amirwanhf/Meta-Llama-3.1-70B-Instruct-plus-Swallow

Merged model to upgrade Swallow-70b to llama-3.1-70b:

Meta-Llama-3.1-70B-Instruct + 0.7*(tokyotech-llm/Llama-3-Swallow-70B-Instruct-v0.1 - meta-llama/Meta-Llama-3-70B)

Safetensors

Model size

70.6B params

Tensor type

BF16

Inference Providers NEW

This model is not currently available via any of the supported Inference Providers.

Model tree for amirwanhf/Meta-Llama-3.1-70B-Instruct-plus-Swallow

Base model

Finetuned

Finetuned

(61)

this model