Instructions to use zaydzuhri/scan-16M-test with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use zaydzuhri/scan-16M-test with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="zaydzuhri/scan-16M-test")# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("zaydzuhri/scan-16M-test", dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use zaydzuhri/scan-16M-test with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "zaydzuhri/scan-16M-test" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "zaydzuhri/scan-16M-test", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/zaydzuhri/scan-16M-test
- SGLang
How to use zaydzuhri/scan-16M-test 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 "zaydzuhri/scan-16M-test" \ --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": "zaydzuhri/scan-16M-test", "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 "zaydzuhri/scan-16M-test" \ --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": "zaydzuhri/scan-16M-test", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use zaydzuhri/scan-16M-test with Docker Model Runner:
docker model run hf.co/zaydzuhri/scan-16M-test
| # -*- coding: utf-8 -*- | |
| from fla.modules.convolution import (ImplicitLongConvolution, LongConvolution, | |
| ShortConvolution) | |
| from fla.modules.fused_cross_entropy import FusedCrossEntropyLoss | |
| from fla.modules.fused_kl_div import FusedKLDivLoss | |
| from fla.modules.fused_linear_cross_entropy import FusedLinearCrossEntropyLoss | |
| from fla.modules.fused_norm_gate import (FusedLayerNormSwishGate, | |
| FusedLayerNormSwishGateLinear, | |
| FusedRMSNormSwishGate, | |
| FusedRMSNormSwishGateLinear) | |
| from fla.modules.layernorm import (GroupNorm, GroupNormLinear, LayerNorm, | |
| LayerNormLinear, RMSNorm, RMSNormLinear) | |
| from fla.modules.rotary import RotaryEmbedding | |
| __all__ = [ | |
| 'ImplicitLongConvolution', 'LongConvolution', 'ShortConvolution', | |
| 'FusedCrossEntropyLoss', 'FusedLinearCrossEntropyLoss', 'FusedKLDivLoss', | |
| 'GroupNorm', 'GroupNormLinear', 'LayerNorm', 'LayerNormLinear', 'RMSNorm', 'RMSNormLinear', | |
| 'FusedLayerNormSwishGate', 'FusedLayerNormSwishGateLinear', 'FusedRMSNormSwishGate', 'FusedRMSNormSwishGateLinear', | |
| 'RotaryEmbedding' | |
| ] | |