LFM2.5 is a new family of hybrid models designed for on-device deployment.

tools 1.2b

ollama run tomng/lfm2.5-instruct:1.2b-q4_K_M

curl http://localhost:11434/api/chat \
  -d '{
    "model": "tomng/lfm2.5-instruct:1.2b-q4_K_M",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='tomng/lfm2.5-instruct:1.2b-q4_K_M',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'tomng/lfm2.5-instruct:1.2b-q4_K_M',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Details

Updated 1 month ago

1 month ago

3b9647debdd4 · 731MB ·

model

archlfm2

parameters1.17B

quantizationQ4_K_M

731MB

license

LICENSE TEXT LFM Open License v1.0 TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION 1. D

11kB

params

{ "repeat_penalty": 1.05, "stop": [ "<|im_start|>", "<|im_end|>" ],

122B

template

{{ if .System }}<|im_start|>system {{ .System }}<|im_end|> {{ end }}{{ if .Prompt }}<|im_start|>user

182B

Readme

Created from GGUF model with the correct PARSER to avoid being identified as thinking model

Documentation • LEAP

LFM2.5-1.2B-Instruct

LFM2.5 is a new family of hybrid models designed for on-device deployment. It builds on the LFM2 architecture with extended pre-training and reinforcement learning.

Find more details in the original model card: https://huggingface.co/LiquidAI/LFM2.5-1.2B-Instruct