Edit model card

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
Downloads last month
49
Safetensors
Model size
12.2B params
Tensor type
BF16
·
Inference API
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for v000000/MN-12B-Estrella-v2.2

Collections including v000000/MN-12B-Estrella-v2.2