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
```

limloop commited on 2 days ago

Commit

1d19382

1 Parent(s): aa545c0

update model files

Browse files

Files changed (4) hide show

chat_template.jinja +4 -0
config.json +1 -1
generation_config.json +1 -1
tokenizer_config.json +1 -2

chat_template.jinja ADDED Viewed

	@@ -0,0 +1,4 @@

+{% for message in messages %}
+    {{"<|im_start|>" + message['role'] + "
+" + message['content'] + "<|im_end|>"}}
+    {% endfor %}

config.json CHANGED Viewed

@@ -33,7 +33,7 @@
   "time_step_min": 0.001,
   "time_step_rank": 32,
   "torch_dtype": "float32",
-  "transformers_version": "4.51.3",
   "use_bias": false,
   "use_cache": true,
   "use_conv_bias": true,

   "time_step_min": 0.001,
   "time_step_rank": 32,
   "torch_dtype": "float32",
+  "transformers_version": "4.54.1",
   "use_bias": false,
   "use_cache": true,
   "use_conv_bias": true,

generation_config.json CHANGED Viewed

@@ -3,5 +3,5 @@
   "bos_token_id": 6,
   "eos_token_id": 6,
   "pad_token_id": 7,
-  "transformers_version": "4.51.3"
 }

   "bos_token_id": 6,
   "eos_token_id": 6,
   "pad_token_id": 7,
+  "transformers_version": "4.54.1"
 }

tokenizer_config.json CHANGED Viewed

@@ -157,12 +157,11 @@
     "<|reserved_8|>"
   ],
   "bos_token": "<|endoftext|>",
-  "chat_template": "{% for message in messages %}\n    {{\"<|im_start|>\" + message['role'] + \"\n\" + message['content'] + \"<|im_end|>\"}}\n    {% endfor %}",
   "clean_up_tokenization_spaces": false,
   "eos_token": "<|endoftext|>",
   "extra_special_tokens": {},
   "mask_token": "<|mask|>",
   "model_max_length": 32768,
   "pad_token": "<|padding|>",
-  "tokenizer_class": "PreTrainedTokenizer"
 }

     "<|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"
 }