Instructions to use ViorikaAI-org/CalmaCatLM-2.1-mini with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ViorikaAI-org/CalmaCatLM-2.1-mini with Transformers:

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

pipe = pipeline("text-generation", model="ViorikaAI-org/CalmaCatLM-2.1-mini")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ViorikaAI-org/CalmaCatLM-2.1-mini")
model = AutoModelForCausalLM.from_pretrained("ViorikaAI-org/CalmaCatLM-2.1-mini", 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=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use ViorikaAI-org/CalmaCatLM-2.1-mini with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ViorikaAI-org/CalmaCatLM-2.1-mini"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ViorikaAI-org/CalmaCatLM-2.1-mini",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ViorikaAI-org/CalmaCatLM-2.1-mini

SGLang

How to use ViorikaAI-org/CalmaCatLM-2.1-mini 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 "ViorikaAI-org/CalmaCatLM-2.1-mini" \
    --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": "ViorikaAI-org/CalmaCatLM-2.1-mini",
		"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 "ViorikaAI-org/CalmaCatLM-2.1-mini" \
        --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": "ViorikaAI-org/CalmaCatLM-2.1-mini",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use ViorikaAI-org/CalmaCatLM-2.1-mini with Docker Model Runner:
```
docker model run hf.co/ViorikaAI-org/CalmaCatLM-2.1-mini
```

CalmaCatLM-2.1-mini / README.md

Dmitriy-Zemskov

Update README.md

6891acf verified 1 day ago

preview code

Raw

History Blame Contribute Delete

1.01 kB

metadata

license: mit
language:
  - ru
tags:
  - llama
  - russian
  - conversational
model-index:
  - name: CalmaCatLM-2
    results: []
library_name: transformers
model_creator: ViorikaAI
pipeline_tag: text-generation
datasets:
  - IlyaGusev/saiga_scored
  - IlyaGusev/ru_turbo_alpaca
  - OpenAssistant/oasst1
  - OpenAssistant/oasst2

🐈‍⬛ CalmaCatLM-2-MINI

Подробнее:

⚙️ Детали модели

Архитектура: LLama
Параметры: 134M
Язык: Русский
Лицения: MIT

🏋️ Детали Тренировки

Датасет: saiga_scored, ru_turbo_alpaca, oasst 1 и 2 (RU часть)
Железо: ОДНА NVIDIA GEFORCE RTX 5060 TI (16GB VRAM)
Эпохи: 3
СРЕДНИЙ LOSS: 2.3000
LR: 5e-4
Контекст: 2048 токенов

🛜 Наши Соц. Сети

Discord: https://discord.gg/8JwTv8zj8d , https://discord.gg/7JE7maH6cf
Telegram: https://t.me/viorika_official