Hugging Face's logo

MrRobotoAI
/
NBeerbower-Narrative-8b-64k

Text Generation
Transformers
Safetensors
llama
mergekit
Merge
conversational
text-generation-inference
Inference Endpoints
Model card Files Community

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 MrRobotoAI/10 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: nbeerbower/llama-3-gutenberg-8B
  - model: nbeerbower/Llama3.1-Allades-8B
  - model: nbeerbower/llama3.1-cc-8B
  - model: nbeerbower/llama-3-SNAMD-8B
  - model: nbeerbower/llama-3-Stheno-Mahou-8B
  - model: nbeerbower/llama-3-stinky-v2-8B
  - model: nbeerbower/llama-3-sauce-v2-8B
  - model: nbeerbower/llama3-KawaiiMahouSauce-8B
  - model: nbeerbower/nbeerbower/llama-3-spicy-abliterated-stella-8B
  - model: nbeerbower/llama-3-spicy-8B
  - model: nbeerbower/llama-3-stella-8B
  - model: nbeerbower/llama-3-dragonmaid-8B-v2
  - model: nbeerbower/llama-3-stinky-8B
  - model: nbeerbower/llama-3-dragonmaid-8B
  - model: nbeerbower/llama-3-sauce-v1-8B
merge_method: model_stock
base_model: MrRobotoAI/10
normalize: false
dtype: float16

Configuration

The following YAML configuration was used to produce this model:

merge_method: dare_linear
models:
  - model: MrRobotoAI/10
    parameters:
      weight:
        - filter: v_proj
          value: [0.8, 0.8, 0.75, 0.55, 0.35, 0.15, 0.35, 0.55, 0.75, 0.8, 0.8]
        - filter: o_proj
          value: [0.8, 0.8, 0.75, 0.55, 0.35, 0.15, 0.35, 0.55, 0.75, 0.8, 0.8]
        - filter: up_proj
          value: [0.8, 0.8, 0.75, 0.55, 0.35, 0.15, 0.35, 0.55, 0.75, 0.8, 0.8]
        - filter: gate_proj
          value: [0.8, 0.8, 0.75, 0.55, 0.35, 0.15, 0.35, 0.55, 0.75, 0.8, 0.8]
        - filter: down_proj
          value: [0.8, 0.8, 0.75, 0.55, 0.35, 0.15, 0.35, 0.55, 0.75, 0.8, 0.8]
        - value: 1
  - model: MrRobotoAI/NBeerbower-ConversationalMix-8b
    parameters:
      weight:
        - filter: v_proj
          value: [0.2, 0.2, 0.25, 0.45, 0.65, 0.85, 0.65, 0.45, 0.25, 0.2, 0.2]
        - filter: o_proj
          value: [0.2, 0.2, 0.25, 0.45, 0.65, 0.85, 0.65, 0.45, 0.25, 0.2, 0.2]
        - filter: up_proj
          value: [0.2, 0.2, 0.25, 0.45, 0.65, 0.85, 0.65, 0.45, 0.25, 0.2, 0.2]
        - filter: gate_proj
          value: [0.2, 0.2, 0.25, 0.45, 0.65, 0.85, 0.65, 0.45, 0.25, 0.2, 0.2]
        - filter: down_proj
          value: [0.2, 0.2, 0.25, 0.45, 0.65, 0.85, 0.65, 0.45, 0.25, 0.2, 0.2]
        - value: 0
base_model: MrRobotoAI/10
tokenizer_source: base
dtype: bfloat16

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: MrRobotoAI/2+Azazelle/Llama-3-Sunfall-8b-lora
  - model: MrRobotoAI/2+Azazelle/Nimue-8B
  - model: MrRobotoAI/2+jeiku/Alpaca_NSFW_Shuffled_Mistral
  - model: MrRobotoAI/2+jeiku/Futadom_Mistral
  - model: MrRobotoAI/2+jeiku/Humiliation_Mistral
  - model: MrRobotoAI/2+jeiku/NSFW_Niche_Mistral
  - model: MrRobotoAI/2+jeiku/Sissification_Hypno_Mistral
  - model: MrRobotoAI/2+jeiku/Synthetic_Soul_1k_Mistral_128
  - model: MrRobotoAI/2+jeiku/Writing_Mistral
  - model: MrRobotoAI/2+jrahn/llama-3-8b-claudstruct-v3
  - model: MrRobotoAI/2+jspr/llama3-instruct-wordcel-smutrom_peft
  - model: MrRobotoAI/2+jspr/llama3-instruct-wordcel-smutrom-8k_peft
  - model: MrRobotoAI/2+jspr/llama3-wordcel-smutrom_peft
  - model: MrRobotoAI/2+jspr/llama3-wordcel-smutrom-reorder_peft
  - model: MrRobotoAI/2+jspr/smut_llama_8b_smut_2k_romance_1k_peft
  - model: MrRobotoAI/2+jspr/smut_llama_8b_smutromance_32k_peft
  - model: MrRobotoAI/2+kik41/lora-formality-informal-llama-3-8b-v2
  - model: MrRobotoAI/2+kik41/lora-sarcasm-more-llama-3-8b-v2
  - model: MrRobotoAI/2+kik41/lora-type-descriptive-llama-3-8b-v2
  - model: MrRobotoAI/2+kik41/lora-type-narrative-llama-3-8b-v2
  - model: MrRobotoAI/2+kik41/lora-type-persuasive-llama-3-8b-v2
  - model: MrRobotoAI/2+kromcomp/L3-Unaligned-r256-LoRA
  - model: MrRobotoAI/2+lemonilia/ShoriRP-v0.75d
  - model: MrRobotoAI/2+mpasila/Llama-3.1-Literotica-LoRA-8B
  - model: MrRobotoAI/2+nothingiisreal/llama3-8B-DWP-lora
  - model: MrRobotoAI/2+ResplendentAI/Aura_Llama3
  - model: MrRobotoAI/2+ResplendentAI/BlueMoon_Llama3
  - model: MrRobotoAI/2+ResplendentAI/Llama3_RP_ORPO_LoRA
  - model: MrRobotoAI/2+ResplendentAI/Luna_Llama3
  - model: MrRobotoAI/2+ResplendentAI/NoWarning_Llama3
  - model: MrRobotoAI/2+ResplendentAI/Theory_of_Mind_Llama3
  - model: MrRobotoAI/2+Triangle104/Vulkane_120-Days-of-Sodom-LoRA-Mistral-7b
  - model: MrRobotoAI/2+vaitech/open-hermes-erotic-story-finetune
  - model: MrRobotoAI/2+vincentyandex/lora_llama3_chunked_novel_bs128
  - model: MrRobotoAI/2+WebNovelTrans/bEn0Kxa3dhCP8PCn
  - model: nothingiisreal/L3-8B-Stheno-Horny-v3.3-32K
merge_method: model_stock
base_model: MrRobotoAI/10
normalize: false
dtype: float16
Downloads last month
14
Safetensors
Model size
8.03B params
Tensor type
FP16
·
Inference Providers NEW
Text Generation
This model is not currently available via any of the supported third-party Inference Providers, and the model is not deployed on the HF Inference API.

Model tree for MrRobotoAI/NBeerbower-Narrative-8b-64k

nbeerbower/Llama3.1-Allades-8B
nbeerbower/llama-3-SNAMD-8B
nbeerbower/llama-3-Stheno-Mahou-8B
nbeerbower/llama-3-dragonmaid-8B
nbeerbower/llama-3-dragonmaid-8B-v2
nbeerbower/llama-3-gutenberg-8B
nbeerbower/llama-3-sauce-v1-8B
nbeerbower/llama-3-sauce-v2-8B
nbeerbower/llama-3-spicy-8B
nbeerbower/llama-3-spicy-abliterated-stella-8B
nbeerbower/llama-3-stella-8B
nbeerbower/llama-3-stinky-8B
nbeerbower/llama-3-stinky-v2-8B
nbeerbower/llama3-KawaiiMahouSauce-8B
nbeerbower/llama3.1-cc-8B
Merge model
this model
Merges
1 model
Quantizations
3 models