Instructions to use Eric111/CatunaMayo3B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Eric111/CatunaMayo3B with Transformers:

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

pipe = pipeline("text-generation", model="Eric111/CatunaMayo3B")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Eric111/CatunaMayo3B")
model = AutoModelForCausalLM.from_pretrained("Eric111/CatunaMayo3B")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Eric111/CatunaMayo3B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Eric111/CatunaMayo3B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Eric111/CatunaMayo3B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Eric111/CatunaMayo3B

SGLang

How to use Eric111/CatunaMayo3B 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 "Eric111/CatunaMayo3B" \
    --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": "Eric111/CatunaMayo3B",
		"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 "Eric111/CatunaMayo3B" \
        --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": "Eric111/CatunaMayo3B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Eric111/CatunaMayo3B with Docker Model Runner:
```
docker model run hf.co/Eric111/CatunaMayo3B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

CatunaMayo3B

CatunaMayo3B is a merge of the following models using mergekit:

🧩 Configuration

slices:
  - sources:
    - model: Eric111/CatunaMayo
      layer_range: [0, 1]
  - sources:
    - model: Eric111/CatunaLaserPi
      layer_range: [2, 3]
  - sources:
    - model: Eric111/CatunaLaserPi
      layer_range: [4, 5]
  - sources:
    - model: Eric111/CatunaLaserPi
      layer_range: [6, 7]
  - sources:
    - model: Eric111/CatunaLaserPi
      layer_range: [8, 9]
  - sources:
    - model: Eric111/CatunaLaserPi
      layer_range: [10, 11]
  - sources:
    - model: Eric111/CatunaLaserPi
      layer_range: [12, 13]
  - sources:
    - model: Eric111/CatunaLaserPi
      layer_range: [14, 15]
  - sources:
    - model: Eric111/CatunaLaserPi
      layer_range: [16, 17]
  - sources:
    - model: Eric111/CatunaLaserPi
      layer_range: [18, 19]
  - sources:
    - model: Eric111/CatunaLaserPi
      layer_range: [20, 21]
  - sources:
    - model: Eric111/CatunaLaserPi
      layer_range: [22, 23]
  - sources:
    - model: Eric111/CatunaLaserPi
      layer_range: [24, 25]
  - sources:
    - model: Eric111/CatunaLaserPi
      layer_range: [26, 27]
  - sources:
    - model: Eric111/CatunaLaserPi
      layer_range: [28, 29]
  - sources:
    - model: Eric111/CatunaLaserPi
      layer_range: [30, 32]
merge_method: passthrough
dtype: bfloat16

Downloads last month: 2

Safetensors

Model size

4B params

Tensor type

BF16

Model tree for Eric111/CatunaMayo3B

Quantizations

1 model