Dmitry Baranchuk f055135b08 rm prefix 3 anos atrás
..
__init__.py 05faa0b3c8 add quantization script for cpu 3 anos atrás
config.json a798ea04a6 add minimalistic benchmarks 3 anos atrás
convert_model.py 5695897620 fix imports 3 anos atrás
deploy_server.sh f055135b08 rm prefix 3 anos atrás
inference_one_block.py 4695071ad2 WIP: make DistributedBloom compliant with HF interface 3 anos atrás
local_server_config_example.cfg f60a7dd183 deploy swarm on local & remote machines 3 anos atrás
remote_server_config_example.cfg f60a7dd183 deploy swarm on local & remote machines 3 anos atrás
run_local_servers.sh d969172208 set requires_grad=False, lm_layer -> h @ word_embeddings, rm lm_layer from comverted_model 3 anos atrás
run_remote_servers.sh f60a7dd183 deploy swarm on local & remote machines 3 anos atrás
run_server.py 9c492bbe8c Infer prefix by defaukt 3 anos atrás