Instructions to use Fantominsight/YAPPERTAR-ai-5B-1.0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Fantominsight/YAPPERTAR-ai-5B-1.0 with Transformers:

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

pipe = pipeline("text-generation", model="Fantominsight/YAPPERTAR-ai-5B-1.0")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("Fantominsight/YAPPERTAR-ai-5B-1.0", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Fantominsight/YAPPERTAR-ai-5B-1.0 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Fantominsight/YAPPERTAR-ai-5B-1.0"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Fantominsight/YAPPERTAR-ai-5B-1.0",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Fantominsight/YAPPERTAR-ai-5B-1.0

SGLang

How to use Fantominsight/YAPPERTAR-ai-5B-1.0 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 "Fantominsight/YAPPERTAR-ai-5B-1.0" \
    --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": "Fantominsight/YAPPERTAR-ai-5B-1.0",
		"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 "Fantominsight/YAPPERTAR-ai-5B-1.0" \
        --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": "Fantominsight/YAPPERTAR-ai-5B-1.0",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Fantominsight/YAPPERTAR-ai-5B-1.0 with Docker Model Runner:
```
docker model run hf.co/Fantominsight/YAPPERTAR-ai-5B-1.0
```

YAPPERTAR-ai-5B-1.0

File size: 1,230 Bytes

e853aa0
5448f96
e853aa0
 
 
 
5448f96
 
 
 
 
 
e853aa0
 
 
 
 
 
 
 
 
 
 
 
 
5448f96
db79cff
face299

---
license: apache-2.0
language:
- ru
- en
- zh
- pt
- es
- el
- ka
- uk
- ja
pipeline_tag: text-generation
library_name: transformers
tags:
- text-generation-inference
datasets:
- MultiLingual_90M.zip
- Yyukki90M.zxc
- VirttauallituAI.cpp
- API_LLM_AI
- LLMGoglaenLAI.rar
- MultiTrainer56-108M
base_model:
- YAPPERTAR_ai_based_on_miscrosoft_phi4
text: null
new_version: Fantominsight/YAPPERTAR-ai-32B-1.0
---
```Markdown
Это флагманская, быстрая, лёгкая модель
для генерации ткста с пятью миллиардами
параметров на основе модели и её архитектуры
семейства моделей Qwen2 от AlibabaCloud.
По лицензии права принадлежат Alibaba.
Мы команда ФантомИнсайт дообучили Qwen2-5B 
под себя. Мы не крадём, мы честно распростроняем
как семейство моделей YAPPERTAR-1.0 на основе **Qwen2**.
Формат GGUF llama.cpp. Запускается в LMStudio, GPT4ALL, Ollama и д.р 
с поддержкой GGUF. Требуется минимум 8-12 ГБ ОЗУ или видеопамяти. 
```