EDIT: Base Mistral, but with some minor head trauma. Promising in theory, needs finetuning, but only really outperforms the 14b in size.

A 11b Mistral base model, based on the NeverSleep recipe.

Recipe

slices

  • sources:

    • model: mistralai/Mistral-7B-v0.1
    • layer_range: [0, 24]
  • sources:

    • model: mistralai/Mistral-7B-v0.1
    • layer_range: [8, 32]

merge_method: passthrough

dtype: bfloat16

Downloads last month
16
Safetensors
Model size
10.7B params
Tensor type
BF16
·
Inference Providers NEW
This model is not currently available via any of the supported Inference Providers.

Model tree for athirdpath/BigMistral-11b

Quantizations
1 model