Instructions to use AyoubChLin/lfm2.5-2.6b-fable5-coding-agent with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use AyoubChLin/lfm2.5-2.6b-fable5-coding-agent with Transformers:

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

pipe = pipeline("text-generation", model="AyoubChLin/lfm2.5-2.6b-fable5-coding-agent")
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("AyoubChLin/lfm2.5-2.6b-fable5-coding-agent")
model = AutoModelForCausalLM.from_pretrained("AyoubChLin/lfm2.5-2.6b-fable5-coding-agent", 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 AyoubChLin/lfm2.5-2.6b-fable5-coding-agent with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "AyoubChLin/lfm2.5-2.6b-fable5-coding-agent"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "AyoubChLin/lfm2.5-2.6b-fable5-coding-agent",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/AyoubChLin/lfm2.5-2.6b-fable5-coding-agent

SGLang

How to use AyoubChLin/lfm2.5-2.6b-fable5-coding-agent 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 "AyoubChLin/lfm2.5-2.6b-fable5-coding-agent" \
    --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": "AyoubChLin/lfm2.5-2.6b-fable5-coding-agent",
		"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 "AyoubChLin/lfm2.5-2.6b-fable5-coding-agent" \
        --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": "AyoubChLin/lfm2.5-2.6b-fable5-coding-agent",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use AyoubChLin/lfm2.5-2.6b-fable5-coding-agent with Docker Model Runner:
```
docker model run hf.co/AyoubChLin/lfm2.5-2.6b-fable5-coding-agent
```

LFM2.5 2.6B Fable5 T4 Inference

by AyoubChLin - opened Aug 16

Discussion

AyoubChLin

Owner Aug 16

•

edited Aug 16

LFM2.5 2.6B Fable5 — T4 Inference 🚀

I've added a Kaggle inference notebook so you can easily test LFM2.5 2.6B Fable5 on a Tesla T4 GPU without setting up the environment locally.

The notebook includes the complete inference setup and lets you run the model directly on Kaggle.

🔗 Kaggle Notebook: https://www.kaggle.com/code/ayoubcherguelaine/lfm2-5-2-6b-fable5-t4-inference

Feel free to try it, benchmark it, and share your results or feedback with the community! 🤗

#LFM2 #Fable5 #HuggingFace #Kaggle #LLM #AI #Inference #T4 #CodingAgent

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment