You can deploy this model and start earning money today!

RichardErkhov/
v000000_-_MN-12B-Estrella-v2.2-gguf

Name: v000000_-_MN-12B-Estrella-v2.2-gguf
Availability: InStock

endpoints_compatible

gguf

template

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

MN-12B-Estrella-v2.2 - GGUF

Model creator: https://huggingface.co/v000000/
Original model: https://huggingface.co/v000000/MN-12B-Estrella-v2.2/

Name	Quant method	Size
MN-12B-Estrella-v2.2.Q2_K.gguf	Q2_K	4.46GB
MN-12B-Estrella-v2.2.IQ3_XS.gguf	IQ3_XS	4.94GB
MN-12B-Estrella-v2.2.IQ3_S.gguf	IQ3_S	5.18GB
MN-12B-Estrella-v2.2.Q3_K_S.gguf	Q3_K_S	5.15GB
MN-12B-Estrella-v2.2.IQ3_M.gguf	IQ3_M	5.33GB
MN-12B-Estrella-v2.2.Q3_K.gguf	Q3_K	5.67GB
MN-12B-Estrella-v2.2.Q3_K_M.gguf	Q3_K_M	5.67GB
MN-12B-Estrella-v2.2.Q3_K_L.gguf	Q3_K_L	6.11GB
MN-12B-Estrella-v2.2.IQ4_XS.gguf	IQ4_XS	6.33GB
MN-12B-Estrella-v2.2.Q4_0.gguf	Q4_0	6.59GB
MN-12B-Estrella-v2.2.IQ4_NL.gguf	IQ4_NL	6.65GB
MN-12B-Estrella-v2.2.Q4_K_S.gguf	Q4_K_S	6.63GB
MN-12B-Estrella-v2.2.Q4_K.gguf	Q4_K	6.96GB
MN-12B-Estrella-v2.2.Q4_K_M.gguf	Q4_K_M	6.96GB
MN-12B-Estrella-v2.2.Q4_1.gguf	Q4_1	7.26GB
MN-12B-Estrella-v2.2.Q5_0.gguf	Q5_0	7.93GB
MN-12B-Estrella-v2.2.Q5_K_S.gguf	Q5_K_S	7.93GB
MN-12B-Estrella-v2.2.Q5_K.gguf	Q5_K	8.13GB
MN-12B-Estrella-v2.2.Q5_K_M.gguf	Q5_K_M	8.13GB
MN-12B-Estrella-v2.2.Q5_1.gguf	Q5_1	8.61GB
MN-12B-Estrella-v2.2.Q6_K.gguf	Q6_K	9.37GB
MN-12B-Estrella-v2.2.Q8_0.gguf	Q8_0	12.13GB

Original model description:

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

[!WARNING] Temperature:
Mistral Nemo likes low temperature between 0.3-0.6

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

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:

yaml

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

RichardErkhov/v000000_-_MN-12B-Estrella-v2.2-gguf