metadata

base_model:
  - akjindal53244/Llama-3.1-Storm-8B
  - Sao10K/L3.1-8B-Niitama-v1.1
library_name: transformers
tags:
  - merge
  - llama

QuantFactory/L3.1-Niitorm-8B-t0.0001-GGUF

This is quantized version of v000000/L3.1-Niitorm-8B-t0.0001 created using llama.cpp

Original Model Card

Llama-3.1-Niitorm-8B

RP model, Niitama 1.1 as a base, nearswapped with one of the smartest 3.1 models "Storm", mostly abliterated.

Thank you mradermacher for the quants!

merge

This is a merge of pre-trained language models.

Merge Details

Merge Method

This model was merged using the NEARSWAP t0.0001 merge algorithm.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

slices:
  - sources:
      - model: Sao10K/L3.1-8B-Niitama-v1.1+grimjim/Llama-3-Instruct-abliteration-LoRA-8B
        layer_range: [0, 32]
      - model: akjindal53244/Llama-3.1-Storm-8B
        layer_range: [0, 32]
merge_method: nearswap
base_model: Sao10K/L3.1-8B-Niitama-v1.1+grimjim/Llama-3-Instruct-abliteration-LoRA-8B
parameters:
  t:
    - value: 0.0001
dtype: bfloat16
out_type: float16 #oops

Prompt Template:

<|begin_of_text|><|start_header_id|>system<|end_header_id|>

{system_prompt}<|eot_id|><|start_header_id|>user<|end_header_id|>

{input}<|eot_id|><|start_header_id|>assistant<|end_header_id|>

{output}<|eot_id|>