intervitens/Nous-Hermes-2-Mixtruct-v0.1-8x7B-DPO-DARE_TIES-3.5bpw-h6-exl2-rpcal

Quantized using 200 samples of 8192 tokens from an RP-oriented PIPPA dataset. For purposes other than RP, use quantizations done on a more general dataset.

Requires ExllamaV2 version 0.0.11 and up.

Original model link: notstoic/Nous-Hermes-2-Mixtruct-v0.1-8x7B-DPO-DARE_TIES

Original model README below.

---

Nous-Hermes-2-Mixtruct-v0.1-8x7B-DPO-DARE_TIES

This is a merge of pre-trained language models created using mergekit.

Merge Details

An experimental merge.

Prompt format: ChatML or Mixtral-8x7B-Instruct-v0.1

Merge Method

This model was merged using the DARE TIES merge method using ./models/Mixtral-8x7B-v0.1 as a base.

Models Merged

The following models were included in the merge:

• Mixtral-8x7B-Instruct-v0.1
• Nous-Hermes-2-Mixtral-8x7B-DPO

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: ./models/Mixtral-8x7B-Instruct-v0.1
    parameters:
      density: 0.5
      weight: 1.0
  - model: ./models/Nous-Hermes-2-Mixtral-8x7B-DPO
    parameters:
      density: 0.5
      weight: 0.5
merge_method: dare_ties
base_model: ./models/Mixtral-8x7B-v0.1
parameters:
  #normalize: false
  #int8_mask: true
dtype: bfloat16