Instructions to use mondk/LFM3-1.7B-Claude-Code-Safetensors with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mondk/LFM3-1.7B-Claude-Code-Safetensors with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="mondk/LFM3-1.7B-Claude-Code-Safetensors", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("mondk/LFM3-1.7B-Claude-Code-Safetensors", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("mondk/LFM3-1.7B-Claude-Code-Safetensors", trust_remote_code=True, device_map="auto")
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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use mondk/LFM3-1.7B-Claude-Code-Safetensors with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "mondk/LFM3-1.7B-Claude-Code-Safetensors"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mondk/LFM3-1.7B-Claude-Code-Safetensors",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/mondk/LFM3-1.7B-Claude-Code-Safetensors

SGLang

How to use mondk/LFM3-1.7B-Claude-Code-Safetensors 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 "mondk/LFM3-1.7B-Claude-Code-Safetensors" \
    --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": "mondk/LFM3-1.7B-Claude-Code-Safetensors",
		"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 "mondk/LFM3-1.7B-Claude-Code-Safetensors" \
        --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": "mondk/LFM3-1.7B-Claude-Code-Safetensors",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use mondk/LFM3-1.7B-Claude-Code-Safetensors with Docker Model Runner:
```
docker model run hf.co/mondk/LFM3-1.7B-Claude-Code-Safetensors
```

LFM3 1.7B Claude Code

hi, I’ve fine-tuned the LiquidAI/LFM3-1.7B model over several rounds using the mondk/Ultra-Trio-Unfiltered dataset:

Round 1: Tool usage
Round 2: Improving benchmark scores
Round 3: RL (the model generates its own questions and answers)

gguf: mondk/LFM3-1.7B-Claude-Code-GGUF

1. Results

Benchmark	Model	Correct	Wrong	Pass rate
BFCL v4	LFM3 1.7B Claude Code	27	3	90.0%
BFCL v4	LFM3 1.7B	25	5	83.3%
LCB v6	LFM3 1.7B Claude Code	2	10	16.7%
LCB v6	LFM3 1.7B	1	11	8.3%
TerminalBench	LFM3 1.7B Claude Code	0	4	0.0%
TerminalBench	LFM3 1.7B	0	4	0.0%
SWE	LFM3 1.7B Claude Code	0	4	0.0%
SWE	LFM3 1.7B	0	4	0.0%

Method

BFCL: function calls matched against gold.
LCB: final code run against all gold tests; original outputs kept where the model finished its answer.
TerminalBench and SWE: correct only if resolved (all verifier tests pass).
Both models: f16, temperature: 0, thinking: default. Max tokens: 1200 (BFCL), 2048 (LCB), 2560 (TerminalBench and SWE). Max tool calls: 9.

Limitations

Sample size is small: 30 BFCL questions, 12 LCB questions, 4 TerminalBench questions and 4 SWE questions. Results may differ slightly from other evaluations.
Some BFCL answers that use JSON or prose instead of the required [func(args)] format were counted as correct if the call content was right.
TerminalBench and SWE come from noodcon/TerminalBench-DockerLess and noodcon/SWE-DockerLess, Docker-free versions of the official benchmarks. Docker was too complex to set up here, so these may not match the official benchmarks.

2. Process metrics

Benchmark	Model	Format errors	Tool calls	Time (s)	Characters generated	Estimated tokens
TerminalBench	LFM3 1.7B Claude Code	7	19	156.2	12,591	~3,150
TerminalBench	LFM3 1.7B	13	3	984.5	103,391	~25,850
SWE	LFM3 1.7B Claude Code	4	36	329.5	24,279	~6,070
SWE	LFM3 1.7B	12	0	90.5	8,018	~2,005

ty!

Downloads last month: 1,708

Safetensors

Model size

2B params

Tensor type

F16

Model tree for mondk/LFM3-1.7B-Claude-Code-Safetensors

Base model

LiquidAI/LFM3-1.7B-Base

Finetuned

LiquidAI/LFM3-1.7B

Finetuned

(56)

this model

Merges

1 model

mondk
/

LFM3-1.7B-Claude-Code-Safetensors

LFM3 1.7B Claude Code

1. Results

2. Process metrics

Model tree for mondk/LFM3-1.7B-Claude-Code-Safetensors

Dataset used to train mondk/LFM3-1.7B-Claude-Code-Safetensors

Space using mondk/LFM3-1.7B-Claude-Code-Safetensors 1