Instructions to use User01110/LFM-2.5-350M-MathMini with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use User01110/LFM-2.5-350M-MathMini with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="User01110/LFM-2.5-350M-MathMini") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoTokenizer, AutoModelForMultimodalLM tokenizer = AutoTokenizer.from_pretrained("User01110/LFM-2.5-350M-MathMini") model = AutoModelForMultimodalLM.from_pretrained("User01110/LFM-2.5-350M-MathMini") 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 Settings
- vLLM
How to use User01110/LFM-2.5-350M-MathMini with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "User01110/LFM-2.5-350M-MathMini" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "User01110/LFM-2.5-350M-MathMini", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/User01110/LFM-2.5-350M-MathMini
- SGLang
How to use User01110/LFM-2.5-350M-MathMini 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 "User01110/LFM-2.5-350M-MathMini" \ --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": "User01110/LFM-2.5-350M-MathMini", "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 "User01110/LFM-2.5-350M-MathMini" \ --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": "User01110/LFM-2.5-350M-MathMini", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use User01110/LFM-2.5-350M-MathMini with Docker Model Runner:
docker model run hf.co/User01110/LFM-2.5-350M-MathMini
File size: 2,553 Bytes
fbee9c9 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 | {{- bos_token -}}
{%- set keep_past_thinking = keep_past_thinking | default(false) -%}
{%- set ns = namespace(system_prompt="") -%}
{%- if messages[0]["role"] == "system" -%}
{%- set sys_content = messages[0]["content"] -%}
{%- if sys_content is not string -%}
{%- for item in sys_content -%}
{%- if item["type"] == "text" -%}
{%- set ns.system_prompt = ns.system_prompt + item["text"] -%}
{%- endif -%}
{%- endfor -%}
{%- else -%}
{%- set ns.system_prompt = sys_content -%}
{%- endif -%}
{%- set messages = messages[1:] -%}
{%- endif -%}
{%- if tools -%}
{%- set ns.system_prompt = ns.system_prompt + ("\n" if ns.system_prompt else "") + "List of tools: [" -%}
{%- for tool in tools -%}
{%- if tool is not string -%}
{%- set tool = tool | tojson -%}
{%- endif -%}
{%- set ns.system_prompt = ns.system_prompt + tool -%}
{%- if not loop.last -%}
{%- set ns.system_prompt = ns.system_prompt + ", " -%}
{%- endif -%}
{%- endfor -%}
{%- set ns.system_prompt = ns.system_prompt + "]" -%}
{%- endif -%}
{%- if ns.system_prompt -%}
{{- "<|im_start|>system\n" + ns.system_prompt + "<|im_end|>\n" -}}
{%- endif -%}
{%- set ns.last_assistant_index = -1 -%}
{%- for message in messages -%}
{%- if message["role"] == "assistant" -%}
{%- set ns.last_assistant_index = loop.index0 -%}
{%- endif -%}
{%- endfor -%}
{%- for message in messages -%}
{{- "<|im_start|>" + message["role"] + "\n" -}}
{%- set content = message["content"] -%}
{%- if content is not string -%}
{%- set ns.content = "" -%}
{%- for item in content -%}
{%- if item["type"] == "image" -%}
{%- set ns.content = ns.content + "<image>" -%}
{%- elif item["type"] == "text" -%}
{%- set ns.content = ns.content + item["text"] -%}
{%- else -%}
{%- set ns.content = ns.content + item | tojson -%}
{%- endif -%}
{%- endfor -%}
{%- set content = ns.content -%}
{%- endif -%}
{%- if message["role"] == "assistant" and not keep_past_thinking and loop.index0 != ns.last_assistant_index -%}
{%- if "</think>" in content -%}
{%- set content = content.split("</think>")[-1] | trim -%}
{%- endif -%}
{%- endif -%}
{{- content + "<|im_end|>\n" -}}
{%- endfor -%}
{%- if add_generation_prompt -%}
{{- "<|im_start|>assistant\n" -}}
{%- endif -%} |