Commit History

Remove HF token from deploy instructions (public repo)
76f5b5c
verified

fjcloud commited on

Fix inf2.8xlarge RAM: 128 GB not 64 GB
f7560a5
verified

fjcloud commited on

Update README with full usage docs
435860a
verified

fjcloud commited on

Flatten neuron-compiled-artifacts: remove config hash subdirectory (NEURON_COMPILED_ARTIFACTS bypasses it)
1b28791
verified

fjcloud commited on

Remove unused config hash 12977ce134e2dd00f6da83766f597687 (HF repo ID path, never works without manual download)
0ea2bfa
verified

fjcloud commited on

Add artifacts under local-path config hash 9162fb3509769803a65ed3c85cbf836c
ce1ee2b
verified

fjcloud commited on

Reorganize artifacts into config hash subdirectory 12977ce134e2dd00f6da83766f597687
5af84c9
verified

fjcloud commited on

Upload model.safetensors with huggingface_hub
40572f4
verified

fjcloud commited on

Delete model.safetensors.index.json with huggingface_hub
63149ca
verified

fjcloud commited on

Move compiled artifacts to neuron-compiled-artifacts/ subdirectory
b0a194e
verified

fjcloud commited on

Upload tokenizer_config.json with huggingface_hub
e4ff2ec
verified

fjcloud commited on

Upload tokenizer.model.v3 with huggingface_hub
c287d51
verified

fjcloud commited on

Upload tokenizer.model with huggingface_hub
042d895
verified

fjcloud commited on

Upload tokenizer.json with huggingface_hub
8eca4c4
verified

fjcloud commited on

Upload special_tokens_map.json with huggingface_hub
d8e4830
verified

fjcloud commited on

Upload params.json with huggingface_hub
9671906
verified

fjcloud commited on

Upload model.safetensors.index.json with huggingface_hub
3ef40d7
verified

fjcloud commited on

Upload generation_config.json with huggingface_hub
8d3d2a4
verified

fjcloud commited on

Upload config.json with huggingface_hub
b3e326e
verified

fjcloud commited on

Upload README.md with huggingface_hub
f56fc47
verified

fjcloud commited on

Upload README.md with huggingface_hub
72a3a54
verified

fjcloud commited on

Upload weights/tp1_sharded_checkpoint.safetensors with huggingface_hub
5c9c6bc
verified

fjcloud commited on

Upload weights/tp0_sharded_checkpoint.safetensors with huggingface_hub
441c9f6
verified

fjcloud commited on

Upload model.pt with huggingface_hub
2432603
verified

fjcloud commited on

Upload neuron_config.json with huggingface_hub
70d1706
verified

fjcloud commited on

initial commit
b0c7994
verified

fjcloud commited on