Instructions to use limloop/whiff-mamba2-20M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use limloop/whiff-mamba2-20M with Transformers:

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

pipe = pipeline("text-generation", model="limloop/whiff-mamba2-20M")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("limloop/whiff-mamba2-20M")
model = AutoModelForCausalLM.from_pretrained("limloop/whiff-mamba2-20M", 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 limloop/whiff-mamba2-20M with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "limloop/whiff-mamba2-20M"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "limloop/whiff-mamba2-20M",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/limloop/whiff-mamba2-20M

SGLang

How to use limloop/whiff-mamba2-20M 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 "limloop/whiff-mamba2-20M" \
    --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": "limloop/whiff-mamba2-20M",
		"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 "limloop/whiff-mamba2-20M" \
        --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": "limloop/whiff-mamba2-20M",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use limloop/whiff-mamba2-20M with Docker Model Runner:
```
docker model run hf.co/limloop/whiff-mamba2-20M
```

whiff-mamba2-20M / tokenizer_config.json

limloop

update model files

1d19382 2 days ago

Raw

History Blame Contribute Delete

3.66 kB

	{
	"added_tokens_decoder": {
	"0": {
	"content": "<\|im_start\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"1": {
	"content": "<\|im_end\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"2": {
	"content": "<\|system\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"3": {
	"content": "<\|user\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"4": {
	"content": "<\|assistant\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"5": {
	"content": "<\|function\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"6": {
	"content": "<\|endoftext\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"7": {
	"content": "<\|padding\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"8": {
	"content": "<\|mask\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"9": {
	"content": "<\|reserved_1\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"10": {
	"content": "<\|reserved_2\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"11": {
	"content": "<\|reserved_3\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"12": {
	"content": "<\|reserved_4\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"13": {
	"content": "<\|reserved_5\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"14": {
	"content": "<\|reserved_6\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"15": {
	"content": "<\|reserved_7\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"16": {
	"content": "<\|reserved_8\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	}
	},
	"additional_special_tokens": [
	"<\|im_start\|>",
	"<\|im_end\|>",
	"<\|system\|>",
	"<\|user\|>",
	"<\|assistant\|>",
	"<\|function\|>",
	"<\|endoftext\|>",
	"<\|padding\|>",
	"<\|mask\|>",
	"<\|reserved_1\|>",
	"<\|reserved_2\|>",
	"<\|reserved_3\|>",
	"<\|reserved_4\|>",
	"<\|reserved_5\|>",
	"<\|reserved_6\|>",
	"<\|reserved_7\|>",
	"<\|reserved_8\|>"
	],
	"bos_token": "<\|endoftext\|>",
	"clean_up_tokenization_spaces": false,
	"eos_token": "<\|endoftext\|>",
	"extra_special_tokens": {},
	"mask_token": "<\|mask\|>",
	"model_max_length": 32768,
	"pad_token": "<\|padding\|>",
	"tokenizer_class": "PreTrainedTokenizerFast"
	}