Instructions to use Ryder99/Llama-3.2-1B-Instruct-Hindi with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Ryder99/Llama-3.2-1B-Instruct-Hindi with Transformers:

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

pipe = pipeline("text-generation", model="Ryder99/Llama-3.2-1B-Instruct-Hindi")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Ryder99/Llama-3.2-1B-Instruct-Hindi")
model = AutoModelForCausalLM.from_pretrained("Ryder99/Llama-3.2-1B-Instruct-Hindi", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use Ryder99/Llama-3.2-1B-Instruct-Hindi 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 Ryder99/Llama-3.2-1B-Instruct-Hindi:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Ryder99/Llama-3.2-1B-Instruct-Hindi:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Ryder99/Llama-3.2-1B-Instruct-Hindi:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Ryder99/Llama-3.2-1B-Instruct-Hindi: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 Ryder99/Llama-3.2-1B-Instruct-Hindi:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Ryder99/Llama-3.2-1B-Instruct-Hindi: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 Ryder99/Llama-3.2-1B-Instruct-Hindi:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Ryder99/Llama-3.2-1B-Instruct-Hindi:Q4_K_M

Use Docker

docker model run hf.co/Ryder99/Llama-3.2-1B-Instruct-Hindi:Q4_K_M

LM Studio
Jan

vLLM

How to use Ryder99/Llama-3.2-1B-Instruct-Hindi with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Ryder99/Llama-3.2-1B-Instruct-Hindi"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Ryder99/Llama-3.2-1B-Instruct-Hindi",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Ryder99/Llama-3.2-1B-Instruct-Hindi:Q4_K_M

SGLang

How to use Ryder99/Llama-3.2-1B-Instruct-Hindi 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 "Ryder99/Llama-3.2-1B-Instruct-Hindi" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Ryder99/Llama-3.2-1B-Instruct-Hindi",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "Ryder99/Llama-3.2-1B-Instruct-Hindi" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Ryder99/Llama-3.2-1B-Instruct-Hindi",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use Ryder99/Llama-3.2-1B-Instruct-Hindi with Ollama:
```
ollama run hf.co/Ryder99/Llama-3.2-1B-Instruct-Hindi:Q4_K_M
```
Unsloth Desktop

How to use Ryder99/Llama-3.2-1B-Instruct-Hindi with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Ryder99/Llama-3.2-1B-Instruct-Hindi:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "Ryder99/Llama-3.2-1B-Instruct-Hindi:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use Ryder99/Llama-3.2-1B-Instruct-Hindi with Docker Model Runner:
```
docker model run hf.co/Ryder99/Llama-3.2-1B-Instruct-Hindi:Q4_K_M
```

Lemonade

How to use Ryder99/Llama-3.2-1B-Instruct-Hindi with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Ryder99/Llama-3.2-1B-Instruct-Hindi:Q4_K_M

Run and chat with the model

lemonade run user.Llama-3.2-1B-Instruct-Hindi-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use Ryder99/Llama-3.2-1B-Instruct-Hindi with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Ryder99/Llama-3.2-1B-Instruct-Hindi: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 Ryder99/Llama-3.2-1B-Instruct-Hindi:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use Ryder99/Llama-3.2-1B-Instruct-Hindi with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Ryder99/Llama-3.2-1B-Instruct-Hindi: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 "Ryder99/Llama-3.2-1B-Instruct-Hindi: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"

Uploaded model

Developed by: Ryder99
License: apache-2.0
Finetuned from model : unsloth/Llama-3.2-1B-Instruct-unsloth-bnb-4bit

This model was created as part of a project for my NLP course at University. I'm limited to what free Colab can handle, but I'm satisfied with the performance of this model considering the small size. With some preliminary testing, it appears to be slightly faster than the base Meta Llama 3.2 1B, while producing significantly better Hindi output and comparable English output. The model appears to prefer outputting Hindi regardless of prompt language if there is any Hindi in the context.

I intend to do some better testing in the future, but until then this model is provided as is for you to try. It might be convenient to use Google Translate or some similar service to write the prompt in Devnagari and translate the output back to English for quick testing if, like me, Hindi is not your first language and you struggle to read it. The model seems viable as an on-device model for Hindi-speakers, with usable inference speeds even on a phone (tested using Ollama on Termux).

A slightly bigger model can be found at Llama-3.2-3B-Instruct-Hindi.

For queries, or to help me train larger models ( ...I couldn't get lab access :( ... ) you can mail me here.

This llama model was trained 2x faster with Unsloth and Huggingface's TRL library.