Hugging Face's logo

MrRobotoAI
/
Frejya-0.8c

Text Generation
Transformers
Safetensors
mistral
mergekit
Merge
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
Frejya-0.8c / README.md
MrRobotoAI's picture
MrRobotoAI
Upload folder using huggingface_hub
d1efbb3 verified
preview code
|
raw
history blame contribute delete
6.13 kB
metadata
base_model:
  - MrRobotoAI/Frejya-0.8b
  - ResplendentAI/Aura_Llama3
  - MrRobotoAI/Frejya-0.8b
  - ResplendentAI/Theory_of_Mind_Llama3
  - MrRobotoAI/Frejya-0.8b
  - Azazelle/Nimue-8B
  - MrRobotoAI/Frejya-0.8b
  - Azazelle/Smarts_Llama3
  - MrRobotoAI/Frejya-0.8b
  - Blackroot/Llama-3-LongStory-LORA
  - MrRobotoAI/Frejya-0.8b
  - ResplendentAI/Luna_Llama3
  - MrRobotoAI/Frejya-0.8b
  - vincentyandex/lora_llama3_chunked_novel_bs128
  - MrRobotoAI/Frejya-0.8b
  - Azazelle/Llama-3-LongStory-LORA
  - MrRobotoAI/Frejya-0.8b
  - nicce/story-mixtral-8x7b-lora
  - MrRobotoAI/Frejya-0.8b
  - ResplendentAI/BlueMoon_Llama3
  - MrRobotoAI/Frejya-0.8b
  - Azazelle/Llama-3-8B-Abomination-LORA
  - Nitral-Archive/HerculeanSea-7b-128k
  - NousResearch/Yarn-Mistral-7b-128k
  - CallComply/zephyr-7b-beta-128k
  - MrRobotoAI/Frejya-0.8b
  - ResplendentAI/Llama3_Aesir_Preview_LoRA_128
  - MrRobotoAI/Frejya-0.8b
  - ResplendentAI/Llama3_RP_ORPO_LoRA
  - MrRobotoAI/Frejya-0.8b
  - Azazelle/Llama-3-LimaRP-Instruct-LoRA-8B
  - MrRobotoAI/Frejya-0.8b
  - Azazelle/Llama-3-Instruct-LiPPA-LoRA-8B
  - MrRobotoAI/Frejya-0.8b
  - Azazelle/L3-Daybreak-8b-lora
  - MrRobotoAI/Frejya-0.8b
  - ResplendentAI/NoWarning_Llama3
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 CallComply/zephyr-7b-beta-128k 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: CallComply/zephyr-7b-beta-128k
  - model: Nitral-Archive/HerculeanSea-7b-128k
  - model: NousResearch/Yarn-Mistral-7b-128k
  - model: MrRobotoAI/Frejya-0.8b+Azazelle/Llama-3-8B-Abomination-LORA
  - model: MrRobotoAI/Frejya-0.8b+Azazelle/Llama-3-LimaRP-Instruct-LoRA-8B
  - model: MrRobotoAI/Frejya-0.8b+Azazelle/Smarts_Llama3
  - model: MrRobotoAI/Frejya-0.8b+Azazelle/Nimue-8B
  - model: MrRobotoAI/Frejya-0.8b+Azazelle/Llama-3-Instruct-LiPPA-LoRA-8B
  - model: MrRobotoAI/Frejya-0.8b+Azazelle/L3-Daybreak-8b-lora
  - model: MrRobotoAI/Frejya-0.8b+vincentyandex/lora_llama3_chunked_novel_bs128
  - model: MrRobotoAI/Frejya-0.8b+ResplendentAI/Theory_of_Mind_Llama3
  - model: MrRobotoAI/Frejya-0.8b+ResplendentAI/Aura_Llama3
  - model: MrRobotoAI/Frejya-0.8b+ResplendentAI/Luna_Llama3
  - model: MrRobotoAI/Frejya-0.8b+ResplendentAI/BlueMoon_Llama3
  - model: MrRobotoAI/Frejya-0.8b+ResplendentAI/NoWarning_Llama3
  - model: MrRobotoAI/Frejya-0.8b+ResplendentAI/Llama3_Aesir_Preview_LoRA_128
  - model: MrRobotoAI/Frejya-0.8b+ResplendentAI/Llama3_RP_ORPO_LoRA
  - model: MrRobotoAI/Frejya-0.8b+Blackroot/Llama-3-LongStory-LORA
  - model: MrRobotoAI/Frejya-0.8b+Azazelle/Llama-3-LongStory-LORA
  - model: MrRobotoAI/Frejya-0.8b+nicce/story-mixtral-8x7b-lora

merge_method: model_stock
base_model: CallComply/zephyr-7b-beta-128k
normalize: true
dtype: float16