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 / trainer_log.jsonl

isbondarev

Upload folder using huggingface_hub

8350475 verified 10 days ago

Raw History Blame Contribute Delete

996 Bytes

{"current_steps": 5, "total_steps": 25, "loss": 2.0679, "lr": 9.949107209404665e-05, "epoch": 0.2, "percentage": 20.0, "elapsed_time": "0:00:01", "remaining_time": "0:00:07"}
{"current_steps": 10, "total_steps": 25, "loss": 1.1673, "lr": 8.274303669726426e-05, "epoch": 0.4, "percentage": 40.0, "elapsed_time": "0:00:03", "remaining_time": "0:00:04"}
{"current_steps": 15, "total_steps": 25, "loss": 0.7209, "lr": 5e-05, "epoch": 0.6, "percentage": 60.0, "elapsed_time": "0:00:04", "remaining_time": "0:00:02"}
{"current_steps": 20, "total_steps": 25, "loss": 0.6153, "lr": 1.725696330273575e-05, "epoch": 0.8, "percentage": 80.0, "elapsed_time": "0:00:05", "remaining_time": "0:00:01"}
{"current_steps": 25, "total_steps": 25, "loss": 0.6119, "lr": 5.089279059533658e-07, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "0:00:06", "remaining_time": "0:00:00"}
{"current_steps": 25, "total_steps": 25, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "0:00:06", "remaining_time": "0:00:00"}

	{"current_steps": 5, "total_steps": 25, "loss": 2.0679, "lr": 9.949107209404665e-05, "epoch": 0.2, "percentage": 20.0, "elapsed_time": "0:00:01", "remaining_time": "0:00:07"}
	{"current_steps": 10, "total_steps": 25, "loss": 1.1673, "lr": 8.274303669726426e-05, "epoch": 0.4, "percentage": 40.0, "elapsed_time": "0:00:03", "remaining_time": "0:00:04"}
	{"current_steps": 15, "total_steps": 25, "loss": 0.7209, "lr": 5e-05, "epoch": 0.6, "percentage": 60.0, "elapsed_time": "0:00:04", "remaining_time": "0:00:02"}
	{"current_steps": 20, "total_steps": 25, "loss": 0.6153, "lr": 1.725696330273575e-05, "epoch": 0.8, "percentage": 80.0, "elapsed_time": "0:00:05", "remaining_time": "0:00:01"}
	{"current_steps": 25, "total_steps": 25, "loss": 0.6119, "lr": 5.089279059533658e-07, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "0:00:06", "remaining_time": "0:00:00"}
	{"current_steps": 25, "total_steps": 25, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "0:00:06", "remaining_time": "0:00:00"}