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

Libraries

How to use ViorikaAI-org/CalmaCatMath with Transformers:

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

pipe = pipeline("text-generation", model="ViorikaAI-org/CalmaCatMath")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ViorikaAI-org/CalmaCatMath")
model = AutoModelForCausalLM.from_pretrained("ViorikaAI-org/CalmaCatMath")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use ViorikaAI-org/CalmaCatMath with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ViorikaAI-org/CalmaCatMath"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ViorikaAI-org/CalmaCatMath",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/ViorikaAI-org/CalmaCatMath

SGLang

How to use ViorikaAI-org/CalmaCatMath 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/CalmaCatMath" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ViorikaAI-org/CalmaCatMath",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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/CalmaCatMath" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ViorikaAI-org/CalmaCatMath",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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

Dmitriy-Zemskov commited on about 23 hours ago

Commit

36fe8b9

verified ·

1 Parent(s): 27163d5

Update README.md

Browse files

Files changed (1) hide show

README.md +1 -22

README.md CHANGED Viewed

@@ -18,25 +18,4 @@ The first generation of the CalmaCatMath series. This is an ultra-compact langua
 ### Model Features
 - **Size:** ~19M parameters — runs lightning-fast even on a potato.
 - **Vocabulary:** Custom Char tokenzier.
-- **Lore:** Basic NLP, Basic Arithmetic.
-## How to run
-```python
-from transformers import GPT2LMHeadModel
-import torch
-from tokenizer import CharTokenizer
-model = GPT2LMHeadModel.from_pretrained("ViorikaAI-org/CalmaCatMath")
-tokenizer = CharTokenizer()
-text = "<s> 2+2="
-ids = torch.tensor([tokenizer.encode(text)])
-with torch.no_grad():
-    out = model.generate(ids, max_new_tokens=16)
-print(tokenizer.decode(out[0].tolist()))
-```

 ### Model Features
 - **Size:** ~19M parameters — runs lightning-fast even on a potato.
 - **Vocabulary:** Custom Char tokenzier.
+- **Lore:** Basic NLP, Basic Arithmetic.