Instructions to use nadiva1243/phi4RAG with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use nadiva1243/phi4RAG with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="nadiva1243/phi4RAG",
	filename="Phi4-Q4_K_M.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use nadiva1243/phi4RAG with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf nadiva1243/phi4RAG:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf nadiva1243/phi4RAG:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf nadiva1243/phi4RAG:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf nadiva1243/phi4RAG:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf nadiva1243/phi4RAG:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf nadiva1243/phi4RAG:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf nadiva1243/phi4RAG:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf nadiva1243/phi4RAG:Q4_K_M

Use Docker

docker model run hf.co/nadiva1243/phi4RAG:Q4_K_M

LM Studio
Jan

vLLM

How to use nadiva1243/phi4RAG with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "nadiva1243/phi4RAG"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "nadiva1243/phi4RAG",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/nadiva1243/phi4RAG:Q4_K_M

Ollama
How to use nadiva1243/phi4RAG with Ollama:
```
ollama run hf.co/nadiva1243/phi4RAG:Q4_K_M
```

Unsloth Studio new

How to use nadiva1243/phi4RAG 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 nadiva1243/phi4RAG 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 nadiva1243/phi4RAG to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for nadiva1243/phi4RAG to start chatting

Docker Model Runner
How to use nadiva1243/phi4RAG with Docker Model Runner:
```
docker model run hf.co/nadiva1243/phi4RAG:Q4_K_M
```

Lemonade

How to use nadiva1243/phi4RAG with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull nadiva1243/phi4RAG:Q4_K_M

Run and chat with the model

lemonade run user.phi4RAG-Q4_K_M

List all available models

lemonade list

nadiva1243 commited on Apr 12

Commit

21d45d4

verified ·

1 Parent(s): 76e9cef

Upload README.md with huggingface_hub

Browse files

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -68,7 +68,7 @@ The **full MonkeyGrab application repository is not public yet** (defense / publ
 - **Sequence limits:** `max_length` 4,096 tokens; context truncated to **2,048** tokens; generation up to **2,048** new tokens.
 - **Optimizer / schedule:** AdamW 8-bit, **lr** 5e-5, **cosine** decay with **warmup_ratio** 0.05, **weight_decay** 0.01, **max_grad_norm** 1.0.
 - **Batching:** `per_device_train_batch_size` 1, **gradient_accumulation_steps** 16 → **effective batch 16**; **bf16** + **TF32**; gradient checkpointing enabled.
-- **Epochs:** 3; checkpoints saved every **300** steps (keep last 3); eval every **150** steps; **load_best_model_at_end** on `eval_loss`; **early stopping** patience **5** evaluations.
 ### Evaluation protocol

 - **Sequence limits:** `max_length` 4,096 tokens; context truncated to **2,048** tokens; generation up to **2,048** new tokens.
 - **Optimizer / schedule:** AdamW 8-bit, **lr** 5e-5, **cosine** decay with **warmup_ratio** 0.05, **weight_decay** 0.01, **max_grad_norm** 1.0.
 - **Batching:** `per_device_train_batch_size` 1, **gradient_accumulation_steps** 16 → **effective batch 16**; **bf16** + **TF32**; gradient checkpointing enabled.
+- **Epochs:** 3; checkpoints saved every **300** steps (keep last 3); eval every **150** steps; **load_best_model_at_end** on `eval_loss`; **early stopping** patience **3** evaluations.
 ### Evaluation protocol