Hugging Face's logo

MrRobotoAI
/
102

Text Generation
Transformers
Safetensors
llama
mergekit
Merge
conversational
text-generation-inference
Model card Files Community
102 / README.md
MrRobotoAI's picture
MrRobotoAI
Update README.md
5329dd4 verified
preview code
|
raw
history blame contribute delete
8.11 kB
metadata
base_model:
  - MrRobotoAI/A4.4
  - MrRobotoAI/A4
library_name: transformers
tags:
  - mergekit
  - merge

merge 13,699 14,014

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

Merge Details

Merge Method

This model was merged using the DARE TIES merge method using MrRobotoAI/A4 as a base.

Models Merged

The following models were included in the merge:

Configuration 

models:
  - model: MrRobotoAI/A4+arushimgupta/lora_save_7
  - model: MrRobotoAI/A4+aryanagrawal1/llama-3-8b-instruct-sft-rewriting-fs-promptbench
  - model: MrRobotoAI/A4+athirdpath/BigMistral-11b-GLUE_LORA
  - model: MrRobotoAI/A4+automorphic/LORA_20231221_042843_philosophy
  - model: MrRobotoAI/A4+Azazelle/go-bruins-v3-lora
  - model: MrRobotoAI/A4+Azazelle/L3-Daybreak-8b-lora
  - model: MrRobotoAI/A4+Azazelle/Llama-3-8B-Abomination-LORA
  - model: MrRobotoAI/A4+Azazelle/llama3-8b-hikikomori-v0.4
  - model: MrRobotoAI/A4+Azazelle/Llama-3-LongStory-LORA
  - model: MrRobotoAI/A4+Azazelle/Llama-3-Sunfall-8b-lora
  - model: MrRobotoAI/A4+Azazelle/Nimue-8B
  - model: MrRobotoAI/A4+Azazelle/Smarts_Llama3
  - model: MrRobotoAI/A4+basilePlus/llama3-8b-schopenhauer
  - model: MrRobotoAI/A4+Blackroot/Llama-3-LongStory-LORA
  - model: MrRobotoAI/A4+Blackroot/Llama3-RP-Lora
  - model: MrRobotoAI/A4+Chat-Error/Claude-Kimiko
  - model: MrRobotoAI/A4+DreadPoor/Everything-COT-8B-r128-LoRA
  - model: MrRobotoAI/A4+Epiculous/Mika-7B-LoRA
  - model: MrRobotoAI/A4+erbacher/zephyr-convsearch-7b-v2
  - model: MrRobotoAI/A4+erbacher/zephyr-rag-agent
  - model: MrRobotoAI/A4+erbacher/zephyr-rag-agent-webgpt
  - model: MrRobotoAI/A4+grimjim/Llama-3-Instruct-abliteration-LoRA-8B
  - model: MrRobotoAI/A4+hannahbillo/dpo-llama3-8b-grammar-rules
  - model: MrRobotoAI/A4+hf-100/Llama-3.1-Spellbound-StoryWriter-0.1-lora
  - model: MrRobotoAI/A4+ian00000/Llama-3-8B_offensive_CoT_finetuned
parameters:
    weight: 1.0
merge_method: linear
dtype: float16

models:
  - model: MrRobotoAI/A4.1+jeiku/Alpaca_NSFW_Shuffled_Mistral
  - model: MrRobotoAI/A4.1+jeiku/Futadom_Mistral
  - model: MrRobotoAI/A4.1+jeiku/Gnosis_Reformatted_Mistral
  - model: MrRobotoAI/A4.1+jeiku/Humiliation_Mistral
  - model: MrRobotoAI/A4.1+jeiku/NSFW_Niche_Mistral
  - model: MrRobotoAI/A4.1+jeiku/Sissification_Hypno_Mistral
  - model: MrRobotoAI/A4.1+jeiku/Synthetic_Soul_1k_Mistral_128
  - model: MrRobotoAI/A4.1+jeiku/Writing_Mistral
  - model: MrRobotoAI/A4.1+jrahn/llama-3-8b-claudstruct-v3
  - model: MrRobotoAI/A4.1+jspr/llama3-instruct-wordcel-smutrom_peft
  - model: MrRobotoAI/A4.1+jspr/llama3-instruct-wordcel-smutrom-8k_peft
  - model: MrRobotoAI/A4.1+jspr/llama3-wordcel-smutrom_peft
  - model: MrRobotoAI/A4.1+jspr/llama3-wordcel-smutrom-reorder_peft
  - model: MrRobotoAI/A4.1+jspr/smut_llama_8b_32k_peft_ax
  - model: MrRobotoAI/A4.1+jspr/smut_llama_8b_smut_2k_romance_1k_peft
  - model: MrRobotoAI/A4.1+jspr/smut_llama_8b_smutromance_32k_peft
  - model: MrRobotoAI/A4.1+kamrr/llama-3-8b_dolly_lora
  - model: MrRobotoAI/A4.1+kik41/lora-formality-informal-llama-3-8b-v2
  - model: MrRobotoAI/A4.1+kik41/lora-function-more-llama-3-8b-v2
  - model: MrRobotoAI/A4.1+kik41/lora-length-long-llama-3-8b-v2
  - model: MrRobotoAI/A4.1+kik41/lora-sarcasm-more-llama-3-8b-v2
  - model: MrRobotoAI/A4.1+kik41/lora-type-descriptive-llama-3-8b-v2
  - model: MrRobotoAI/A4.1+kik41/lora-type-expository-llama-3-8b-v2
  - model: MrRobotoAI/A4.1+kik41/lora-type-narrative-llama-3-8b-v2
  - model: MrRobotoAI/A4.1+kik41/lora-type-persuasive-llama-3-8b-v2
parameters:
    weight: 1.0
merge_method: linear
dtype: float16

models:
  - model: MrRobotoAI/A4.2+kik41/lora-voice-active-llama-3-8b-v2
  - model: MrRobotoAI/A4.2+kromcomp/L3-Unaligned-r256-LoRA
  - model: MrRobotoAI/A4.2+lemonilia/ShoriRP-v0.75d
  - model: MrRobotoAI/A4.2+marsfu2009/writer_lora
  - model: MrRobotoAI/A4.2+mpasila/Llama-3-LiPPA-LoRA-8B
  - model: MrRobotoAI/A4.2+NewEden/Control-8B-V.2-Erebus-Lora
  - model: MrRobotoAI/A4.2+nicce/story-mixtral-8x7b-lora
  - model: MrRobotoAI/A4.2+Nuts123/mistral-finetuned-bookcorpus
  - model: MrRobotoAI/A4.2+Ozaii/Wali-8B-Uncensored-Model
  - model: MrRobotoAI/A4.2+pcalhoun/Llama-3.1-8B-JonathanSwift-lora
  - model: MrRobotoAI/A4.2+prayslaks/wikimedia_wikipedia_100K_100000_fedavg_c3s3_i10_b4a1_l512_r16a32_20241116070731
  - model: MrRobotoAI/A4.2+prayslaks/wikimedia_wikipedia_100K_100000_fedavg_c4s4_i10_b4a1_l512_r16a32_20241116082857
  - model: MrRobotoAI/A4.2+prayslaks/wikimedia_wikipedia_100K_100000_fedavg_c5s5_i10_b4a1_l512_r16a32_20241116091554
  - model: MrRobotoAI/A4.2+ResplendentAI/Aura_Llama3
  - model: MrRobotoAI/A4.2+ResplendentAI/BlueMoon_Llama3
  - model: MrRobotoAI/A4.2+ResplendentAI/Llama3_Aesir_Preview_LoRA_128
  - model: MrRobotoAI/A4.2+ResplendentAI/Luna_Llama3
  - model: MrRobotoAI/A4.2+ResplendentAI/Theory_of_Mind_Llama3
  - model: MrRobotoAI/A4.2+sardukar/physiology-8k-llama3-8b-qlora
  - model: MrRobotoAI/A4.2+sayhan/OpenHermes-2.5-Strix-Philosophy-Mistral-7B-LoRA
  - model: MrRobotoAI/A4.2+surya-narayanan/human_sexuality
  - model: MrRobotoAI/A4.2+yjcsean/fintuned_story
  - model: MrRobotoAI/A4.2+vincentyandex/lora_llama3_chunked_novel_bs128
  - model: MrRobotoAI/A4.2+W1lson/mistral-trained-on-Book3
  - model: MrRobotoAI/A4.2+W1lson/zephyr-book-3
parameters:
    weight: 1.0
merge_method: linear
dtype: float16

The following YAML configuration was used to produce this model:
models:
  - model: MrRobotoAI/A4.3+basilePlus/llama3-8b-schopenhauer
  - model: MrRobotoAI/A4.3+Blackroot/Llama-3-LongStory-LORA
  - model: MrRobotoAI/A4.3+hf-100/Llama-3.1-Spellbound-StoryWriter-0.1-lora
  - model: MrRobotoAI/A4.3+jspr/smut_llama_8b_smutromance_32k_peft
  - model: MrRobotoAI/A4.3+mpasila/Llama-3.1-Literotica-LoRA-8B
  - model: MrRobotoAI/A4.3+MrRobotoAI/Llama-3.1-8B-Instruct-Adapter-512K
  - model: MrRobotoAI/A4.3+nothingiisreal/llama3-8B-DWP-lora
  - model: MrRobotoAI/A4.3+ResplendentAI/NoWarning_Llama3
  - model: MrRobotoAI/A4.3+SayedNabeel/mistral-7b-mj-finetuned-HorrorStory
  - model: MrRobotoAI/A4.3+Triangle104/Vulkane_120-Days-of-Sodom-LoRA-Mistral-7b
  - model: MrRobotoAI/A4.3+vaitech/open-hermes-erotic-story-finetune
  - model: MrRobotoAI/A4.3+vaitech/open-hermes-sd-finetune
  - model: nothingiisreal/L3-8B-Stheno-Horny-v3.3-32K+Blackroot/Llama-3-LongStory-LORA
  - model: Cas-Archive/L3-Umbral-Mind-RP-v0.1-8B+ResplendentAI/NoWarning_Llama3
  - model: Casual-Autopsy/L3-Uncen-Merger-Omelette-RP-8B-EXPERIMENTAL+ResplendentAI/NoWarning_Llama3
parameters:
    weight: 1.0
merge_method: linear
dtype: float16

merge_method: dare_ties
models:
  - model: MrRobotoAI/A4
    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/A4.4
    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/A4
tokenizer_source: base
dtype: bfloat16