Instructions to use nkthebass/tinybrainbot-100m-v3-math with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use nkthebass/tinybrainbot-100m-v3-math with Transformers:

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

pipe = pipeline("text-generation", model="nkthebass/tinybrainbot-100m-v3-math")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("nkthebass/tinybrainbot-100m-v3-math")
model = AutoModelForCausalLM.from_pretrained("nkthebass/tinybrainbot-100m-v3-math", 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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use nkthebass/tinybrainbot-100m-v3-math 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 nkthebass/tinybrainbot-100m-v3-math:F16
# Run inference directly in the terminal:
llama cli -hf nkthebass/tinybrainbot-100m-v3-math:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf nkthebass/tinybrainbot-100m-v3-math:F16
# Run inference directly in the terminal:
llama cli -hf nkthebass/tinybrainbot-100m-v3-math:F16

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 nkthebass/tinybrainbot-100m-v3-math:F16
# Run inference directly in the terminal:
./llama-cli -hf nkthebass/tinybrainbot-100m-v3-math:F16

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 nkthebass/tinybrainbot-100m-v3-math:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf nkthebass/tinybrainbot-100m-v3-math:F16

Use Docker

docker model run hf.co/nkthebass/tinybrainbot-100m-v3-math:F16

LM Studio
Jan

vLLM

How to use nkthebass/tinybrainbot-100m-v3-math with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "nkthebass/tinybrainbot-100m-v3-math"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "nkthebass/tinybrainbot-100m-v3-math",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/nkthebass/tinybrainbot-100m-v3-math:F16

SGLang

How to use nkthebass/tinybrainbot-100m-v3-math 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 "nkthebass/tinybrainbot-100m-v3-math" \
    --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": "nkthebass/tinybrainbot-100m-v3-math",
		"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 "nkthebass/tinybrainbot-100m-v3-math" \
        --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": "nkthebass/tinybrainbot-100m-v3-math",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use nkthebass/tinybrainbot-100m-v3-math with Ollama:
```
ollama run hf.co/nkthebass/tinybrainbot-100m-v3-math:F16
```
Unsloth Desktop
Docker Model Runner
How to use nkthebass/tinybrainbot-100m-v3-math with Docker Model Runner:
```
docker model run hf.co/nkthebass/tinybrainbot-100m-v3-math:F16
```

Lemonade

How to use nkthebass/tinybrainbot-100m-v3-math with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull nkthebass/tinybrainbot-100m-v3-math:F16

Run and chat with the model

lemonade run user.tinybrainbot-100m-v3-math-F16

List all available models

lemonade list

Atomic Chat

TinyBrainBot-100M-v3-Math

A 100M-parameter math/reasoning specialist, SFT'd from tinybrainbot-100m-v3-base on a math-heavy diet (order-of-operations, word problems, chain-of-thought). Beats Supra2-100M-Instruct on 5/7 benchmarks on the official EleutherAI LM-Eval Harness.

Architecture: Llama-compatible, 100.1M params (768/12L/12h·4kv, ctx 1024, vocab 32k).
Chat template: <|user|>\n{msg}\n<|end|>\n<|assistant|>\n

Benchmarks (EleutherAI lm-eval, 0-shot, acc_norm; WinoGrande/MMLU = acc)

Benchmark	This model	Supra2-100M-Instruct
ARC-Easy	53.7	44.4
ARC-Easy (raw acc)	57.5	51.4
ARC-Challenge	29.0	24.7
ARC-Challenge (raw acc)	26.4	22.7
OpenBookQA	32.0	30.4
OpenBookQA (raw acc)	21.2	17.2
PIQA	65.7	64.4
PIQA (raw acc)	65.5	64.3
WinoGrande	50.9	50.5
HellaSwag	33.3	35.9
HellaSwag (raw acc)	30.3	31.5
MMLU	25.7	25.8

Reproduce these numbers

EleutherAI lm-eval-harness v0.4.12, 0-shot, on the HF repo (not the GGUF — llama.cpp's --multiple-choice path under-reports these tasks):

lm_eval --model hf \
  --model_args pretrained=nkthebass/tinybrainbot-100m-v3-math,dtype=float32 \
  --tasks hellaswag,arc_easy,arc_challenge,openbookqa,winogrande,piqa,mmlu \
  --num_fewshot 0 --batch_size 32

Metrics: acc_norm for HellaSwag / ARC / OpenBookQA / PIQA; acc for WinoGrande & MMLU.

What it does

✅ Order-of-operations: correct — e.g. What is 12 + 7 * 3? → "First: 7×3=21, then 12+21 = 33." (the base and general instruct both get this wrong.)
✅ Reasoning: strongest ARC-Challenge of the family.
⚠️ Word problems: attempts chain-of-thought but multi-step arithmetic is unreliable (100M ceiling).
⚠️ Not conversational — it specialized toward math; use tinybrainbot-100m-v3-instruct to chat.

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer
tok = AutoTokenizer.from_pretrained("nkthebass/tinybrainbot-100m-v3-math")
model = AutoModelForCausalLM.from_pretrained("nkthebass/tinybrainbot-100m-v3-math")
prompt = "<|user|>\nWhat is 12 + 7 * 3?\n<|end|>\n<|assistant|>\n"
ids = tok(prompt, return_tensors="pt").input_ids
print(tok.decode(model.generate(ids, max_new_tokens=60)[0][ids.shape[1]:], skip_special_tokens=True))

GGUF

An F16 GGUF is included (tinybrainbot-100m-v3-math-f16.gguf) for llama.cpp / Ollama / LM Studio, with the add_space_prefix=false + leading-space chat template baked in — order-of-operations works faithfully from the GGUF.

Not safety-tuned.

Downloads last month: 400

Safetensors

Model size

0.1B params

Tensor type

F16

Collection including nkthebass/tinybrainbot-100m-v3-math

TinyBrainBot v3

Collection

Third generation: 100M and 350M base, instruct and math models. • 6 items • Updated 8 days ago