Instructions to use LiquidAI/LFM2.5-1.2B-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use LiquidAI/LFM2.5-1.2B-Instruct with Transformers:

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

pipe = pipeline("text-generation", model="LiquidAI/LFM2.5-1.2B-Instruct")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("LiquidAI/LFM2.5-1.2B-Instruct")
model = AutoModelForCausalLM.from_pretrained("LiquidAI/LFM2.5-1.2B-Instruct")
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

vLLM

How to use LiquidAI/LFM2.5-1.2B-Instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "LiquidAI/LFM2.5-1.2B-Instruct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "LiquidAI/LFM2.5-1.2B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/LiquidAI/LFM2.5-1.2B-Instruct

SGLang

How to use LiquidAI/LFM2.5-1.2B-Instruct 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 "LiquidAI/LFM2.5-1.2B-Instruct" \
    --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": "LiquidAI/LFM2.5-1.2B-Instruct",
		"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 "LiquidAI/LFM2.5-1.2B-Instruct" \
        --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": "LiquidAI/LFM2.5-1.2B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use LiquidAI/LFM2.5-1.2B-Instruct with Docker Model Runner:
```
docker model run hf.co/LiquidAI/LFM2.5-1.2B-Instruct
```

fine tuning instruct model

#13

by elenapop - opened Feb 25

Discussion

elenapop

Feb 25

•

edited Feb 25

I'm fine-tuning LFM2.5-1.2B-Instruct with a strict output format requirement.
The model must output responses following a specific [[ ## field ## ]] structure with nested fields like [[ ## answer ## ]], [[ ## confidence ## ]], [[ ## references ## ]], etc.
After fine-tuning, the model completely ignores the format and outputs random JSON structures, hallucinated fields, and sometimes responds in english instead of french.

Dataset:
56,000 training examples
Format: prompt-completion pairs ({
"prompt": "SYSTEM + USER combined into one string, ending with <|im_start|>assistant\n",
"completion": "ONLY the assistant response"
})
Training method: completion-only loss (TRL's completion_only_loss=True)

Attempts made:
Original approach: Full system prompt (17,089 chars, ~4,405 tokens)
Result: Training very slow (150-170 sec/step)
Model output: Completely broken, random JSON, hallucinations

Condensed system prompt: Reduced to 1,762 chars ~440 tokens, 90% reduction

Result: Training 2x faster (~70 sec/step)
Model output: Still broken, same issues

16k token filtering: Only trained on examples <16k tokens (21,409 examples, 38% of data)
Result: Training 4x faster overall (~38-45 sec/step)
Model output: Still broken, model doesn't follow format at all

Training config:
Base model: unsloth/LFM2.5-1.2B-Instruct
Max seq length: 32,768 (reduced to 16,384 for test)
LoRA: r=16, alpha=16
Batch size: 1, gradient accumulation: 16
Learning rate: 5e-5, 1 epoch
Completion-only loss: enabled

Example broken outputs:
Outputs {"## today ##": "...", "## user_context ##": {}} instead of proper format
Hallucinates fields like "decision number", "date of decision"
Ignores required [[ ## field ## ]] markers entirely
Sometimes outputs in English instead of French

Question: Is LFM2.5-1.2B-Instruct known to struggle with complex structured outputs? and can you provide a solution to this issue?

mlabonne

Liquid AI org Feb 25

No, it should be easy to fine-tune. It looks like a training-related issue with your specific configuration, but hard to say based on this.

I can recommend trying https://huggingface.co/LiquidAI/LFM2.5-1.2B-Base to double-check. If you still have broken outputs, it means there's an error with your setup.

elenapop

Mar 2

Alright, so even though i have a huge system prompt its no problem...
I will attempt the base model as you mentioned and will come back with a feedback.

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