Instructions to use ermiaazarkhalili/Carnice-9B-Function-Calling-xLAM-Unsloth with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ermiaazarkhalili/Carnice-9B-Function-Calling-xLAM-Unsloth with Transformers:

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

pipe = pipeline("text-generation", model="ermiaazarkhalili/Carnice-9B-Function-Calling-xLAM-Unsloth")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ermiaazarkhalili/Carnice-9B-Function-Calling-xLAM-Unsloth")
model = AutoModelForCausalLM.from_pretrained("ermiaazarkhalili/Carnice-9B-Function-Calling-xLAM-Unsloth")
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 ermiaazarkhalili/Carnice-9B-Function-Calling-xLAM-Unsloth with PEFT:
```
Task type is invalid.
```
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use ermiaazarkhalili/Carnice-9B-Function-Calling-xLAM-Unsloth with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ermiaazarkhalili/Carnice-9B-Function-Calling-xLAM-Unsloth"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ermiaazarkhalili/Carnice-9B-Function-Calling-xLAM-Unsloth",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ermiaazarkhalili/Carnice-9B-Function-Calling-xLAM-Unsloth

SGLang

How to use ermiaazarkhalili/Carnice-9B-Function-Calling-xLAM-Unsloth 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 "ermiaazarkhalili/Carnice-9B-Function-Calling-xLAM-Unsloth" \
    --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": "ermiaazarkhalili/Carnice-9B-Function-Calling-xLAM-Unsloth",
		"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 "ermiaazarkhalili/Carnice-9B-Function-Calling-xLAM-Unsloth" \
        --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": "ermiaazarkhalili/Carnice-9B-Function-Calling-xLAM-Unsloth",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Studio

How to use ermiaazarkhalili/Carnice-9B-Function-Calling-xLAM-Unsloth 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 ermiaazarkhalili/Carnice-9B-Function-Calling-xLAM-Unsloth 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 ermiaazarkhalili/Carnice-9B-Function-Calling-xLAM-Unsloth to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for ermiaazarkhalili/Carnice-9B-Function-Calling-xLAM-Unsloth to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="ermiaazarkhalili/Carnice-9B-Function-Calling-xLAM-Unsloth",
    max_seq_length=2048,
)

Docker Model Runner
How to use ermiaazarkhalili/Carnice-9B-Function-Calling-xLAM-Unsloth with Docker Model Runner:
```
docker model run hf.co/ermiaazarkhalili/Carnice-9B-Function-Calling-xLAM-Unsloth
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Carnice-9B-xLAM-Unsloth — Fine-tuned on xLAM-60k

Fine-tuned adapter-merged checkpoint of Carnice-9b on the Salesforce/xlam-function-calling-60k dataset, produced via Unsloth + Hugging Face TRL's SFTTrainer.

Field	Value
Base model	`kai-os/Carnice-9b`
Architecture	`Gemma2ForCausalLM`
Parameters	9B
Precision	bfloat16 (merged 16-bit)
Fine-tuning method	QLoRA (4-bit base, LoRA r=16, α=16)
Dataset	`Salesforce/xlam-function-calling-60k` (60,000 examples)
Training	N=1 full epoch (7,500 steps, effective batch=8)
Learning rate	2e-4 (linear decay, warmup 5 steps)
Unsloth version	2026.4.6
Trained on	DRAC Fir cluster, NVIDIA H100 80GB HBM3 MIG 3g.40gb

Usage

Python (transformers)

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model = AutoModelForCausalLM.from_pretrained(
    "ermiaazarkhalili/Carnice-9B-Function-Calling-xLAM-Unsloth",
    torch_dtype=torch.bfloat16,
    device_map="auto",
    trust_remote_code=True,
)
tokenizer = AutoTokenizer.from_pretrained("ermiaazarkhalili/Carnice-9B-Function-Calling-xLAM-Unsloth", trust_remote_code=True)

messages = [{"role": "user", "content": "Find flights from SFO to NYC on December 25th"}]
text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = tokenizer(text=text, return_tensors="pt").to(model.device)
outputs = model.generate(**inputs, max_new_tokens=256, do_sample=False)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Unsloth (2× faster inference)

from unsloth import FastLanguageModel
model, tokenizer = FastLanguageModel.from_pretrained(
    "ermiaazarkhalili/Carnice-9B-Function-Calling-xLAM-Unsloth",
    max_seq_length=2048,
    load_in_4bit=False,
)
FastLanguageModel.for_inference(model)

GGUF (llama.cpp / Ollama)

Quantized GGUF versions are available at ermiaazarkhalili/Carnice-9B-Function-Calling-xLAM-Unsloth-GGUF:

# llama-cli
llama-cli -hf ermiaazarkhalili/Carnice-9B-Function-Calling-xLAM-Unsloth-GGUF --jinja -p "Find flights from SFO to NYC on December 25th" -n 256

# Ollama
ollama run hf.co/ermiaazarkhalili/Carnice-9B-Function-Calling-xLAM-Unsloth-GGUF:Q4_K_M

Training details

Function-calling fine-tuning on 60,000 examples from Salesforce/xlam-function-calling-60k.

SFTTrainer (trl >= 0.14) via Unsloth's FastLanguageModel
LoRA config: r=16, α=16, dropout=0, targeting q_proj/k_proj/v_proj/o_proj/gate_proj/up_proj/down_proj
Effective batch size: 8 (per_device=2 × grad_accum=4)
Max sequence length: 2048
Optimizer: adamw_8bit with linear LR scheduler
Seed: 3407

Intended use

For research and non-commercial experimentation only. Outputs should be independently verified before any downstream use.

Limitations

Trained on a single epoch (~7,500 optimizer steps); further training may yield additional gains.
Fine-tuned from Carnice-9b, inherits its limitations and biases.
Evaluated only on training-data perplexity; no external benchmarks run on this checkpoint.
Limited to the 60 function schemas covered in the training dataset; performance on novel APIs may degrade. GGUF sibling repo currently ships Q4_K_M, Q5_K_M, and Q8_0 only (the 6-quant conversion exceeded memory limits on MIG 3g.40gb; the 3 successful quants cover the typical inference spectrum).

Citation

@misc{ carnice_9b_xlam_unsloth_2026 ,
  author = {Ermia Azarkhalili},
  title = { Carnice-9B-xLAM-Unsloth — Function-calling fine-tune of Carnice-9b },
  year = {2026},
  publisher = {Hugging Face},
  howpublished = {\url{https://huggingface.co/ermiaazarkhalili/Carnice-9B-Function-Calling-xLAM-Unsloth}}
}

This gemma2 model was trained 2× faster with Unsloth and Hugging Face's TRL library.