RichardErkhov/Weyaxi_-_Instruct-v0.2-Seraph-7B-8bits

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Instruct-v0.2-Seraph-7B - bnb 8bits

• Model creator: https://huggingface.co/Weyaxi/
• Original model: https://huggingface.co/Weyaxi/Instruct-v0.2-Seraph-7B/

Original model description:

license: apache-2.0 tags: - merge

Instruct-v0.2-Seraph-7B

This is the model for Instruct-v0.2-Seraph-7B. I used mergekit to merge models.

Yaml Config

slices:
  - sources:
      - model: Weyaxi/Seraph-7B
        layer_range: [0, 32]
      - model: mistralai/Mistral-7B-Instruct-v0.2
        layer_range: [0, 32]
merge_method: slerp
base_model: mistralai/Mistral-7B-v0.1
parameters:
  t:
    - filter: self_attn
      value: [0, 0.5, 0.3, 0.7, 1]
    - filter: mlp
      value: [1, 0.5, 0.7, 0.3, 0]
    - value: 0.5
dtype: bfloat16