Instructions to use qbz506/nyaya-llama-3b-stage0-full with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use qbz506/nyaya-llama-3b-stage0-full with Transformers:

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

pipe = pipeline("text-generation", model="qbz506/nyaya-llama-3b-stage0-full")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("qbz506/nyaya-llama-3b-stage0-full")
model = AutoModelForMultimodalLM.from_pretrained("qbz506/nyaya-llama-3b-stage0-full")
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]:]))

llama-cpp-python

How to use qbz506/nyaya-llama-3b-stage0-full with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="qbz506/nyaya-llama-3b-stage0-full",
	filename="nyaya-llama-3b-stage0-merged-q4.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use qbz506/nyaya-llama-3b-stage0-full with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf qbz506/nyaya-llama-3b-stage0-full
# Run inference directly in the terminal:
llama-cli -hf qbz506/nyaya-llama-3b-stage0-full

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf qbz506/nyaya-llama-3b-stage0-full
# Run inference directly in the terminal:
llama-cli -hf qbz506/nyaya-llama-3b-stage0-full

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 qbz506/nyaya-llama-3b-stage0-full
# Run inference directly in the terminal:
./llama-cli -hf qbz506/nyaya-llama-3b-stage0-full

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 qbz506/nyaya-llama-3b-stage0-full
# Run inference directly in the terminal:
./build/bin/llama-cli -hf qbz506/nyaya-llama-3b-stage0-full

Use Docker

docker model run hf.co/qbz506/nyaya-llama-3b-stage0-full

LM Studio
Jan

vLLM

How to use qbz506/nyaya-llama-3b-stage0-full with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "qbz506/nyaya-llama-3b-stage0-full"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "qbz506/nyaya-llama-3b-stage0-full",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/qbz506/nyaya-llama-3b-stage0-full

SGLang

How to use qbz506/nyaya-llama-3b-stage0-full 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 "qbz506/nyaya-llama-3b-stage0-full" \
    --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": "qbz506/nyaya-llama-3b-stage0-full",
		"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 "qbz506/nyaya-llama-3b-stage0-full" \
        --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": "qbz506/nyaya-llama-3b-stage0-full",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use qbz506/nyaya-llama-3b-stage0-full with Ollama:
```
ollama run hf.co/qbz506/nyaya-llama-3b-stage0-full
```

Unsloth Studio

How to use qbz506/nyaya-llama-3b-stage0-full 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 qbz506/nyaya-llama-3b-stage0-full 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 qbz506/nyaya-llama-3b-stage0-full to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for qbz506/nyaya-llama-3b-stage0-full to start chatting

How to use qbz506/nyaya-llama-3b-stage0-full with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf qbz506/nyaya-llama-3b-stage0-full

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": "qbz506/nyaya-llama-3b-stage0-full"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use qbz506/nyaya-llama-3b-stage0-full with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf qbz506/nyaya-llama-3b-stage0-full

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 qbz506/nyaya-llama-3b-stage0-full

Run Hermes

hermes

Atomic Chat new
Docker Model Runner
How to use qbz506/nyaya-llama-3b-stage0-full with Docker Model Runner:
```
docker model run hf.co/qbz506/nyaya-llama-3b-stage0-full
```

Lemonade

How to use qbz506/nyaya-llama-3b-stage0-full with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull qbz506/nyaya-llama-3b-stage0-full

Run and chat with the model

lemonade run user.nyaya-llama-3b-stage0-full-{{QUANT_TAG}}

List all available models

lemonade list

Pramana Stage 0 (Full Merged Weights)

This folder contains full merged weights for the Stage 0 Nyaya-structured model. It does not require a LoRA adapter at inference time.

What is included

model-00001-of-00002.safetensors
model-00002-of-00002.safetensors
model.safetensors.index.json
config.json, tokenizer.json, tokenizer_config.json, chat_template.jinja
nyaya-llama-3b-stage0-merged-q4.gguf (quantized full model for Ollama)

Base model

unsloth/llama-3.2-3b-instruct

Usage (Transformers)

from transformers import AutoModelForCausalLM, AutoTokenizer

repo_id = "qbz506/nyaya-llama-3b-stage0"
subfolder = "full/nyaya-llama-3b-stage0-merged"

model = AutoModelForCausalLM.from_pretrained(
    repo_id,
    subfolder=subfolder,
    torch_dtype="auto",
    device_map="auto",
)

tokenizer = AutoTokenizer.from_pretrained(
    repo_id,
    subfolder=subfolder,
    use_fast=True,
)

Usage (Ollama with GGUF)

Download nyaya-llama-3b-stage0-merged-q4.gguf, then:

cat > Modelfile <<EOM
FROM ./nyaya-llama-3b-stage0-merged-q4.gguf
SYSTEM """
You are a Nyaya reasoning engine. Follow the exact output format provided.
"""
PARAMETER temperature 0
PARAMETER top_p 1
EOM

ollama create nyaya-llama-3b-stage0-merged-q4 -f Modelfile
ollama run nyaya-llama-3b-stage0-merged-q4 "<your prompt>"

Prompting

Use the exact Nyaya section headers for best adherence:

## Samshaya (Doubt Analysis)
## Pramana (Sources of Knowledge)
## Pancha Avayava (5-Member Syllogism)
## Tarka (Counterfactual Reasoning)
## Hetvabhasa (Fallacy Check)
## Nirnaya (Ascertainment)

Intended use

This model is tuned for structured 6-phase Nyaya reasoning on logic-style problems. It is research-grade and optimized for format adherence over open-ended creativity.

Limitations

Responses may be verbose due to strict format.
Best results require the exact section headers and a system prompt.
Not evaluated for safety-critical domains. Paper: Pramana: Fine-Tuning Large Language Models for Epistemic Reasoning through Navya-Nyaya

Citations

If you use this model/dataset, please cite:

@misc{sathish2026pramanafinetuninglargelanguage,
      title={Pramana: Fine-Tuning Large Language Models for Epistemic Reasoning through Navya-Nyaya}, 
      author={Sharath Sathish},
      year={2026},
      eprint={2604.04937},
      archivePrefix={arXiv},
      primaryClass={cs.AI},
      url={https://arxiv.org/abs/2604.04937}, 
}

Downloads last month: 164

Safetensors

Model size

3B params

Tensor type

F16

Space using qbz506/nyaya-llama-3b-stage0-full 1

Paper for qbz506/nyaya-llama-3b-stage0-full

Pramana: Fine-Tuning Large Language Models for Epistemic Reasoning through Navya-Nyaya

Paper • 2604.04937 • Published Feb 14 • 1