Instructions to use Haamipromax/HamAI-Science-1b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use Haamipromax/HamAI-Science-1b 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 Haamipromax/HamAI-Science-1b
# Run inference directly in the terminal:
llama cli -hf Haamipromax/HamAI-Science-1b

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Haamipromax/HamAI-Science-1b
# Run inference directly in the terminal:
llama cli -hf Haamipromax/HamAI-Science-1b

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 Haamipromax/HamAI-Science-1b
# Run inference directly in the terminal:
./llama-cli -hf Haamipromax/HamAI-Science-1b

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 Haamipromax/HamAI-Science-1b
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Haamipromax/HamAI-Science-1b

Use Docker

docker model run hf.co/Haamipromax/HamAI-Science-1b

LM Studio
Jan

vLLM

How to use Haamipromax/HamAI-Science-1b with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Haamipromax/HamAI-Science-1b

Ollama
How to use Haamipromax/HamAI-Science-1b with Ollama:
```
ollama run hf.co/Haamipromax/HamAI-Science-1b
```

Unsloth Studio

How to use Haamipromax/HamAI-Science-1b 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 Haamipromax/HamAI-Science-1b 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 Haamipromax/HamAI-Science-1b to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Haamipromax/HamAI-Science-1b to start chatting

Docker Model Runner
How to use Haamipromax/HamAI-Science-1b with Docker Model Runner:
```
docker model run hf.co/Haamipromax/HamAI-Science-1b
```

Lemonade

How to use Haamipromax/HamAI-Science-1b with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Haamipromax/HamAI-Science-1b

Run and chat with the model

lemonade run user.HamAI-Science-1b-{{QUANT_TAG}}

List all available models

lemonade list

Atomic Chat

HamAI Science Model

A lightweight language model designed to answer science questions clearly and accurately in English.

Overview

HamAI Science Model is trained and fine-tuned on science question–answer datasets. It is built to provide straightforward explanations across topics like physics, chemistry, and biology.

Features

Focused on science Q&A
Clear and simple English answers
Lightweight and efficient
Suitable for educational use

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "Haamipromax/HamAI-Science-1b"

tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name)

input_text = "Explain how quantum entanglement violates classical locality."
inputs = tokenizer(input_text, return_tensors="pt")

outputs = model.generate(**inputs, max_new_tokens=100)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Training Data

The model was trained on a mix of science question–answer datasets, including:

General science questions
Educational textbooks
Scientific materials

Limitations

May produce incorrect answers outside science topics
Not suitable for advanced research-level questions

Intended Use

Students learning science
Simple question answering systems
Educational tools and assistants

License

Apache-2.0

Downloads last month: 220

Safetensors

Model size

1B params

Tensor type

F16

Model tree for Haamipromax/HamAI-Science-1b

Base model

TinyLlama/TinyLlama-1.1B-Chat-v1.0

Quantized

(150)

this model

Quantizations

1 model