Instructions to use DebateLabKIT/Phi-4-Argunaut-1-SFT-dev1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use DebateLabKIT/Phi-4-Argunaut-1-SFT-dev1 with Transformers:

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

pipe = pipeline("text-generation", model="DebateLabKIT/Phi-4-Argunaut-1-SFT-dev1")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("DebateLabKIT/Phi-4-Argunaut-1-SFT-dev1")
model = AutoModelForCausalLM.from_pretrained("DebateLabKIT/Phi-4-Argunaut-1-SFT-dev1", device_map="auto")
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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use DebateLabKIT/Phi-4-Argunaut-1-SFT-dev1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "DebateLabKIT/Phi-4-Argunaut-1-SFT-dev1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "DebateLabKIT/Phi-4-Argunaut-1-SFT-dev1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/DebateLabKIT/Phi-4-Argunaut-1-SFT-dev1

SGLang

How to use DebateLabKIT/Phi-4-Argunaut-1-SFT-dev1 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 "DebateLabKIT/Phi-4-Argunaut-1-SFT-dev1" \
    --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": "DebateLabKIT/Phi-4-Argunaut-1-SFT-dev1",
		"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 "DebateLabKIT/Phi-4-Argunaut-1-SFT-dev1" \
        --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": "DebateLabKIT/Phi-4-Argunaut-1-SFT-dev1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use DebateLabKIT/Phi-4-Argunaut-1-SFT-dev1 with Docker Model Runner:
```
docker model run hf.co/DebateLabKIT/Phi-4-Argunaut-1-SFT-dev1
```

ggbetz commited on Aug 4, 2025

Commit

8abf6ca

verified ·

1 Parent(s): f660383

Model save

Browse files

Files changed (11) hide show

all_results.json +8 -0
config.json +1 -1
generation_config.json +7 -0
model-00001-of-00006.safetensors +1 -1
model-00002-of-00006.safetensors +1 -1
model-00003-of-00006.safetensors +1 -1
model-00004-of-00006.safetensors +1 -1
model-00005-of-00006.safetensors +1 -1
model-00006-of-00006.safetensors +1 -1
train_results.json +8 -0
trainer_state.json +0 -0

+{
+    "total_flos": 7.305161816110268e+18,
+    "train_loss": 0.14658924444761975,
+    "train_runtime": 62800.0257,
+    "train_samples": 1000000,
+    "train_samples_per_second": 5.279,
+    "train_steps_per_second": 0.082
+}

@@ -26,6 +26,6 @@
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.53.3",
-  "use_cache": false,
   "vocab_size": 100352
 }

   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.53.3",
+  "use_cache": true,
   "vocab_size": 100352
 }

+{
+  "_from_model_config": true,
+  "bos_token_id": 100257,
+  "eos_token_id": 100265,
+  "pad_token_id": 100351,
+  "transformers_version": "4.53.3"
+}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e87f1506161dfe6378f2badb07daa737fc4715ff580b6abfeed3e9da24db071
 size 4933658528

 version https://git-lfs.github.com/spec/v1
+oid sha256:e7fa85e331d6ebdcc1aeb2ab2c6e616a91aedd5558abbc64bf877f41ad9de5da
 size 4954693112

 version https://git-lfs.github.com/spec/v1
+oid sha256:6cdc894c366b55bf38106d176ff46250bbb116b9d8506ee8e4b420095b519c50
 size 4902243992

 version https://git-lfs.github.com/spec/v1
+oid sha256:feac99861388e12465e33da8ae615f3d68c9baef72b625bdac21f9dd08a509f6
 size 4954672440

 version https://git-lfs.github.com/spec/v1
+oid sha256:81953f2bf9e87b5045a309b14a0786939a6b335963edabd39f64b984eb45297f
 size 4954672432

 version https://git-lfs.github.com/spec/v1
+oid sha256:c5aa34a3b30da506301529285de1ea3eca8421bc44dd1d32ab4d11123af82213
 size 4619116224

	@@ -0,0 +1,8 @@

	@@ -0,0 +1,7 @@

	@@ -0,0 +1,8 @@