Instructions to use Dmitriy-Zemskov/CalmaCatLM-2-mini with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Dmitriy-Zemskov/CalmaCatLM-2-mini with Transformers:

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

pipe = pipeline("text-generation", model="Dmitriy-Zemskov/CalmaCatLM-2-mini")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Dmitriy-Zemskov/CalmaCatLM-2-mini")
model = AutoModelForCausalLM.from_pretrained("Dmitriy-Zemskov/CalmaCatLM-2-mini", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Dmitriy-Zemskov/CalmaCatLM-2-mini with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Dmitriy-Zemskov/CalmaCatLM-2-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": "Dmitriy-Zemskov/CalmaCatLM-2-mini",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Dmitriy-Zemskov/CalmaCatLM-2-mini

SGLang

How to use Dmitriy-Zemskov/CalmaCatLM-2-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 "Dmitriy-Zemskov/CalmaCatLM-2-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": "Dmitriy-Zemskov/CalmaCatLM-2-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 "Dmitriy-Zemskov/CalmaCatLM-2-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": "Dmitriy-Zemskov/CalmaCatLM-2-mini",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Dmitriy-Zemskov/CalmaCatLM-2-mini with Docker Model Runner:
```
docker model run hf.co/Dmitriy-Zemskov/CalmaCatLM-2-mini
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

🐈‍⬛ CalmaCatLM-2-MINI

Подробнее:

⚙️ Детали модели

Архитектура: GPT-3
Параметры: 125M
Язык: Русский
Лицения: MIT

🏋️ Детали Тренировки

Датасет: ``
Железо: ОДНА NVIDIA GEFORCE RTX 5060 TI (16GB VRAM)
Эпохи: ...
Шагов: - 20 тысяч
СРЕДНИЙ LOSS: 0.9000
Оптимизатор: 3e-4
Контекст: 1024 токенов

🏋️ Использование

from transformers import GPT2LMHeadModel, GPT2Tokenizer

model = GPT2LMHeadModel.from_pretrained("ViorikaAI/CalmaCatLM-2-mini")
tokenizer = GPT2Tokenizer.from_pretrained("ViorikaAI/CalmaCatLM-2-mini")
tokenizer.pad_token = tokenizer.eos_token

inputs = tokenizer("Привет, как дела?", return_tensors="pt")
outputs = model.generate(
    **inputs,
    max_new_tokens=80,
    temperature=0.7,
    top_k=50,
    do_sample=True,
    pad_token_id=tokenizer.eos_token_id,
)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

🛜 Наши Соц. Сети

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

Downloads last month: 38

Safetensors

Model size

0.1B params

Tensor type

F32

Model tree for Dmitriy-Zemskov/CalmaCatLM-2-mini

Quantizations

1 model