---
# @see https://github.com/huggingface/hub-docs/blob/main/modelcard.md
# @see https://huggingface.co/docs/huggingface_hub/guides/model-cards#update-metadata
# @see https://huggingface.co/docs/hub/model-cards#model-card-metadata
version: '0.32'
timestamp: '20260221_012419846_UTC'
model_name: retrain-pipelines Function Caller
base_model: unsloth/Qwen2.5-1.5B
base_model_relation: adapter
library_name: transformers
datasets:
- retrain-pipelines/func_calls_ds
license: apache-2.0
language:
- en
task_categories:
- text-generation
tags:
- retrain-pipelines
- function-calling
- LLM Agent
- code
- unsloth
thumbnail: https://cdn-avatars.huggingface.co/v1/production/uploads/651e93137b2a2e027f9e55df/96hzBved0YMjCq--s0kad.png
# @see https://huggingface.co/docs/hub/models-widgets#enabling-a-widget
# @see https://huggingface.co/docs/hub/models-widgets-examples
# @see https://huggingface.co/docs/hub/en/model-cards#specifying-a-task--pipelinetag-
pipeline_tag: text-generation
widget:
- text: >-
Hello
example_title: No function call
output:
text: '[]'
- text: >-
Is 49 a perfect square?
example_title: Perfect square
output:
text: '[{"name": "is_perfect_square", "arguments": {"num": 49}}]'
exec_id: '135'
# @see https://huggingface.co/docs/huggingface_hub/guides/model-cards#include-evaluation-results
# @see https://huggingface.co/docs/huggingface_hub/main/en/package_reference/cards#huggingface_hub.EvalResult
model-index:
- name: retrain-pipelines Function Caller
results:
- task:
type: text-generation
name: Text Generation
dataset:
name: retrain-pipelines Function Calling
type: retrain-pipelines/func_calls_ds
split: validation
revision: 70f9a2864d71472a383596aa4ffec6e603d762ea
metrics:
- type: precision
value: 0.78253722729447
- type: recall
value: 0.7825566381742679
- type: f1
value: 0.7823158181198717
- type: jaccard
value: 0.7654290889550754
---
Training dataset :
- retrain-pipelines/func_calls_ds v0.31
(70f9a28 -
2026-02-20 18:34:18 UTC)
Base model :
- unsloth/Qwen2.5-1.5B
(1582479 -
2025-04-28 04:13:37 UTC)
arxiv :
- 2407.10671
The herein LoRa adapter can for instance be used as follows :
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
from torch import device, cuda
repo_id = "retrain-pipelines/function_caller_lora"
revision = ""
model = AutoModelForCausalLM.from_pretrained(
repo_id, revision=revision, torch_dtype="auto", device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(
repo_id, revision=revision, torch_dtype="auto", device_map="auto")
device = device("cuda" if cuda.is_available() else "cpu")
def generate_tool_calls_list(query, max_new_tokens=400) -> str:
formatted_query = tokenizer.chat_template.format(query, "")
inputs = tokenizer(formatted_query, return_tensors="pt").input_ids.to(device)
outputs = model.generate(inputs, max_new_tokens=max_new_tokens, do_sample=False)
generated_text = tokenizer.batch_decode(outputs, skip_special_tokens=True)[0]
return generated_text[len(formatted_query):].strip()
generate_tool_calls_list("Is 49 a perfect square ?")
```