Instructions to use tiny-random/lfm3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tiny-random/lfm3 with Transformers:

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

pipe = pipeline("text-generation", model="tiny-random/lfm3", trust_remote_code=True)
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("tiny-random/lfm3", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("tiny-random/lfm3", trust_remote_code=True, 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

vLLM

How to use tiny-random/lfm3 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "tiny-random/lfm3"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "tiny-random/lfm3",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/tiny-random/lfm3

SGLang

How to use tiny-random/lfm3 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 "tiny-random/lfm3" \
    --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": "tiny-random/lfm3",
		"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 "tiny-random/lfm3" \
        --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": "tiny-random/lfm3",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use tiny-random/lfm3 with Docker Model Runner:
```
docker model run hf.co/tiny-random/lfm3
```

lfm3 / .meta /create_model.py

yujiepan

Upload folder using huggingface_hub

f0e7fe0 verified 6 days ago

Raw History Blame Contribute Delete

2.41 kB

def create_model(source_model_id: str, source_revision: str, save_folder: str) -> str:
    import json
    from pathlib import Path

    import torch
    from huggingface_hub import hf_hub_download
    from transformers import AutoConfig, AutoModelForCausalLM, set_seed

    folder = Path(save_folder)
    folder.mkdir(parents=True, exist_ok=True)
    # LFM3 is not registered in the installed Transformers release; ship its pinned
    # remote code so the checkpoint loads without a newer package.
    for name in (
        "configuration_lfm3.py",
        "modeling_lfm3.py",
        "lfm3_conv.py",
        "chat_template.jinja",
        "generation_config.json",
        "special_tokens_map.json",
        "tokenizer.json",
        "tokenizer_config.json",
        "LICENSE",
    ):
        (folder / name).write_bytes(Path(hf_hub_download(source_model_id, name, revision=source_revision)).read_bytes())

    config = json.loads(Path(hf_hub_download(source_model_id, "config.json", revision=source_revision)).read_text())
    # Keep the two-conv prefix and two complete full/conv/sliding/conv cycles.
    # Match tiny-random/lfm2's residual/MLP widths; retain LFM3's 4:1 Q/KV ratio.
    config.update(
        hidden_size=64,
        intermediate_size=128,
        num_hidden_layers=10,
        num_attention_heads=4,
        num_key_value_heads=1,
        head_dim=32,
        max_position_embeddings=128000,
    )
    config["layer_types"] = config["layer_types"][:10]
    (folder / "config.json").write_text(json.dumps(config, indent=2) + "\n")

    set_seed(42)
    model = AutoModelForCausalLM.from_config(
        AutoConfig.from_pretrained(folder, trust_remote_code=True), trust_remote_code=True, dtype=torch.bfloat16
    )
    model.save_pretrained(folder)
    # `save_pretrained()` rewrites these two files with this environment's
    # versions; restore the pinned source bytes plus the deliberate config edits
    # so only the intended fields differ from the source.
    (folder / "config.json").write_text(json.dumps(config, indent=2) + "\n")
    (folder / "generation_config.json").write_bytes(
        Path(hf_hub_download(source_model_id, "generation_config.json", revision=source_revision)).read_bytes()
    )
    return str(model)


create_model(
    source_model_id="LiquidAI/LFM3-1.7B",
    source_revision="ac2586a34f1a1c03329dbdcdefabd8b6478ddaa7",
    save_folder="/tmp/lfm3",
)

	def create_model(source_model_id: str, source_revision: str, save_folder: str) -> str:
	import json
	from pathlib import Path

	import torch
	from huggingface_hub import hf_hub_download
	from transformers import AutoConfig, AutoModelForCausalLM, set_seed

	folder = Path(save_folder)
	folder.mkdir(parents=True, exist_ok=True)
	# LFM3 is not registered in the installed Transformers release; ship its pinned
	# remote code so the checkpoint loads without a newer package.
	for name in (
	"configuration_lfm3.py",
	"modeling_lfm3.py",
	"lfm3_conv.py",
	"chat_template.jinja",
	"generation_config.json",
	"special_tokens_map.json",
	"tokenizer.json",
	"tokenizer_config.json",
	"LICENSE",
	):
	(folder / name).write_bytes(Path(hf_hub_download(source_model_id, name, revision=source_revision)).read_bytes())

	config = json.loads(Path(hf_hub_download(source_model_id, "config.json", revision=source_revision)).read_text())
	# Keep the two-conv prefix and two complete full/conv/sliding/conv cycles.
	# Match tiny-random/lfm2's residual/MLP widths; retain LFM3's 4:1 Q/KV ratio.
	config.update(
	hidden_size=64,
	intermediate_size=128,
	num_hidden_layers=10,
	num_attention_heads=4,
	num_key_value_heads=1,
	head_dim=32,
	max_position_embeddings=128000,
	)
	config["layer_types"] = config["layer_types"][:10]
	(folder / "config.json").write_text(json.dumps(config, indent=2) + "\n")

	set_seed(42)
	model = AutoModelForCausalLM.from_config(
	AutoConfig.from_pretrained(folder, trust_remote_code=True), trust_remote_code=True, dtype=torch.bfloat16
	)
	model.save_pretrained(folder)
	# `save_pretrained()` rewrites these two files with this environment's
	# versions; restore the pinned source bytes plus the deliberate config edits
	# so only the intended fields differ from the source.
	(folder / "config.json").write_text(json.dumps(config, indent=2) + "\n")
	(folder / "generation_config.json").write_bytes(
	Path(hf_hub_download(source_model_id, "generation_config.json", revision=source_revision)).read_bytes()
	)
	return str(model)


	create_model(
	source_model_id="LiquidAI/LFM3-1.7B",
	source_revision="ac2586a34f1a1c03329dbdcdefabd8b6478ddaa7",
	save_folder="/tmp/lfm3",
	)