v000000's picture
Update README.md
5650add verified
metadata
base_model:
  - anthracite-org/magnum-v2.5-12b-kto
  - TheDrummer/Rocinante-12B-v1.1
  - v000000/MN-12B-Estrella-v1
  - elinas/Chronos-Gold-12B-1.0
library_name: transformers
tags:
  - mergekit
  - merge
  - mistral
license: cc-by-nc-4.0

Temperature:
Mistral Nemo likes low temperature between 0.3-0.6

Mistral-Nemo-2407-12B-Estrella-v2.2

image/png

Prompt Format: Seems best with "Mistral Instruct" but ChatML might also work.

[INST] System Message [/INST]

[INST] Name: Let's get started. Please respond based on the information and instructions provided above. [/INST]

<s>[INST] Name: What is your favourite condiment? [/INST]
AssistantName: Well, I'm quite partial to a good squeeze of fresh lemon juice. It adds just the right amount of zesty flavour to whatever I'm cooking up in the kitchen!</s> 
[INST] Name: Do you have mayonnaise recipes? [/INST]

Thanks mradermacher for the quants!


merge

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

Merge Details

Merge Method

This model was merged using the della_linear merge method using anthracite-org/magnum-v2.5-12b-kto as a base.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: v000000/MN-12B-Estrella-v1
    parameters:
      weight: 0.25
      density: 0.84
  - model: elinas/Chronos-Gold-12B-1.0
    parameters:
      weight: 0.4
      density: 0.88
  - model: TheDrummer/Rocinante-12B-v1.1
    parameters:
      weight: 0.6
      density: 0.9
merge_method: della_linear
base_model: anthracite-org/magnum-v2.5-12b-kto
parameters:
  int8_mask: true
  epsilon: 0.07
  lambda: 1
dtype: bfloat16