[KongchangAI]
ModelLlama 3 8B

Llama3-8B

An open-source large language model in the Llama 3 series released by Meta, with 8 billion parameters, supporting long-context reasoning.

Timeline (last 90 days)

Nov 11

In the code output prediction task on the coding benchmark LiveCodeBench, the compositional generalization performance of the pretrained model Llama3-8B is affected by compositional equivalence.

Unverified50%
Nov 10

LongCapHarness was applied on Llama3-8B and successfully transferred to Qwen2.5-3B.

Unverified50%

All Facts (2)

Source Articles