Instructions to use sudarshan-plus/stock-gemma-merged-new with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use sudarshan-plus/stock-gemma-merged-new 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 sudarshan-plus/stock-gemma-merged-new:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf sudarshan-plus/stock-gemma-merged-new:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf sudarshan-plus/stock-gemma-merged-new:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf sudarshan-plus/stock-gemma-merged-new: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 sudarshan-plus/stock-gemma-merged-new:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf sudarshan-plus/stock-gemma-merged-new: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 sudarshan-plus/stock-gemma-merged-new:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf sudarshan-plus/stock-gemma-merged-new:Q4_K_M

Use Docker

docker model run hf.co/sudarshan-plus/stock-gemma-merged-new:Q4_K_M

LM Studio
Jan
Ollama
How to use sudarshan-plus/stock-gemma-merged-new with Ollama:
```
ollama run hf.co/sudarshan-plus/stock-gemma-merged-new:Q4_K_M
```

Unsloth Studio

How to use sudarshan-plus/stock-gemma-merged-new 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 sudarshan-plus/stock-gemma-merged-new 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 sudarshan-plus/stock-gemma-merged-new to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for sudarshan-plus/stock-gemma-merged-new to start chatting

How to use sudarshan-plus/stock-gemma-merged-new with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf sudarshan-plus/stock-gemma-merged-new:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "sudarshan-plus/stock-gemma-merged-new:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use sudarshan-plus/stock-gemma-merged-new with Docker Model Runner:
```
docker model run hf.co/sudarshan-plus/stock-gemma-merged-new:Q4_K_M
```

Lemonade

How to use sudarshan-plus/stock-gemma-merged-new with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull sudarshan-plus/stock-gemma-merged-new:Q4_K_M

Run and chat with the model

lemonade run user.stock-gemma-merged-new-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use sudarshan-plus/stock-gemma-merged-new with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf sudarshan-plus/stock-gemma-merged-new:Q4_K_M

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default sudarshan-plus/stock-gemma-merged-new:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use sudarshan-plus/stock-gemma-merged-new with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf sudarshan-plus/stock-gemma-merged-new:Q4_K_M

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "sudarshan-plus/stock-gemma-merged-new:Q4_K_M" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

A newer version of this model is available: sudarshan-plus/stock-gemma-31b-GGUF

Model Details

Model Description

Trained on selected NSE symbols and not tested[

REL
TCS
INFY
HDFCBANK
TMPV ]. Refer to sudarshan-plus/stock-gemma-31b-GGUF model which was tested during training.
Developed by: Sudarshan
Model type: instruction-tuned
Language(s) (NLP): en
License: apache-2.0
Finetuned from model gemma-4-31b:

Uses

Example use. Analyzing RELIANCE...

''user You are an expert quantitative analyst. Review the technical snapshot for RELIANCE on 2026-08-14.

Close Price: 1310.00
20-Day SMA: 1302.34
50-Day SMA: 1301.43
RSI (14): 57.80
MACD Diff: 2.7464
20-Day Volatility: 0.0126
Volume Shift: 5.22%

Provide an analytical breakdown and a final 5-day recommendation (BUY, SELL, or HOLD). '' ''model

-> Price: 1310.00 | RSI: 57.8 | MACD: 2.75 -> Querying Hugging Face Endpoint (streaming, attempt 1/1)...

RSI (14): 57.80 MACD: 2.7464 20-day volatility: 0.0126 Volume change vs prior day: 5.22% Recommendation: HOLD Rationale: Based on the technical snapshot, the 5-day forward return was historically consistent with a HOLD signal given the RSI, MACD, and moving-average positioning shown above.

Out-of-Scope Use

Model is not intended for making financial decisions. The model is suggesstive, not concretised decision maker. The developer is not responsible for any financial losses.

Bias, Risks, and Limitations

No guarantee of accuracy of the model predictions.

Recommendations

For more organised results refer to the newer version of the model.

Training Details

Training Data

The data was trained using proprietory service. So pretrained data can be considered as accurate.

Training Procedure

Training was done on cloud based shared freemium gpus, FastLanguageModel module and chronological datasets, efficieny is not guaranteed while training.

Preprocessing

Data preparation and preprocessing was done.

Training Hyperparameters

fp16

Testing Data

Testing data was 10% of the training data.

Results

Untested so, results may vary.

Model Architecture and Objective

To test the feasibility of high parameter models on stock market data.

Compute Infrastructure

A100-40GB GPU

Model Card Authors

Sudarshan

Knowledge Cutoff on 14-Aug-2026

Downloads last month: 62

GGUF

Model size

31B params

Architecture

gemma4

Hardware compatibility

4-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for sudarshan-plus/stock-gemma-merged-new

Base model

google/gemma-4-31B

Finetuned

google/gemma-4-31B-it

Quantized

(305)

this model