Instructions to use User01110/LFM-2.5-350M-MathMini with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

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
```

User01110 commited on 5 days ago

Commit

12d4fdc

verified ·

1 Parent(s): fbee9c9

Update README.md

Browse files

Files changed (1) hide show

README.md +3 -6

README.md CHANGED Viewed

@@ -60,7 +60,7 @@ model = AutoModelForCausalLM.from_pretrained(model_id)
 messages = [
     {"role": "system", "content": "You are a math-focused assistant. Solve the user's math problem and follow the training format: Understanding Query, Drafting Answer, Refining The Answer, and Final Response."},
-    {"role": "user", "content": "John has 22 apples, he eats 10 of them, now john has"},
 ]
 prompt = tokenizer.apply_chat_template(
     messages,
@@ -70,11 +70,8 @@ prompt = tokenizer.apply_chat_template(
 inputs = tokenizer(prompt, return_tensors="pt")
 outputs = model.generate(
     **inputs,
-    max_new_tokens=128,
-    do_sample=True,
-    temperature=0.7,
-    top_k=40,
-    top_p=0.95,
     repetition_penalty=1.1,
     pad_token_id=tokenizer.pad_token_id,
     eos_token_id=tokenizer.eos_token_id,

 messages = [
     {"role": "system", "content": "You are a math-focused assistant. Solve the user's math problem and follow the training format: Understanding Query, Drafting Answer, Refining The Answer, and Final Response."},
+    {"role": "user", "content": "John has 22 apples, he eats 10 of them, how many apples does john have now?"},
 ]
 prompt = tokenizer.apply_chat_template(
     messages,
 inputs = tokenizer(prompt, return_tensors="pt")
 outputs = model.generate(
     **inputs,
+    max_new_tokens=512,
+    do_sample=False,
     repetition_penalty=1.1,
     pad_token_id=tokenizer.pad_token_id,
     eos_token_id=tokenizer.eos_token_id,