Based on LFM2-1.2B, LFM2-1.2B-Tool is designed for concise and precise tool calling. The key challenge was designing a non-thinking model that outperforms similarly sized thinking models for tool use.
Use cases:
Mobile and edge devices requiring instant API calls, database queries, or system integrations without cloud dependency.
Real-time assistants in cars, IoT devices, or customer support, where response latency is critical.
Resource-constrained environments like embedded systems or battery-powered devices needing efficient tool execution.
You can find more information about other task-specific models in this blog post.
Function definition: LFM2 takes JSON function definitions as input (JSON objects between <|tool_list_start|> and <|tool_list_end|> special tokens), usually in the system prompt
Function call: LFM2 writes Pythonic function calls (a Python list between <|tool_call_start|> and <|tool_call_end|> special tokens), as the assistant answer.
Function execution: The function call is executed and the result is returned (string between <|tool_response_start|> and <|tool_response_end|> special tokens), as a "tool" role.
Final answer: LFM2 interprets the outcome of the function call to address the original user prompt in plain text.
Here is a simple example of a conversation using tool use:
<|startoftext|><|im_start|>system
List of tools: <|tool_list_start|>[{"name": "get_candidate_status", "description": "Retrieves the current status of a candidate in the recruitment process", "parameters": {"type": "object", "properties": {"candidate_id": {"type": "string", "description": "Unique identifier for the candidate"}}, "required": ["candidate_id"]}}]<|tool_list_end|><|im_end|>
<|im_start|>user
What is the current status of candidate ID 12345?<|im_end|>
<|im_start|>assistant
<|tool_call_start|>[get_candidate_status(candidate_id="12345")]<|tool_call_end|>Checking the current status of candidate ID 12345.<|im_end|>
<|im_start|>tool
<|tool_response_start|>{"candidate_id": "12345", "status": "Interview Scheduled", "position": "Clinical Research Associate", "date": "2023-11-20"}<|tool_response_end|><|im_end|>
<|im_start|>assistant
The candidate with ID 12345 is currently in the "Interview Scheduled" stage for the position of Clinical Research Associate, with an interview date set for 2023-11-20.<|im_end|>
Warning. ⚠️ The model supports both single-turn and multi-turn conversations.
For edge inference, latency is a crucial factor in delivering a seamless and satisfactory user experience. Consequently, while test-time-compute inherently provides more accuracy, it ultimately compromises the user experience due to increased waiting times for function calls.
Therefore, the goal was to develop a tool calling model that is competitive with thinking models, yet operates without any internal chain-of-thought process.
We evaluated each model on a proprietary benchmark that was specifically designed to prevent data contamination. The benchmark ensures that performance metrics reflect genuine tool-calling capabilities rather than memorized patterns from training data.
# custom terms: read the license before you download$ fw get onnx-community/LFM2-1.2B-Tool-ONNX
# manifest sha256 f94d650c6b8f… · 10.4 GB · 21 files$ fw verify ./LFM2-1.2B-Tool-ONNX onnx-community/LFM2-1.2B-Tool-ONNX
Terms that come with these files. LFM 1.0: commercial use only for organisations under US$10M annual revenue. Keep a copy of the license with the files.
Custom license (custom).Read the license text first. Open this panel to show the commands once you accept its terms.
fw.pyChecks the signature and every sha256, tries each source in order, resumes.
onnx-community <huggingface.co/onnx-community>Newsgroups: alt.freeweights.lfmSubject: 
