Image-Text-to-Text
GGUF
English
Hindi
geospatial
satellite-imagery
remote-sensing
object-detection
multimodal
vision
ollama
defense
indic
sovereign-ai
Instructions to use techindro/SamyamLM-V1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use techindro/SamyamLM-V1 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 techindro/SamyamLM-V1:F16 # Run inference directly in the terminal: llama cli -hf techindro/SamyamLM-V1:F16
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf techindro/SamyamLM-V1:F16 # Run inference directly in the terminal: llama cli -hf techindro/SamyamLM-V1:F16
Build from source code
git clone https://github.com/ggml-org/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-app # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama serve -hf techindro/SamyamLM-V1:F16 # Run inference directly in the terminal: ./build/bin/llama cli -hf techindro/SamyamLM-V1:F16
Use Docker
docker model run hf.co/techindro/SamyamLM-V1:F16
- Llama new
- LM Studio
- Jan
- vLLM
How to use techindro/SamyamLM-V1 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "techindro/SamyamLM-V1" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "techindro/SamyamLM-V1", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/techindro/SamyamLM-V1:F16
- Ollama
How to use techindro/SamyamLM-V1 with Ollama:
ollama run hf.co/techindro/SamyamLM-V1:F16
- Unsloth Desktop
- Docker Model Runner
How to use techindro/SamyamLM-V1 with Docker Model Runner:
docker model run hf.co/techindro/SamyamLM-V1:F16
- Lemonade
How to use techindro/SamyamLM-V1 with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull techindro/SamyamLM-V1:F16
Run and chat with the model
lemonade run user.SamyamLM-V1-F16
List all available models
lemonade list
- Atomic Chat
Download inference.py from techindro/SamyamLM-V1: direct link, hf CLI and curl.
- Browser
- Download file 1.54 kB
-
https://huggingface.co/techindro/SamyamLM-V1/resolve/main/inference.py
- Command line
-
hf download hf://techindro/SamyamLM-V1/inference.py
-
curl -L -o inference.py https://huggingface.co/techindro/SamyamLM-V1/resolve/main/inference.py
1.54 kB
| #!/usr/bin/env python3 | |
| """ | |
| SamyamLM-V1 — Test Inference Client | |
| Quickly run spatial & satellite image analysis with local Ollama runtime. | |
| """ | |
| import sys | |
| import base64 | |
| import requests | |
| def analyze_image(image_path: str, prompt: str = "Analyze this image and identify all objects with bounding boxes."): | |
| # 1. Base64 encode the image | |
| with open(image_path, "rb") as f: | |
| img_b64 = base64.b64encode(f.read()).decode("utf-8") | |
| # 2. Query local SamyamLM server | |
| payload = { | |
| "model": "samyam-lm-v1", | |
| "prompt": prompt, | |
| "images": [img_b64], | |
| "stream": False, | |
| "options": { | |
| "temperature": 0.2, | |
| "top_p": 0.9 | |
| } | |
| } | |
| try: | |
| response = requests.post("http://localhost:11434/api/generate", json=payload) | |
| response.raise_for_status() | |
| return response.json().get("response", "") | |
| except requests.exceptions.ConnectionError: | |
| return "❌ Error: Ollama is not running on http://localhost:11434. Start it with: ollama serve" | |
| if __name__ == "__main__": | |
| if len(sys.argv) < 2: | |
| print("Usage: python inference.py <path_to_satellite_or_drone_image.jpg> [prompt]") | |
| sys.exit(1) | |
| img_path = sys.argv[1] | |
| user_prompt = sys.argv[2] if len(sys.argv) > 2 else "Describe tactical assets and provide bounding boxes [ymin, xmin, ymax, xmax]." | |
| print(f"🛰️ Running SamyamLM-V1 inference on: {img_path}...") | |
| result = analyze_image(img_path, user_prompt) | |
| print("\n--- Model Output ---") | |
| print(result) | |