Instructions to use retrain-pipelines/function_caller_lora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use retrain-pipelines/function_caller_lora with Transformers:

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

pipe = pipeline("text-generation", model="retrain-pipelines/function_caller_lora")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("retrain-pipelines/function_caller_lora", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use retrain-pipelines/function_caller_lora with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/retrain-pipelines/function_caller_lora

SGLang

How to use retrain-pipelines/function_caller_lora 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 "retrain-pipelines/function_caller_lora" \
    --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": "retrain-pipelines/function_caller_lora",
		"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 "retrain-pipelines/function_caller_lora" \
        --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": "retrain-pipelines/function_caller_lora",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Studio new

How to use retrain-pipelines/function_caller_lora with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for retrain-pipelines/function_caller_lora to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for retrain-pipelines/function_caller_lora to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for retrain-pipelines/function_caller_lora to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="retrain-pipelines/function_caller_lora",
    max_seq_length=2048,
)

Docker Model Runner
How to use retrain-pipelines/function_caller_lora with Docker Model Runner:
```
docker model run hf.co/retrain-pipelines/function_caller_lora
```

function_caller_lora / README.md

Aurelien-Morgan-Bot

v0.32 - 2026-02-21 01:24:19 UTC - retrain-pipelines v0.1.2 - Upload model and tokenizer with README.

e9f7bcc verified 3 months ago

preview code

raw

history blame contribute delete

6.22 kB

	---
	# @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

	---

	<div
	class="
	p-6 mb-4 rounded-lg
	pt-6 sm:pt-9
	bg-gradient-to-b
	from-purple-500
	dark:from-purple-500/20
	"
	>
	<div
	class="
	pl-4 rounded-lg
	border-2 border-gray-100
	bg-gradient-to-b
	from-purple-500
	dark:from-purple-500/20
	"
	>
	<b>retrain-pipelines Function Caller</b>
	</div>
	<code>version 0.32</code> - <code>2026-02-21 01:24:19 UTC</code>
	(retraining
	<a target="_blank"
	href="https://huggingface.co/retrain-pipelines/function_caller_lora/tree/retrain-pipelines_source-code/v0.32_20260221_012419846_UTC">source-code</a> \|
	<a target="_blank"
	href="https://huggingface.co/spaces/retrain-pipelines/online_pipeline_card_renderer/?model_repo_id=retrain-pipelines/function_caller_lora&version_id=v0.32_20260221_012419846_UTC">pipeline-card</a>)
	</div>

	Training dataset :
	- <code>retrain-pipelines/func_calls_ds v0.31</code>
	(<a href="https://huggingface.co/datasets/retrain-pipelines/func_calls_ds/blob/70f9a2864d71472a383596aa4ffec6e603d762ea/README.md"
	target="_blank">70f9a28</a> -
	2026-02-20 18:34:18 UTC)
	<br />
	<img alt="" src="https://img.shields.io/badge/dynamic/json?url=https%3A%2F%2Fhuggingface.co%2Fapi%2Fdatasets%2Fretrain-pipelines/func_calls_ds&query=%24.downloads&logo=huggingface&label=downloads" class="inline-block" /> <img alt="" src="https://img.shields.io/badge/dynamic/json?url=https%3A%2F%2Fhuggingface.co%2Fapi%2Fdatasets%2Fretrain-pipelines/func_calls_ds&query=%24.likes&logo=huggingface&label=likes" class="inline-block" />

	Base model :
	- <code>unsloth/Qwen2.5-1.5B</code>
	(<a href="https://huggingface.co/unsloth/Qwen2.5-1.5B/blob/1582479a65dd3252951448feee6868d2cfda6452/README.md"
	target="_blank">1582479</a> -
	2025-04-28 04:13:37 UTC)
	<br />
	<img alt="" src="https://img.shields.io/badge/dynamic/json?url=https%3A%2F%2Fhuggingface.co%2Fapi%2Fmodels%2Funsloth/Qwen2.5-1.5B&query=%24.downloads&logo=huggingface&label=downloads" class="inline-block" /> <img alt="" src="https://img.shields.io/badge/dynamic/json?url=https%3A%2F%2Fhuggingface.co%2Fapi%2Fmodels%2Funsloth/Qwen2.5-1.5B&query=%24.likes&logo=huggingface&label=likes" class="inline-block" /><br />
	arxiv :<br />
	- <code><a href="https://huggingface.co/papers/2407.10671"
	target="_blank">2407.10671</a></code><br />
	The herein LoRa adapter can for instance be used as follows :<br />
	```python
	from transformers import AutoModelForCausalLM, AutoTokenizer
	from torch import device, cuda

	repo_id = "retrain-pipelines/function_caller_lora"
	revision = "<model_revision_commit_hash>"
	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 ?")
	```

	<br />
	<br />

	<div
	class="
	p-6 mb-4 rounded-lg
	pt-6 sm:pt-9
	px-4
	pb-1
	bg-gradient-to-t
	from-purple-500
	dark:from-purple-500/20
	"
	>
	<div
	class="
	p-6 mb-4 rounded-lg
	border-2 border-gray-100
	pt-6 sm:pt-9
	bg-gradient-to-t
	from-purple-500
	dark:from-purple-500/20
	"
	>
	Powered by
	<code><a target="_blank"
	href="https://github.com/aurelienmorgan/retrain-pipelines">retrain-pipelines
	0.1.2</a></code> -
	<code>Run by <a target="_blank" href="https://huggingface.co/Aurelien-Morgan-Bot">Aurelien-Morgan-Bot</a></code> -
	<em><b>UnslothFuncCallFlow</b></em> - exec_id : <code>135</code>
	</div>
	</div>