Instructions to use goldfish-models/mai_deva_5mb with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use goldfish-models/mai_deva_5mb with Transformers:

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

pipe = pipeline("text-generation", model="goldfish-models/mai_deva_5mb")

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

tokenizer = AutoTokenizer.from_pretrained("goldfish-models/mai_deva_5mb")
model = AutoModelForCausalLM.from_pretrained("goldfish-models/mai_deva_5mb", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use goldfish-models/mai_deva_5mb with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "goldfish-models/mai_deva_5mb"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "goldfish-models/mai_deva_5mb",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/goldfish-models/mai_deva_5mb

SGLang

How to use goldfish-models/mai_deva_5mb 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 "goldfish-models/mai_deva_5mb" \
    --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": "goldfish-models/mai_deva_5mb",
		"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 "goldfish-models/mai_deva_5mb" \
        --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": "goldfish-models/mai_deva_5mb",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use goldfish-models/mai_deva_5mb with Docker Model Runner:
```
docker model run hf.co/goldfish-models/mai_deva_5mb
```

mai_deva_5mb

Commit History

Feb 15, 2025

01:01
Adding `safetensors` variant of this model⁠

SFconvertbot

Verified signature
62f48a5

Aug 26, 2024

16:48
Upload config.json with huggingface_hub

goldfish-models

Verified signature
b8a1e9d

Aug 25, 2024

23:38
Upload README.md with huggingface_hub

goldfish-models

Verified signature
8766527

Aug 17, 2024

01:18
Upload README.md with huggingface_hub

goldfish-models

Verified signature
2c97f26
00:49
Upload README.md with huggingface_hub

goldfish-models

Verified signature
4a5a01b

Aug 15, 2024

00:01
Upload mai_deva_5mb tokenizer.

goldfish-models

0016d2a
00:00
Upload mai_deva_5mb model.

goldfish-models

54d1e00
00:00
initial commit

goldfish-models

Verified signature
dc27f71

Commit History

Feb 15, 2025

Adding `safetensors` variant of this model⁠

Aug 26, 2024

Upload config.json with huggingface_hub

Aug 25, 2024

Upload README.md with huggingface_hub

Aug 17, 2024

Upload README.md with huggingface_hub

Upload README.md with huggingface_hub

Aug 15, 2024

Upload mai_deva_5mb tokenizer.

Upload mai_deva_5mb model.

initial commit