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

Libraries

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

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("nkthebass/tinybrainbot-100m-v3-instruct")
model = AutoModelForCausalLM.from_pretrained("nkthebass/tinybrainbot-100m-v3-instruct", 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

llama.cpp

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

Use Docker

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

LM Studio
Jan

vLLM

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

Use Docker

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

SGLang

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

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

Lemonade

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

Pull the model

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

Run and chat with the model

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

List all available models

lemonade list

Atomic Chat

TinyBrainBot-100M-v3-Instruct

A 100M-parameter chat/instruct model that beats SupraLabs/Supra2-100M-Instruct on 6/7 benchmarks on the official EleutherAI LM-Eval Harness — and actually converses.

Built by SFT from tinybrainbot-100m-v3-base (chat / instruction-following / recall data), then a WiSE-FT weight soup (α=0.7 interpolation back toward the base) to recover benchmark accuracy while keeping chat.

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	Δ
ARC-Easy	54.5	44.4	+10.1
ARC-Challenge	29.2	24.7	+4.5
OpenBookQA	32.8	30.4	+2.4
PIQA	65.5	64.4	+1.1
WinoGrande	51.4	50.5	+0.9
MMLU	26.1	25.8	+0.3
HellaSwag	32.8	35.9	−3.1

6/7 vs Supra2-Instruct — only HellaSwag lost.

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-instruct,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.

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer
tok = AutoTokenizer.from_pretrained("nkthebass/tinybrainbot-100m-v3-instruct")
model = AutoModelForCausalLM.from_pretrained("nkthebass/tinybrainbot-100m-v3-instruct")
prompt = "<|user|>\nWhat is the capital of France?\n<|end|>\n<|assistant|>\n"
ids = tok(prompt, return_tensors="pt").input_ids
print(tok.decode(model.generate(ids, max_new_tokens=40)[0][ids.shape[1]:], skip_special_tokens=True))
# -> "Paris."

GGUF

An F16 GGUF is included (tinybrainbot-100m-v3-instruct-f16.gguf) for llama.cpp / Ollama / LM Studio, with the add_space_prefix=false + leading-space chat template baked in so it chats faithfully out of the box.

Limitations

Coherent for short chat and 1–2 sentence answers; longer generations can confabulate (the 100M ceiling on factual generation). Arithmetic is unreliable — use tinybrainbot-100m-v3-math. Not safety-tuned.

Downloads last month: 503

Safetensors

Model size

0.1B params

Tensor type

F16