Instructions to use MaliosDark/Isabel-50M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use MaliosDark/Isabel-50M with Transformers:

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

pipe = pipeline("text-generation", model="MaliosDark/Isabel-50M")

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

tokenizer = AutoTokenizer.from_pretrained("MaliosDark/Isabel-50M")
model = AutoModelForCausalLM.from_pretrained("MaliosDark/Isabel-50M", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use MaliosDark/Isabel-50M with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "MaliosDark/Isabel-50M"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "MaliosDark/Isabel-50M",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/MaliosDark/Isabel-50M

SGLang

How to use MaliosDark/Isabel-50M 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 "MaliosDark/Isabel-50M" \
    --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": "MaliosDark/Isabel-50M",
		"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 "MaliosDark/Isabel-50M" \
        --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": "MaliosDark/Isabel-50M",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use MaliosDark/Isabel-50M with Docker Model Runner:
```
docker model run hf.co/MaliosDark/Isabel-50M
```

MaliosDark commited on Jun 21

Commit

c418740

verified ·

1 Parent(s): c8a0b6b

Card: remove architecture model reference

Browse files

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -58,7 +58,7 @@ A two-stage, single-GPU recipe (RTX 3090 Ti):
 | | |
 |---|---|
-| Type | Decoder-only transformer (Llama-style) |
 | Hidden size | 512 |
 | Layers | 9 |
 | Heads | 8 |

 | | |
 |---|---|
+| Type | Decoder-only transformer |
 | Hidden size | 512 |
 | Layers | 9 |
 | Heads | 8 |