Instructions to use adhafajp/phi2-qlora-zero-chat with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use adhafajp/phi2-qlora-zero-chat with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("E:\AI\model-base\phi-2-2.7B")
model = PeftModel.from_pretrained(base_model, "adhafajp/phi2-qlora-zero-chat")

Transformers

How to use adhafajp/phi2-qlora-zero-chat with Transformers:

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

pipe = pipeline("text-generation", model="adhafajp/phi2-qlora-zero-chat")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("adhafajp/phi2-qlora-zero-chat", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use adhafajp/phi2-qlora-zero-chat with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "adhafajp/phi2-qlora-zero-chat"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "adhafajp/phi2-qlora-zero-chat",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/adhafajp/phi2-qlora-zero-chat

SGLang

How to use adhafajp/phi2-qlora-zero-chat 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 "adhafajp/phi2-qlora-zero-chat" \
    --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": "adhafajp/phi2-qlora-zero-chat",
		"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 "adhafajp/phi2-qlora-zero-chat" \
        --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": "adhafajp/phi2-qlora-zero-chat",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use adhafajp/phi2-qlora-zero-chat with Docker Model Runner:
```
docker model run hf.co/adhafajp/phi2-qlora-zero-chat
```

adhafajp commited on Nov 18, 2025

Commit

d2fa0db

verified ·

1 Parent(s): 55a9aaa

Another stuff left behind

Browse files

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -78,7 +78,7 @@ Fine-tuning was performed entirely on a consumer-grade laptop:
 - **RAM:** 16 GB
 - **Quantization:** 4-bit NF4
 - **Strategy:** Low VRAM setup using gradient accumulation, packing, and LoRA adapters
--
 This demonstrates that Phi-2 can be fine-tuned effectively even on low-VRAM devices.
 ---

 - **RAM:** 16 GB
 - **Quantization:** 4-bit NF4
 - **Strategy:** Low VRAM setup using gradient accumulation, packing, and LoRA adapters
 This demonstrates that Phi-2 can be fine-tuned effectively even on low-VRAM devices.
 ---