flammenai_-_flammen17-mistral-7B-4bits

Quantization made by Richard Erkhov.

Github

Discord

Request more models

flammen17-mistral-7B - bnb 4bits

• Model creator: https://huggingface.co/flammenai/
• Original model: https://huggingface.co/flammenai/flammen17-mistral-7B/

Original model description:

license: apache-2.0 base_model:

• nbeerbower/Flammen-Bophades-7B
• nbeerbower/flammen16-mistral-7B library_name: transformers tags:
• mergekit
• merge

---

flammen17-mistral-7B

A Mistral 7B LLM built from merging pretrained models and finetuning. Flammen specializes in exceptional character roleplay, creative writing, and general intelligence

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

Merge Details

Merge Method

This model was merged using the SLERP merge method.

Models Merged

The following models were included in the merge:

• nbeerbower/Flammen-Bophades-7B
• nbeerbower/flammen16-mistral-7B

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: nbeerbower/Flammen-Bophades-7B
    layer_range: [0, 32]
  - model: nbeerbower/flammen16-mistral-7B
    layer_range: [0, 32]
merge_method: slerp
base_model: nbeerbower/flammen16-mistral-7B
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