RichardErkhov/djuna_-_L3.1-Romes-Ninomos-8bits

Quantization made by Richard Erkhov.

Github

Discord

Request more models

L3.1-Romes-Ninomos - bnb 8bits

• Model creator: https://huggingface.co/djuna/
• Original model: https://huggingface.co/djuna/L3.1-Romes-Ninomos/

Original model description:

base_model:

• hf-100/Llama-3-Spellbound-Instruct-8B-0.3
• Sao10K/L3-8B-Tamamo-v1
• Sao10K/L3-8B-Stheno-v3.2
• Sao10K/L3.1-8B-Niitama-v1.1
• vicgalle/Roleplay-Hermes-3-Llama-3.1-8B
• Edgerunners/Lyraea-large-llama-3.1 library_name: transformers tags:
• mergekit
• merge

---

merge

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

Merge Details

Merge Method

This model was merged using the Model Stock merge method using vicgalle/Roleplay-Hermes-3-Llama-3.1-8B as a base.

Models Merged

The following models were included in the merge:

• hf-100/Llama-3-Spellbound-Instruct-8B-0.3
• Sao10K/L3-8B-Tamamo-v1
• Sao10K/L3-8B-Stheno-v3.2
• Sao10K/L3.1-8B-Niitama-v1.1
• Edgerunners/Lyraea-large-llama-3.1

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: Sao10K/L3.1-8B-Niitama-v1.1
  - model: Sao10K/L3-8B-Stheno-v3.2
  - model: Sao10K/L3-8B-Tamamo-v1
  - model: hf-100/Llama-3-Spellbound-Instruct-8B-0.3
  - model: Edgerunners/Lyraea-large-llama-3.1
base_model: vicgalle/Roleplay-Hermes-3-Llama-3.1-8B
parameters:
  normalize: false
  int8_mask: true
tokenizer_source: base
merge_method: model_stock
dtype: float32
out_dtype: bfloat16