Instructions to use isbondarev/phi-4-mini-reasoning-adapter-sql with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use isbondarev/phi-4-mini-reasoning-adapter-sql with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("microsoft/Phi-4-mini-reasoning")
model = PeftModel.from_pretrained(base_model, "isbondarev/phi-4-mini-reasoning-adapter-sql")

Transformers

How to use isbondarev/phi-4-mini-reasoning-adapter-sql with Transformers:

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

pipe = pipeline("text-generation", model="isbondarev/phi-4-mini-reasoning-adapter-sql")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("isbondarev/phi-4-mini-reasoning-adapter-sql", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use isbondarev/phi-4-mini-reasoning-adapter-sql with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "isbondarev/phi-4-mini-reasoning-adapter-sql"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "isbondarev/phi-4-mini-reasoning-adapter-sql",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/isbondarev/phi-4-mini-reasoning-adapter-sql

SGLang

How to use isbondarev/phi-4-mini-reasoning-adapter-sql 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 "isbondarev/phi-4-mini-reasoning-adapter-sql" \
    --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": "isbondarev/phi-4-mini-reasoning-adapter-sql",
		"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 "isbondarev/phi-4-mini-reasoning-adapter-sql" \
        --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": "isbondarev/phi-4-mini-reasoning-adapter-sql",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use isbondarev/phi-4-mini-reasoning-adapter-sql with Docker Model Runner:
```
docker model run hf.co/isbondarev/phi-4-mini-reasoning-adapter-sql
```

phi-4-mini-reasoning-adapter-sql / README.md

isbondarev

Upload folder using huggingface_hub

8350475 verified 11 days ago

preview code

Raw History Blame Contribute Delete

1.34 kB

metadata

library_name: peft
license: other
base_model: microsoft/Phi-4-mini-reasoning
tags:
  - base_model:adapter:microsoft/Phi-4-mini-reasoning
  - llama-factory
  - lora
  - transformers
pipeline_tag: text-generation
model-index:
  - name: lora_adapter
    results: []

lora_adapter

This model is a fine-tuned version of microsoft/Phi-4-mini-reasoning on the user_dataset dataset.

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 0.0001
train_batch_size: 4
eval_batch_size: 8
seed: 42
optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.1
num_epochs: 1

Training results

Framework versions

PEFT 0.18.1
Transformers 4.57.1
Pytorch 2.11.0+cu126
Datasets 4.0.0
Tokenizers 0.22.2