Instructions to use notnotsamuel/LFM2.5-350M-RLCD with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use notnotsamuel/LFM2.5-350M-RLCD with Transformers:

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

pipe = pipeline("text-generation", model="notnotsamuel/LFM2.5-350M-RLCD")
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("notnotsamuel/LFM2.5-350M-RLCD")
model = AutoModelForCausalLM.from_pretrained("notnotsamuel/LFM2.5-350M-RLCD", 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 notnotsamuel/LFM2.5-350M-RLCD with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "notnotsamuel/LFM2.5-350M-RLCD"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "notnotsamuel/LFM2.5-350M-RLCD",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/notnotsamuel/LFM2.5-350M-RLCD

SGLang

How to use notnotsamuel/LFM2.5-350M-RLCD 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 "notnotsamuel/LFM2.5-350M-RLCD" \
    --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": "notnotsamuel/LFM2.5-350M-RLCD",
		"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 "notnotsamuel/LFM2.5-350M-RLCD" \
        --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": "notnotsamuel/LFM2.5-350M-RLCD",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use notnotsamuel/LFM2.5-350M-RLCD with Docker Model Runner:
```
docker model run hf.co/notnotsamuel/LFM2.5-350M-RLCD
```

LFM2.5-350M-RLCD / rlcd /stress_tasks.py

notnotsamuel

Release unchanged-weight LFM2.5 parallel constrained inference and benchmarks

a99edfc verified about 1 month ago

Raw History Blame Contribute Delete

1.07 kB

"""Synthetic scaling probes, reported separately from diagnostic accuracy."""
from .tasks import schema, enum, boolean

CASES = []
for cardinality in [64, 255]:
    choices = [f"tariff_{i:03d}" for i in range(cardinality)]
    s = schema(tariff=enum("Copy the exact tariff code in the text", *choices))
    CASES.append((f"enum-{cardinality}", s, f"The assigned tariff code is {choices[-2]}.", {"tariff": choices[-2]}))
for count in [12, 28]:
    fields = {f"flag_{i:02d}": boolean(f"True if item {i:02d} is enabled; false if disabled") for i in range(count)}
    expected = {name: i % 2 == 0 for i, name in enumerate(fields)}
    context = "\n".join(f"Item {i:02d} is {'enabled' if i % 2 == 0 else 'disabled'}." for i in range(count))
    CASES.append((f"fields-{count}", schema(**fields), context, expected))
s = schema(signal=enum("Copy the final signal color", "red", "green", "blue"))
context = "Archive entries follow.\n" + "An old record was checked and filed.\n" * 160 + "\nFinal signal color: blue."
CASES.append(("long-context", s, context, {"signal":"blue"}))

	"""Synthetic scaling probes, reported separately from diagnostic accuracy."""
	from .tasks import schema, enum, boolean

	CASES = []
	for cardinality in [64, 255]:
	choices = [f"tariff_{i:03d}" for i in range(cardinality)]
	s = schema(tariff=enum("Copy the exact tariff code in the text", *choices))
	CASES.append((f"enum-{cardinality}", s, f"The assigned tariff code is {choices[-2]}.", {"tariff": choices[-2]}))
	for count in [12, 28]:
	fields = {f"flag_{i:02d}": boolean(f"True if item {i:02d} is enabled; false if disabled") for i in range(count)}
	expected = {name: i % 2 == 0 for i, name in enumerate(fields)}
	context = "\n".join(f"Item {i:02d} is {'enabled' if i % 2 == 0 else 'disabled'}." for i in range(count))
	CASES.append((f"fields-{count}", schema(**fields), context, expected))
	s = schema(signal=enum("Copy the final signal color", "red", "green", "blue"))
	context = "Archive entries follow.\n" + "An old record was checked and filed.\n" * 160 + "\nFinal signal color: blue."
	CASES.append(("long-context", s, context, {"signal":"blue"}))