Documentation Index
Fetch the complete documentation index at: /llms.txt
Use this file to discover all available pages before exploring further.
🚀 New: d1.1 — our latest hosted decision model, now on the Liquid API! Learn more →
350M parameter model for math problem solving
| Property | Value |
|---|---|
| Parameters | 350M |
| Context Length | 32K tokens |
| Task | Mathematical Reasoning |
| Language | English |
temperature=0.6, top_p=0.95, min_p=0.1, repetition_penalty=1.05. Do not use a system prompt. The model supports English only and is intended for single-turn conversations.pip install "transformers>=5.2.0" torch accelerate
from transformers import AutoTokenizer, AutoModelForCausalLM
model_id = "LiquidAI/LFM2-350M-Math"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto")
messages = [
{"role": "user", "content": "If a train travels at 60 mph for 2.5 hours, how far does it travel?"}
]
inputs = tokenizer.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt", return_dict=True).to(model.device)
outputs = model.generate(
**inputs,
max_new_tokens=4096,
do_sample=True,
temperature=0.6,
top_p=0.95,
min_p=0.1,
repetition_penalty=1.05,
)
response = tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:], skip_special_tokens=True)
print(response)
hf download LiquidAI/LFM2-350M-Math-GGUF \
--local-dir ./LFM2-350M-Math-GGUF
llama-cli -m ./LFM2-350M-Math-GGUF/LFM2-350M-Math-Q4_K_M.gguf \
-p "Solve: 2x + 5 = 15" \
-n 4096 \
--temp 0.6 --top-p 0.95 --min-p 0.1 --repeat-penalty 1.05
Was this page helpful?