Instructions to use nkthebass/tinybrainbot-320mV2-math with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use nkthebass/tinybrainbot-320mV2-math with Transformers:

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

pipe = pipeline("text-generation", model="nkthebass/tinybrainbot-320mV2-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-320mV2-math")
model = AutoModelForCausalLM.from_pretrained("nkthebass/tinybrainbot-320mV2-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-320mV2-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-320mV2-math:F16
# Run inference directly in the terminal:
llama cli -hf nkthebass/tinybrainbot-320mV2-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-320mV2-math:F16
# Run inference directly in the terminal:
llama cli -hf nkthebass/tinybrainbot-320mV2-math:F16

Build from source code

git clone https://github.com/ggml-org/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-app
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama serve -hf nkthebass/tinybrainbot-320mV2-math:F16
# Run inference directly in the terminal:
./build/bin/llama cli -hf nkthebass/tinybrainbot-320mV2-math:F16

Use Docker

docker model run hf.co/nkthebass/tinybrainbot-320mV2-math:F16

Llama new
LM Studio
Jan

vLLM

How to use nkthebass/tinybrainbot-320mV2-math with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "nkthebass/tinybrainbot-320mV2-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-320mV2-math",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/nkthebass/tinybrainbot-320mV2-math:F16

SGLang

How to use nkthebass/tinybrainbot-320mV2-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-320mV2-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-320mV2-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-320mV2-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-320mV2-math",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use nkthebass/tinybrainbot-320mV2-math with Ollama:
```
ollama run hf.co/nkthebass/tinybrainbot-320mV2-math:F16
```
Unsloth Desktop
Docker Model Runner
How to use nkthebass/tinybrainbot-320mV2-math with Docker Model Runner:
```
docker model run hf.co/nkthebass/tinybrainbot-320mV2-math:F16
```

Lemonade

How to use nkthebass/tinybrainbot-320mV2-math with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull nkthebass/tinybrainbot-320mV2-math:F16

Run and chat with the model

lemonade run user.tinybrainbot-320mV2-math-F16

List all available models

lemonade list

Atomic Chat

nkthebass commited on Aug 10

Commit

9e7a2ce

verified ·

1 Parent(s): cca49d1

Card: document GGUF add_space_prefix=false + leading-space template fix (#23840)

Browse files

Files changed (1) hide show

README.md +3 -1

README.md CHANGED Viewed

@@ -95,7 +95,9 @@ ids = tok.apply_chat_template([{"role":"user","content":"A theater has 56 rows w
                               add_generation_prompt=True, return_tensors="pt")
 print(tok.decode(m.generate(ids, max_new_tokens=256, do_sample=False)[0][ids.shape[1]:], skip_special_tokens=True))
 ```
-GGUF file (`*-F16.gguf`) works directly in LM Studio / Ollama / llama.cpp.
 ### Prompting tips

                               add_generation_prompt=True, return_tensors="pt")
 print(tok.decode(m.generate(ids, max_new_tokens=256, do_sample=False)[0][ids.shape[1]:], skip_special_tokens=True))
 ```
+GGUF file (`*-F16.gguf`) works directly in LM Studio / Ollama / llama.cpp — use the model's built-in chat template as-is.
+> **GGUF tokenization fix (this release):** the F16 GGUF now sets `tokenizer.ggml.add_space_prefix=false` and ships a **leading-space chat template**, so llama.cpp tokenizes the chat format **token-for-token identically to the native SentencePiece tokenizer**. This fixes a prior export mismatch (llama.cpp [#23840](https://github.com/ggml-org/llama.cpp/issues/23840): the default `add_space_prefix=true` injects phantom `▁` around special tokens) that garbled arithmetic in GGUF apps. Multi-digit **add/subtract now compute correctly in-app** (e.g. `56321 − 28479 → 27842`). Note: multiplication is the model's **fp16-precision soft spot** — it's stronger in fp32 than at the fp16 the GGUF runs — so hard multiplies can still miss.
 ### Prompting tips