Instructions to use anisiraj/tinytune-smollm2-xlam with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use anisiraj/tinytune-smollm2-xlam with Transformers:

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

pipe = pipeline("text-generation", model="anisiraj/tinytune-smollm2-xlam")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("anisiraj/tinytune-smollm2-xlam")
model = AutoModelForCausalLM.from_pretrained("anisiraj/tinytune-smollm2-xlam")
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]:]))

PEFT
How to use anisiraj/tinytune-smollm2-xlam with PEFT:
```
Task type is invalid.
```
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use anisiraj/tinytune-smollm2-xlam with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "anisiraj/tinytune-smollm2-xlam"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "anisiraj/tinytune-smollm2-xlam",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/anisiraj/tinytune-smollm2-xlam

SGLang

How to use anisiraj/tinytune-smollm2-xlam 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 "anisiraj/tinytune-smollm2-xlam" \
    --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": "anisiraj/tinytune-smollm2-xlam",
		"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 "anisiraj/tinytune-smollm2-xlam" \
        --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": "anisiraj/tinytune-smollm2-xlam",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Studio

How to use anisiraj/tinytune-smollm2-xlam 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 anisiraj/tinytune-smollm2-xlam 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 anisiraj/tinytune-smollm2-xlam to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for anisiraj/tinytune-smollm2-xlam to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="anisiraj/tinytune-smollm2-xlam",
    max_seq_length=2048,
)

Docker Model Runner
How to use anisiraj/tinytune-smollm2-xlam with Docker Model Runner:
```
docker model run hf.co/anisiraj/tinytune-smollm2-xlam
```

tinytune-smollm2-xlam

A LoRA fine-tune of HuggingFaceTB/SmolLM2-135M-Instruct that emits structured tool / function calls, trained on Salesforce/xlam-function-calling-60k.

Ships two artifacts: a standalone merged model at the repo root (plain transformers, no PEFT) and the raw LoRA adapter under adapter/. Merge produced with Unsloth.

⚠️ Checkpoint snapshot (~1.67 epochs, step 5000/9000 (56%)); may not be a fully-trained final run.

Results

Greedy generation over 200 held-out test examples:

Metric	Score
Tool-name match — function name(s) match gold	96.0%
Exact match — name and all arguments match	72.5%

exact_match is the metric that matters: one wrong argument fails it while barely denting token accuracy, so a low SFT loss can still mean imperfect calls.

Output format

The assistant replies with one or more <tool_call>{"name": ..., "arguments": {...}}</tool_call> blocks.

Usage — merged model

from transformers import AutoModelForCausalLM, AutoTokenizer

tok = AutoTokenizer.from_pretrained("anisiraj/tinytune-smollm2-xlam")
model = AutoModelForCausalLM.from_pretrained("anisiraj/tinytune-smollm2-xlam").eval()

messages = [
    {"role": "system", "content": "You are a function-calling assistant. Available tools:\n"
        '{"name": "get_weather", "arguments": {"city": "string"}}'},
    {"role": "user", "content": "What's the weather in Paris?"},
]
inp = tok.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt")
out = model.generate(inp, max_new_tokens=128, do_sample=False)
print(tok.decode(out[0][inp.shape[1]:], skip_special_tokens=True))

Usage — LoRA adapter

from transformers import AutoModelForCausalLM
from peft import PeftModel

base = AutoModelForCausalLM.from_pretrained("HuggingFaceTB/SmolLM2-135M-Instruct")
model = PeftModel.from_pretrained(base, "anisiraj/tinytune-smollm2-xlam", subfolder="adapter")

Training

LoRA (full-precision) via TRL SFTTrainer: r=16, alpha=32, dropout=0.05, targets = attention + MLP; completion-only (generation) loss; lr 2e-4 cosine, warmup 0.03, batch 4 × grad-accum 4. Custom ChatML+tools template (tools in the system turn).

License & data

Weights derive from HuggingFaceTB/SmolLM2-135M-Instruct (Apache-2.0). Trained on Salesforce/xlam-function-calling-60k — review that dataset's license before downstream use.

Downloads last month: 20

Safetensors

Model size

0.1B params

Tensor type

BF16

Model tree for anisiraj/tinytune-smollm2-xlam

Base model

HuggingFaceTB/SmolLM2-135M

Quantized

HuggingFaceTB/SmolLM2-135M-Instruct

Adapter

(54)

this model

Dataset used to train anisiraj/tinytune-smollm2-xlam

Evaluation results

Tool-name match (n=200) on xLAM 60k (held-out)
self-reported

0.960
Exact match name+args (n=200) on xLAM 60k (held-out)
self-reported

0.725