You can deploy this model and start earning money today!

RichardErkhov/
Nohobby_-_MN-12B-Siskin-v0.1-gguf

Name: Nohobby_-_MN-12B-Siskin-v0.1-gguf
Availability: InStock

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

MN-12B-Siskin-v0.1 - GGUF

Model creator: https://huggingface.co/Nohobby/
Original model: https://huggingface.co/Nohobby/MN-12B-Siskin-v0.1/

Name	Quant method	Size
MN-12B-Siskin-v0.1.Q2_K.gguf	Q2_K	4.46GB
MN-12B-Siskin-v0.1.IQ3_XS.gguf	IQ3_XS	4.94GB
MN-12B-Siskin-v0.1.IQ3_S.gguf	IQ3_S	5.18GB
MN-12B-Siskin-v0.1.Q3_K_S.gguf	Q3_K_S	5.15GB
MN-12B-Siskin-v0.1.IQ3_M.gguf	IQ3_M	5.33GB
MN-12B-Siskin-v0.1.Q3_K.gguf	Q3_K	5.67GB
MN-12B-Siskin-v0.1.Q3_K_M.gguf	Q3_K_M	5.67GB
MN-12B-Siskin-v0.1.Q3_K_L.gguf	Q3_K_L	6.11GB
MN-12B-Siskin-v0.1.IQ4_XS.gguf	IQ4_XS	6.33GB
MN-12B-Siskin-v0.1.Q4_0.gguf	Q4_0	6.59GB
MN-12B-Siskin-v0.1.IQ4_NL.gguf	IQ4_NL	6.65GB
MN-12B-Siskin-v0.1.Q4_K_S.gguf	Q4_K_S	6.63GB
MN-12B-Siskin-v0.1.Q4_K.gguf	Q4_K	6.96GB
MN-12B-Siskin-v0.1.Q4_K_M.gguf	Q4_K_M	6.96GB
MN-12B-Siskin-v0.1.Q4_1.gguf	Q4_1	7.26GB
MN-12B-Siskin-v0.1.Q5_0.gguf	Q5_0	7.93GB
MN-12B-Siskin-v0.1.Q5_K_S.gguf	Q5_K_S	7.93GB
MN-12B-Siskin-v0.1.Q5_K.gguf	Q5_K	8.13GB
MN-12B-Siskin-v0.1.Q5_K_M.gguf	Q5_K_M	8.13GB
MN-12B-Siskin-v0.1.Q5_1.gguf	Q5_1	8.61GB
MN-12B-Siskin-v0.1.Q6_K.gguf	Q6_K	9.37GB
MN-12B-Siskin-v0.1.Q8_0.gguf	Q8_0	12.13GB

Original model description:

base_model:

nbeerbower/Lyra-Gutenberg-mistral-nemo-12B
NeverSleep/Lumimaid-v0.2-12B
ArliAI/Mistral-Nemo-12B-ArliAI-RPMax-v1.1
v000000/NM-12B-Lyris-dev-3 library_name: transformers tags:
mergekit
merge

Siskin 0.1

The 0.2 version writes more — check it out here

Overview

Somewhat experimental merge of some Nemo models. Consists mostly of human data, so there should be very little gptisms/claudisms. Models work with about ~28k context and could maybe be stretched further.

Note: Both v0.1 and v0.2 can write in the first person despite the initial message. Specify the narrative style somewhere in the prompt to fix this if you don't like it.

Prompt template: Mistral

<s>[INST] {input} [/INST] {output}</s>

Quants

Static

Imatrix

Merge Details

Merge Method

This model was merged using the della_linear merge method using ArliAI/Mistral-Nemo-12B-ArliAI-RPMax-v1.1 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: ArliAI/Mistral-Nemo-12B-ArliAI-RPMax-v1.1
    parameters:
      weight: [0.2, 0.3, 0.2, 0.3, 0.2]
      density: [0.45, 0.55, 0.45, 0.55, 0.45]
  - model: NeverSleep/Lumimaid-v0.2-12B
    parameters:
      weight: [0.01768, -0.01675, 0.01285, -0.01696, 0.01421]
      density: [0.6, 0.4, 0.5, 0.4, 0.6]
  - model: v000000/NM-12B-Lyris-dev-3
    parameters:
      weight: [0.208, 0.139, 0.139, 0.139, 0.208]
      density: [0.7]
  - model: nbeerbower/Lyra-Gutenberg-mistral-nemo-12B
    parameters:
      weight: [0.33]
      density: [0.45, 0.55, 0.45, 0.55, 0.45]
merge_method: della_linear
base_model: ArliAI/Mistral-Nemo-12B-ArliAI-RPMax-v1.1
parameters:
  epsilon: 0.04
  lambda: 1.05
  int8_mask: true
  rescale: true
  normalize: false
dtype: bfloat16
tokenizer_source: base

RichardErkhov/Nohobby_-_MN-12B-Siskin-v0.1-gguf