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

Libraries

How to use SoumilB7/Moonfinance_Technical with Transformers:

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

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

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

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use SoumilB7/Moonfinance_Technical with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "SoumilB7/Moonfinance_Technical"
# 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_Technical",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/SoumilB7/Moonfinance_Technical

SGLang

How to use SoumilB7/Moonfinance_Technical 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_Technical" \
    --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_Technical",
		"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_Technical" \
        --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_Technical",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Unsloth Studio new

How to use SoumilB7/Moonfinance_Technical 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_Technical 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_Technical 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_Technical to start chatting

Load model with FastModel

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

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

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 Technical Core — Version 3 (March 2026)

MoonFinance Technical Core is a specialized financial language model focused on the methodology and reasoning processes behind technical market analysis. This Version 3 (March 2026) release improves structured interpretation of price action, indicator confluence, and signal validation workflows.

Model Overview

*Model Name:- MoonFinance Technical Core
*Version:- v3.1
*Developed by:- SoumilB7
*Base Model:- unsloth/meta-llama-3.1-8b-bnb-4bit
*Architecture:- Quantized LLaMA-3.1 finetuned for technical analysis reasoning
*Primary Domain:- Chart analysis logic, indicator interaction reasoning, trading signal methodology
*License:- CC-BY-4.0

This model is designed to assist in:

Step-by-step technical analysis reasoning
Multi-indicator confluence interpretation
Trend structure and momentum assessment
Volatility regime understanding
Strategy construction from chart-driven signals

Version 3 Improvements (March 2026)

This release introduces:

Expanded training exposure to recent market structure behaviour
Improved reasoning consistency across multi-timeframe analysis prompts
Better handling of conflicting indicator signals
Enhanced structured analytical output formatting
Stability improvements for longer technical reasoning chains

Optimized for efficient 4-bit inference on consumer-grade GPUs.

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