Instructions to use CycleCoreTechnologies/Maaza-SLM-360M-JSON-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use CycleCoreTechnologies/Maaza-SLM-360M-JSON-v1 with Transformers:

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

pipe = pipeline("text-generation", model="CycleCoreTechnologies/Maaza-SLM-360M-JSON-v1")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("CycleCoreTechnologies/Maaza-SLM-360M-JSON-v1")
model = AutoModelForCausalLM.from_pretrained("CycleCoreTechnologies/Maaza-SLM-360M-JSON-v1")

PEFT
How to use CycleCoreTechnologies/Maaza-SLM-360M-JSON-v1 with PEFT:
```
Task type is invalid.
```
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use CycleCoreTechnologies/Maaza-SLM-360M-JSON-v1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "CycleCoreTechnologies/Maaza-SLM-360M-JSON-v1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "CycleCoreTechnologies/Maaza-SLM-360M-JSON-v1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/CycleCoreTechnologies/Maaza-SLM-360M-JSON-v1

SGLang

How to use CycleCoreTechnologies/Maaza-SLM-360M-JSON-v1 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 "CycleCoreTechnologies/Maaza-SLM-360M-JSON-v1" \
    --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": "CycleCoreTechnologies/Maaza-SLM-360M-JSON-v1",
		"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 "CycleCoreTechnologies/Maaza-SLM-360M-JSON-v1" \
        --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": "CycleCoreTechnologies/Maaza-SLM-360M-JSON-v1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use CycleCoreTechnologies/Maaza-SLM-360M-JSON-v1 with Docker Model Runner:
```
docker model run hf.co/CycleCoreTechnologies/Maaza-SLM-360M-JSON-v1
```

CycleCore-Technologies commited on Nov 23, 2025

Commit

afd1859

verified ·

1 Parent(s): 0375f72

Upload adapter_config.json with huggingface_hub

Browse files

Files changed (1) hide show

adapter_config.json +1 -1

adapter_config.json CHANGED Viewed

@@ -9,7 +9,7 @@
     "layers_pattern": null,
     "layers_to_transform": null,
     "loftq_config": {},
-    "lora_alpha": 32,
     "lora_dropout": 0.1,
     "modules_to_save": null,
     "peft_type": "LORA",

     "layers_pattern": null,
     "layers_to_transform": null,
     "loftq_config": {},
+    "lora_alpha": 64,
     "lora_dropout": 0.1,
     "modules_to_save": null,
     "peft_type": "LORA",