Instructions to use ShubhamGTiwari/Tina-3.1-8B-Reasoning with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ShubhamGTiwari/Tina-3.1-8B-Reasoning with Transformers:

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

pipe = pipeline("text-generation", model="ShubhamGTiwari/Tina-3.1-8B-Reasoning")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ShubhamGTiwari/Tina-3.1-8B-Reasoning")
model = AutoModelForCausalLM.from_pretrained("ShubhamGTiwari/Tina-3.1-8B-Reasoning", 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]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use ShubhamGTiwari/Tina-3.1-8B-Reasoning with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ShubhamGTiwari/Tina-3.1-8B-Reasoning"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ShubhamGTiwari/Tina-3.1-8B-Reasoning",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ShubhamGTiwari/Tina-3.1-8B-Reasoning

SGLang

How to use ShubhamGTiwari/Tina-3.1-8B-Reasoning 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 "ShubhamGTiwari/Tina-3.1-8B-Reasoning" \
    --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": "ShubhamGTiwari/Tina-3.1-8B-Reasoning",
		"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 "ShubhamGTiwari/Tina-3.1-8B-Reasoning" \
        --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": "ShubhamGTiwari/Tina-3.1-8B-Reasoning",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Studio

How to use ShubhamGTiwari/Tina-3.1-8B-Reasoning 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 ShubhamGTiwari/Tina-3.1-8B-Reasoning 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 ShubhamGTiwari/Tina-3.1-8B-Reasoning to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for ShubhamGTiwari/Tina-3.1-8B-Reasoning to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="ShubhamGTiwari/Tina-3.1-8B-Reasoning",
    max_seq_length=2048,
)

Docker Model Runner
How to use ShubhamGTiwari/Tina-3.1-8B-Reasoning with Docker Model Runner:
```
docker model run hf.co/ShubhamGTiwari/Tina-3.1-8B-Reasoning
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Tina-3.1-8B-Reasoning

Tina-3.1-8B-Reasoning is a fine-tuned version of Llama 3.1 8B, optimized for complex reasoning, tool usage, and agentic workflows. It serves as the primary intelligence for multi-agent systems using the Agent-to-Agent (A2A) protocol.

🚀 Quantized Versions

For faster inference and lower VRAM usage, please use the following GGUF versions provided by the community:

GGUF (Imatrix & Static): mradermacher/Tina-3.1-8B-Reasoning-GGUF

Model Details

Model Description

This model is a 16-bit implementation verified for agentic orchestration. It is designed to act as a "Purchasing Concierge" brain, capable of managing specialized agents.

Developed by: Shubham Tiwari
Model type: LLM Fine-tune (Reasoning/Agentic)
Language(s): English
Finetuned from model: meta-llama/Llama-3.1-8B-Instruct
Training Framework: Unsloth

Uses

Direct Use

Ideal for:

Complex reasoning tasks.
Multi-agent orchestration (CrewAI, LangGraph).
Tool-calling and API interaction.

Hardware Compatibility

Tested on AMD Instinct™ GPUs and compatible with Google Agent Development Kit (ADK). The GGUF versions allow this model to run on consumer hardware (MacBooks, NVIDIA RTX GPUs) via LM Studio or Ollama.