Instructions to use daanand/qwen2_stock with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use daanand/qwen2_stock 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 daanand/qwen2_stock:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf daanand/qwen2_stock:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf daanand/qwen2_stock:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf daanand/qwen2_stock:Q4_K_M

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 daanand/qwen2_stock:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf daanand/qwen2_stock:Q4_K_M

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 daanand/qwen2_stock:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf daanand/qwen2_stock:Q4_K_M

Use Docker

docker model run hf.co/daanand/qwen2_stock:Q4_K_M

LM Studio
Jan

vLLM

How to use daanand/qwen2_stock with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "daanand/qwen2_stock"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "daanand/qwen2_stock",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/daanand/qwen2_stock:Q4_K_M

Ollama
How to use daanand/qwen2_stock with Ollama:
```
ollama run hf.co/daanand/qwen2_stock:Q4_K_M
```

Unsloth Studio

How to use daanand/qwen2_stock 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 daanand/qwen2_stock 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 daanand/qwen2_stock to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for daanand/qwen2_stock to start chatting

Docker Model Runner
How to use daanand/qwen2_stock with Docker Model Runner:
```
docker model run hf.co/daanand/qwen2_stock:Q4_K_M
```

Lemonade

How to use daanand/qwen2_stock with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull daanand/qwen2_stock:Q4_K_M

Run and chat with the model

lemonade run user.qwen2_stock-Q4_K_M

List all available models

lemonade list

Atomic Chat

📈 Qwen2 Stock Analysis SLM (GGUF)

Welcome to the Qwen2 Stock Analysis SLM, a fine-tuned Small Language Model (SLM) based on the Qwen-7B architecture. This model has been specifically optimized to perform technical stock market analysis, with a particular focus on Indian stock market indicators.

By leveraging Unsloth and QLoRA, this model has been trained to interpret technical data such as Price, Relative Strength Index (RSI), and Moving Average Convergence Divergence (MACD) to generate concise, actionable momentum summaries.

📊 Model Details

Feature	Description
Developer	daanand
Model Type	Causal Language Model (Fine-tuned)
Base Model	`unsloth/qwen2-7b-bnb-4bit`
Language	English
License	Apache 2.0
Format	GGUF (`Q4_K_M`)

🎯 Intended Use

This model is designed for developers, quantitative analysts, and financial enthusiasts who want to run a lightweight, local AI model to interpret stock data.

Primary Capabilities:

Summarizing a stock's technical status based on Price and RSI.
Analyzing MACD momentum and identifying potential trend reversals.
Operating entirely locally via GGUF for maximum privacy and low latency.

⚠️ Disclaimer: This model is for educational and informational purposes only. It does not provide financial advice. Always conduct your own research or consult a certified financial advisor before making investment decisions.

⚙️ Training Details

The model was efficiently fine-tuned using a synthetic dataset tailored to Indian stock market technical indicators.

Training Method: QLoRA (Rank 16)
Framework: Unsloth
Epochs: 15
Steps: 60
Quantization: 4-bit (bitsandbytes) during training, subsequently merged and exported to Q4_K_M GGUF for highly optimized CPU/GPU inference.

🚀 How to Use (Local Inference)

Because this model is provided in the GGUF format, it is highly accessible and can be run on consumer hardware using popular local AI inference engines.

1. llama.cpp

You can run this model directly in your terminal using llama.cpp. Once you have downloaded the .gguf file, use the following command:

./llama-cli --model qwen2_stock_analysis.Q4_K_M.gguf --prompt "### Instruction:\nSummarize the technical status for HDFC\n\n### Input:\nPrice: 1650.00, RSI: 78.50\n\n### Response:\n"

Downloads last month: 20

GGUF

Model size

8B params

Architecture

qwen2

Hardware compatibility

4-bit