Documentation Index
Fetch the complete documentation index at: /llms.txt
Use this file to discover all available pages before exploring further.
🚀 New: LFM2.5-VL-3B — our most capable vision-language model is now available! Learn more →
8B parameter Mixture-of-Experts model with 1.5B active parameters for fast, reliable tool calling and 128K context
| Property | Value |
|---|---|
| Parameters | 8B (1.5B active) |
| Context Length | 128K tokens |
| Architecture | LFM2.5 (MoE) |
transformers>=5.0.0):from transformers import AutoModelForCausalLM, AutoTokenizer, TextStreamer
model_id = "LiquidAI/LFM2.5-8B-A1B"
model = AutoModelForCausalLM.from_pretrained(
model_id,
device_map="auto",
dtype="bfloat16",
# attn_implementation="flash_attention_2" <- uncomment on compatible GPU
)
tokenizer = AutoTokenizer.from_pretrained(model_id)
streamer = TextStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True)
prompt = "What is C. elegans?"
input_ids = tokenizer.apply_chat_template(
[{"role": "user", "content": prompt}],
add_generation_prompt=True,
return_tensors="pt",
tokenize=True,
).to(model.device)
output = model.generate(
input_ids,
do_sample=True,
temperature=0.2,
top_k=80,
repetition_penalty=1.05,
max_new_tokens=8192,
streamer=streamer,
)
Was this page helpful?