[P] New LLM Pre-training and Post-training Paradigms: Comparing Qwen 2, Llama 3.1, Gemma 2, and Apple's FMs
https://magazine.sebastianraschka.com/p/new-llm-pre-training-and-post-training
Discussions: https://discu.eu/q/https://magazine.sebastianraschka.com/p/new-llm-pre-training-and-post-training
#compsci #machinelearning
Compsci Weekly /
npub12y…mwm90
2024-08-20 07:23:47
Author Public Key
npub12yxz5pw6kxawd4wshrvzkrdzyp772te52nzdeujcdjsjxngcqulsqmwm90Published at
2024-08-20 07:23:47Event JSON
{
"id": "a8642417b49ac62d5c33ba33faff90a297aa39b301b47c3bad5db1ce6a9ea88d",
"pubkey": "510c2a05dab1bae6d5d0b8d82b0da2207de52f3454c4dcf2586ca1234d18073f",
"created_at": 1724138627,
"kind": 1,
"tags": [
[
"t",
"compsci"
],
[
"t",
"machinelearning"
],
[
"proxy",
"https://mastodon.social/users/compsci_discussions/statuses/112993149068691114",
"activitypub"
]
],
"content": "[P] New LLM Pre-training and Post-training Paradigms: Comparing Qwen 2, Llama 3.1, Gemma 2, and Apple's FMs\n\nhttps://magazine.sebastianraschka.com/p/new-llm-pre-training-and-post-training\n\nDiscussions: https://discu.eu/q/https://magazine.sebastianraschka.com/p/new-llm-pre-training-and-post-training\n\n#compsci #machinelearning",
"sig": "d390580280a663f7dcdd8ad86a5b46f260a6bba75e7d69e2eb9349725564380da27764ae25daae1997bd0be4ee0b32a9e2190d1872f204aca7a708fcac3b4ad3"
}