Closed CSEEduanyu closed 2 days ago
The actual load of the LLM part may be 20B?
the LLM base for this model is Yi-34B, which totals ~70GB using the bfloat16
dtype
https://huggingface.co/NousResearch/Nous-Hermes-2-Yi-34B/blob/fcb0a8847e76aea14aba9aa44009d4418ad7c18f/config.json#L25
our model is stored in float32
, which is likely the cause of the increased size
https://huggingface.co/nyu-visionx/cambrian-34b/blob/7fc61cdc8e5207071c5c3a842c9cb181aa1cfbc7/config.json#L64
the LLM base for this model is Yi-34B, which totals ~70GB using the
bfloat16
dtype https://huggingface.co/NousResearch/Nous-Hermes-2-Yi-34B/blob/fcb0a8847e76aea14aba9aa44009d4418ad7c18f/config.json#L25our model is stored in
float32
, which is likely the cause of the increased size https://huggingface.co/nyu-visionx/cambrian-34b/blob/7fc61cdc8e5207071c5c3a842c9cb181aa1cfbc7/config.json#L64
I didn't change config. Why did I successfully load the model in A100*1? Only 80 gigabytes of video memory.
the LLM base for this model is Yi-34B, which totals ~70GB using the
bfloat16
dtype https://huggingface.co/NousResearch/Nous-Hermes-2-Yi-34B/blob/fcb0a8847e76aea14aba9aa44009d4418ad7c18f/config.json#L25our model is stored in
float32
, which is likely the cause of the increased size https://huggingface.co/nyu-visionx/cambrian-34b/blob/7fc61cdc8e5207071c5c3a842c9cb181aa1cfbc7/config.json#L64
The other question is, if you change the dtype to fp16, what will happen?
https://huggingface.co/nyu-visionx/cambrian-34b/tree/main