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)

# 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=40)
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

File size: 1,841 Bytes

a99edfc
 
 
 
 
 
deb589d
 
 
 
 
a99edfc
 
 
deb589d
a99edfc
 
 
 
 
 
 
 
 
 
 
 
deb589d
 
a99edfc

"""Assemble a local release directory. Deliberately has no network/upload code."""
import hashlib
import json
import shutil
from pathlib import Path

def file_sha256(path):
    with path.open("rb") as source:
        return hashlib.file_digest(source, "sha256").hexdigest()


root = Path(__file__).resolve().parents[1]
destination = root / "release" / "notnotsamuel" / "LFM2.5-350M-RLCD"
destination.mkdir(parents=True, exist_ok=True)
files = [root / f for f in ["README.md", "LICENSE", "LICENSE-CODE", "requirements.txt", "modal_benchmark.py", ".gitignore", "BASE_MODEL_MANIFEST.json", "model.safetensors", "config.json", "generation_config.json", "tokenizer.json", "tokenizer_config.json", "chat_template.jinja"]]
for directory in ["rlcd", "tests", "scripts", "docs"]:
    files.extend(p for p in (root / directory).rglob("*") if p.is_file() and "__pycache__" not in p.parts)
files.extend((root / "results").glob("*.json"))
files.extend(root / "results" / f for f in ["REPORT.md", "local-tests.log", "environment-macos.txt"])
files.extend((root / "results" / "exploratory").glob("*.json"))
for source in files:
    relative = source.relative_to(root)
    target = destination / relative
    target.parent.mkdir(parents=True, exist_ok=True)
    shutil.copy2(source, target)
manifest = {"target_repository": "notnotsamuel/LFM2.5-350M-RLCD", "status": "release",
            "base_model": "LiquidAI/LFM2.5-350M", "base_revision": "9e6c6ccf47cd318696e137d381a7ded8fe4df09f",
            "contains_weights": True, "weights_modified": False, "training_performed": False,
            "files_sha256": {str(p.relative_to(root)):file_sha256(p) for p in sorted(files)}}
(destination / "RELEASE_MANIFEST.json").write_text(json.dumps(manifest, indent=2) + "\n")
print(destination)
print(f"Prepared {len(files)} files; no network operation performed.")