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

Libraries

How to use Crossie/Nayari with Transformers:

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

pipe = pipeline("text-generation", model="Crossie/Nayari")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Crossie/Nayari")
model = AutoModelForCausalLM.from_pretrained("Crossie/Nayari")
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=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Crossie/Nayari with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Crossie/Nayari

SGLang

How to use Crossie/Nayari 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 "Crossie/Nayari" \
    --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": "Crossie/Nayari",
		"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 "Crossie/Nayari" \
        --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": "Crossie/Nayari",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Studio new

How to use Crossie/Nayari 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 Crossie/Nayari 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 Crossie/Nayari to start chatting

Using HuggingFace Spaces for Unsloth

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

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="Crossie/Nayari",
    max_seq_length=2048,
)

Docker Model Runner
How to use Crossie/Nayari with Docker Model Runner:
```
docker model run hf.co/Crossie/Nayari
```

Crossie commited on 14 days ago

Commit

8cd12c9

verified ·

1 Parent(s): 40e9b09

Update README.md

Browse files

Files changed (1) hide show

README.md +14 -9

README.md CHANGED Viewed

@@ -7,7 +7,6 @@ language:
 pipeline_tag: text-generation
 ---
 # 🌸 Nayari AI
 A fine-tuned AI companion character built on **Qwen 2.5 1.5B Instruct**, trained using **Unsloth + LoRA** on Kaggle's free GPU tier.
@@ -29,6 +28,7 @@ Nayari-AI/
 │
 ├── nayari_build_dataset.ipynb     # LOCAL — converts all files → nayari_dataset.json + uploads to Kaggle
 ├── nayari_train.ipynb             # KAGGLE — fine-tunes Qwen 2.5 using the uploaded dataset
 ├── nayari_dataset.json            # Auto-generated dataset (do not edit manually)
 ├── nayari_system_prompt.txt       # Nayari's system prompt (baked into tokenizer at training time)
 └── README.md
@@ -57,18 +57,23 @@ You will need a **Kaggle API token** for the upload step:
 1. Go to [kaggle.com/code](https://kaggle.com/code) → **New Notebook** → Upload `nayari_train.ipynb`
 2. Click **+ Add Data** → search for your uploaded `nayari-dataset` → Add
 3. Set **Accelerator = GPU T4 x2** and **Internet = On**
-4. Run cells **in order** (Steps 1 → 9, then 8/10 are reference only)
 Training takes ~15–30 min on T4 x2.
-### Step 3 — Download & Run with KoboldCpp (run locally)
-1. Run **Step 9E** in the Kaggle notebook to get a Cloudflare download link
-2. Download `nayari-Q4_K_M.gguf` (fast) or `nayari-Q8_0.gguf` (higher quality)
-3. Install [KoboldCpp](https://github.com/LostRuins/koboldcpp/releases)
-4. Launch: `koboldcpp.exe nayari-Q4_K_M.gguf --contextsize 4096`
-5. Open `http://localhost:5001` — set **Instruct mode = ChatML**
-6. Nayari's personality is baked in — no system prompt needed in the UI
 ---

 pipeline_tag: text-generation
 ---
 # 🌸 Nayari AI
 A fine-tuned AI companion character built on **Qwen 2.5 1.5B Instruct**, trained using **Unsloth + LoRA** on Kaggle's free GPU tier.
 │
 ├── nayari_build_dataset.ipynb     # LOCAL — converts all files → nayari_dataset.json + uploads to Kaggle
 ├── nayari_train.ipynb             # KAGGLE — fine-tunes Qwen 2.5 using the uploaded dataset
+├── nayari_export.ipynb            # KAGGLE — exports the fine-tuned model to GGUF, HuggingFace, etc.
 ├── nayari_dataset.json            # Auto-generated dataset (do not edit manually)
 ├── nayari_system_prompt.txt       # Nayari's system prompt (baked into tokenizer at training time)
 └── README.md
 1. Go to [kaggle.com/code](https://kaggle.com/code) → **New Notebook** → Upload `nayari_train.ipynb`
 2. Click **+ Add Data** → search for your uploaded `nayari-dataset` → Add
 3. Set **Accelerator = GPU T4 x2** and **Internet = On**
+4. Run cells **in order**.
 Training takes ~15–30 min on T4 x2.
+### Step 3 — Export & Download (run on Kaggle)
+1. After training, open `nayari_export.ipynb` in your Kaggle environment (or upload it to a new notebook with the same workspace context).
+2. Run the cells to generate LoRA adapters, merged 16-bit, and GGUF outputs.
+3. Use the **Cloudflare Tunnel** cell to get direct HTTP download links for the generated `.gguf` files.
+4. Download `nayari-Q4_K_M.gguf` (fast) or `nayari-Q8_0.gguf` (higher quality).
+### Step 4 — Run with KoboldCpp (run locally)
+1. Install [KoboldCpp](https://github.com/LostRuins/koboldcpp/releases)
+2. Launch: `koboldcpp.exe nayari-Q4_K_M.gguf --contextsize 4096`
+3. Open `http://localhost:5001` — set **Instruct mode = ChatML**
+4. Nayari's personality is baked in — no system prompt needed in the UI
 ---