princeton-nlp/Llama-3-8B-ProLong-64k-Instruct

Text generation · served with vLLM · ↓ 8.7K downloads a month · View on Hugging Face

Weights: 16 GB
GPU memory needed: about 21.3 GB
Conversation length: 8,192 tokens
Model allows: 65,536 tokens
Memory · disk: 16 GB · 58 GB
Architecture: LlamaForCausalLM
Licence: llama3

Versions of Llama-3 8B

The same model packaged differently: a quantized version needs less GPU memory and runs on a cheaper machine.

Version	Runtime	Weights	GPU memory	Cheapest machine now
Originalprinceton-nlp/Llama-3-8B-ProLong-64k-Base	vLLM	16 GB	21.3 GB	$0.16/h 2x RTX 3060
Instructprinceton-nlp/Llama-3-8B-ProLong-64k-Instruct	vLLM	16 GB	21.3 GB	$0.16/h 2x RTX 3060

Hardware and deploy

Endpoint name

$0.58/h from your balance while it runs, billed by the hour; stop it from its page. GridPup rents the machine with vLLM, which downloads the model from Hugging Face (usually ready in 10 to 15 minutes), and gives you an https address, keys and a Playground.

Loading…