adaptation, reasoning stability, and updated financial datasets.

Model Overview

Model Name: MoonFinance
Version: v3.1
Developed by: SoumilB7
Base Model: unsloth/llama-3-8b-bnb-4bit
Architecture: Quantized LLaMA-3 with Low-Rank Adapter (LoRA) finetuning
Primary Domain: Financial analysis, trading signals, macro reasoning, retrieval-augmented financial QA
License: CC-BY-4.0

This model is designed to assist in:

Fundamental equity analysis
Technical indicator interpretation
Financial news reasoning
Strategy hypothesis generation
Structured financial Q&A pipelines
Retrieval-augmented generation (RAG) workflows

Version 3 Improvements (March 2026)

This release introduces:

Expanded financial training corpus updated to March 2026 market context
Improved multi-step reasoning consistency
Better handling of noisy market narratives and speculative signals
Stability improvements in long-context inference
Enhanced alignment for structured financial outputs
Optimized LoRA adaptation layers for reduced hallucination in domain queries

Weights are optimized for efficient inference on consumer GPUs via 4-bit quantization.

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

Model tree for SoumilB7/Moonfinance_Fundamental

Base model

meta-llama/Meta-Llama-3-8B

Quantized

unsloth/llama-3-8b-bnb-4bit

Adapter

(314)

this model