Instructions to use vtava/Tiny-LLM-PDelta3-GDN2-InputRoute with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use vtava/Tiny-LLM-PDelta3-GDN2-InputRoute with Transformers:

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

pipe = pipeline("text-generation", model="vtava/Tiny-LLM-PDelta3-GDN2-InputRoute")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("vtava/Tiny-LLM-PDelta3-GDN2-InputRoute", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use vtava/Tiny-LLM-PDelta3-GDN2-InputRoute with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "vtava/Tiny-LLM-PDelta3-GDN2-InputRoute"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "vtava/Tiny-LLM-PDelta3-GDN2-InputRoute",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/vtava/Tiny-LLM-PDelta3-GDN2-InputRoute

SGLang

How to use vtava/Tiny-LLM-PDelta3-GDN2-InputRoute 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 "vtava/Tiny-LLM-PDelta3-GDN2-InputRoute" \
    --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": "vtava/Tiny-LLM-PDelta3-GDN2-InputRoute",
		"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 "vtava/Tiny-LLM-PDelta3-GDN2-InputRoute" \
        --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": "vtava/Tiny-LLM-PDelta3-GDN2-InputRoute",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use vtava/Tiny-LLM-PDelta3-GDN2-InputRoute with Docker Model Runner:
```
docker model run hf.co/vtava/Tiny-LLM-PDelta3-GDN2-InputRoute
```

Tiny-LLM-PDelta3-GDN2-InputRoute / validation_context_summary.csv

vtava

Upload conv4_gdn2_inputroute_f96 from TinyCeNN Tiny-LLM compatibility benchmark

c21da77 verified 26 days ago

Raw History Blame Contribute Delete

1.75 kB

	candidate_nll,candidate_ppl,context,delta_nll,name,state_bytes,state_vs_transformer_fp16,transformer_nll,transformer_ppl
	4.329811489582061,75.92997162928616,256,0.23298438787460274,conv4_pdelta_f96,19392,0.197265625,4.096827101707459,60.14913741228434
	4.29708606004715,73.48534951669176,512,0.21623675823211652,conv4_pdelta_f96,19392,0.0986328125,4.080849301815033,59.19572354203201
	4.334633874893188,76.29701952100608,1024,0.23117593526840174,conv4_pdelta_f96,19392,0.04931640625,4.1034579396247866,60.54930183986028
	4.336314916610718,76.42538585809872,256,0.2394878149032591,conv4_channel_decay_f96,19392,0.197265625,4.096827101707459,60.14913741228434
	4.303501772880554,73.95832603505018,512,0.22265247106552088,conv4_channel_decay_f96,19392,0.0986328125,4.080849301815033,59.19572354203201
	4.337036406993866,76.48054593536355,1024,0.23357846736907906,conv4_channel_decay_f96,19392,0.04931640625,4.1034579396247866,60.54930183986028
	4.306775999069214,74.20087919328297,256,0.20994889736175537,conv4_gdn2_f96,20736,0.2109375,4.096827101707459,60.14913741228434
	4.280840587615967,72.30118995581762,512,0.19999128580093384,conv4_gdn2_f96,20736,0.10546875,4.080849301815033,59.19572354203201
	4.316916954517365,74.95717530459878,1024,0.21345901489257812,conv4_gdn2_f96,20736,0.052734375,4.1034579396247866,60.54930183986028
	4.302966368198395,73.91873899949412,256,0.20613926649093628,conv4_gdn2_inputroute_f96,20736,0.2109375,4.096827101707459,60.14913741228434
	4.277678978443146,72.07296282305448,512,0.1968296766281128,conv4_gdn2_inputroute_f96,20736,0.10546875,4.080849301815033,59.19572354203201
	4.313992857933044,74.73831342690009,1024,0.21053491830825788,conv4_gdn2_inputroute_f96,20736,0.052734375,4.1034579396247866,60.54930183986028