LLaMa-3-CursedStock-v2.0-8B.yaml

merge_method: model_stock
base_model: NousResearch/Meta-Llama-3-8B
dtype: float32
models:
  # Roleplay
  - model: openlynn/Llama-3-Soliloquy-8B-v2  # LLaMa-3-Instruct
  - model: Undi95/Llama-3-LewdPlay-8B-evo  # LLaMa-3-Instruct
  - model: NeverSleep/Llama-3-Lumimaid-8B-v0.1  # LLaMa-3-Instruct
  - model: NeverSleep/Llama-3-Lumimaid-8B-v0.1-OAS  # LLaMa-3-Instruct
  - model: dreamgen-preview/opus-v1.2-llama-3-8b-base-run3.4-epoch2  # Possibly LLaMa-3-Instruct?
  - model: dreamgen-preview/opus-v1.2-llama-3-8b-instruct-run3.5-epoch2.5  # LLaMa-3-Instruct
  - model: Sao10K/L3-8B-Stheno-v3.2  # LLaMa-3-Instruct
  - model: mpasila/Llama-3-LiPPA-8B  # LLaMa-3-Instruct (Unsloth changed assistant to gpt and user to human.)
  - model: mpasila/Llama-3-Instruct-LiPPA-8B  # LLaMa-3-Instruct (Unsloth changed assistant to gpt and user to human.)
  - model: Abdulhanan2006/WaifuAI-L3-8B-8k  # Possibly LLaMa-3-Instruct?
  - model: NousResearch/Meta-Llama-3-8B-Instruct+Blackroot/Llama-3-8B-Abomination-LORA  # LLaMa-3-Instruct
  - model: Nitral-AI/Hathor_Stable-v0.2-L3-8B  # Possibly LLaMa-3-Instruct?
  # Smart
  - model: NousResearch/Meta-Llama-3-8B-Instruct  # LLaMa-3-Instruct
  - model: abacusai/Llama-3-Smaug-8B  # Possibly LLaMa-3-Instruct?
  - model: jondurbin/bagel-8b-v1.0  # LLaMa-3-Instruct
  - model: TIGER-Lab/MAmmoTH2-8B-Plus  # Possibly LLaMa-3-Instruct?
  - model: VAGOsolutions/Llama-3-SauerkrautLM-8b-Instruct  # LLaMa-3-Instruct
  - model: turboderp/llama3-turbcat-instruct-8b  # LLaMa-3-Instruct
  # Uncensored
  - model: failspy/Meta-Llama-3-8B-Instruct-abliterated-v3  # LLaMa-3-Instruct
  - model: Undi95/Llama-3-Unholy-8B  # LLaMa-3-Instruct
  - model: Undi95/Llama3-Unholy-8B-OAS  # LLaMa-3-Instruct
  - model: Undi95/Unholy-8B-DPO-OAS  # LLaMa-3-Instruct
  - model: Edgerunners/meta-llama-3-8b-instruct-hf-ortho-baukit-5fail-3000total-bf16  # Possibly LLaMa-3-Instruct?
  - model: vicgalle/Configurable-Llama-3-8B-v0.3  # LLaMa-3-Instruct
  - model: lodrick-the-lafted/Limon-8B  # LLaMa-3-Instruct
  - model: AwanLLM/Awanllm-Llama-3-8B-Cumulus-v1.0  # LLaMa-3-Instruct
  # Code
  - model: WhiteRabbitNeo/Llama-3-WhiteRabbitNeo-8B-v2.0  # LLaMa-3-Instruct
  - model: migtissera/Tess-2.0-Llama-3-8B  # LLaMa-3-Instruct
  - model: defog/llama-3-sqlcoder-8b  # LLaMa-3-Instruct
  # Medical
  - model: HPAI-BSC/Llama3-Aloe-8B-Alpha  # LLaMa-3-Instruct
  # Story
  - model: maldv/llama-3-fantasy-writer-8b  # LLaMa-3-Instruct
  - model: lodrick-the-lafted/Olethros-8B  # LLaMa-3-Instruct
  - model: NousResearch/Meta-Llama-3-8B-Instruct+Blackroot/Llama-3-LongStory-LORA  # LLaMa-3-Instruct
  # Base LLaMa-3 FFT
  - model: Magpie-Align/Llama-3-8B-WildChat  # LLaMa-3-Instruct
  - model: Magpie-Align/Llama-3-8B-Tulu-330K  # LLaMa-3-Instruct
  - model: Magpie-Align/Llama-3-8B-OpenHermes-243K  # LLaMa-3-Instruct
  - model: Magpie-Align/Llama-3-8B-WizardLM-196K  # LLaMa-3-Instruct
  - model: Magpie-Align/Llama-3-8B-Ultrachat-200K  # LLaMa-3-Instruct
  - model: Magpie-Align/Llama-3-8B-ShareGPT-112K  # LLaMa-3-Instruct
  # Misc
  - model: refuelai/Llama-3-Refueled  # LLaMa-3-Instruct
  - model: Danielbrdz/Barcenas-Llama3-8b-ORPO  # LLaMa-3-Instruct
  - model: migtissera/Llama-3-8B-Synthia-v3.5  # LLaMa-3-Instruct
  - model: RLHFlow/LLaMA3-iterative-DPO-final  # LLaMa-3-Instruct
  - model: chujiezheng/LLaMA3-iterative-DPO-final-ExPO  # LLaMa-3-Instruct
  - model: princeton-nlp/Llama-3-Instruct-8B-SimPO  # LLaMa-3-Instruct
  - model: chujiezheng/Llama-3-Instruct-8B-SimPO-ExPO  # LLaMa-3-Instruct
  - model: chargoddard/prometheus-2-llama-3-8b  # LLaMa-3-Instruct


# Model Count: 47
#
# v2.0
#  - Add chargoddard/prometheus-2-llama-3-8b. Technically a merge, but it's 2 finetunes intended to be merged 50/50 to follow the prometheus paper.
#  - Add turboderp/llama3-turbcat-instruct-8b. Cat finally got trained with L3-Instruct format.
#
# v1.9
#  - Add NousResearch/Meta-Llama-3-8B-Instruct. Should have had it from the start, but I forgot lol.
#  - Add maldv/llama-3-fantasy-writer-8b.
#  - Add Nitral-AI/Hathor_Stable-v0.2-L3-8B.
#  - Add defog/llama-3-sqlcoder-8b.
#  - Add Blackroot/Llama-3-LongStory-LORA.
#  - Add Magpie-Align/Llama-3-8B-WildChat.
#  - Add Magpie-Align/Llama-3-8B-Tulu-330K.
#  - Add Magpie-Align/Llama-3-8B-OpenHermes-243K.
#  - Add Magpie-Align/Llama-3-8B-WizardLM-196K.
#  - Add Magpie-Align/Llama-3-8B-Ultrachat-200K.
#  - Add Magpie-Align/Llama-3-8B-ShareGPT-112K.
#
# v1.8
#  - Only LLaMa-3-Instruct template models from now on. Not even gonna bother with the jank lol.
#  - Add princeton-nlp/Llama-3-Instruct-8B-SimPO.
#  - Add chujiezheng/LLaMA3-iterative-DPO-final-ExPO.
#  - Add chujiezheng/Llama-3-Instruct-8B-SimPO-ExPO.
#  - Add AwanLLM/Awanllm-Llama-3-8B-Cumulus-v1.0 as it's trained on failspy/Meta-Llama-3-8B-Instruct-abliterated-v3 with 8K length using rank 64 QLoRA and claims to be good at RP and storywriting.
#  - Add Blackroot/Llama-3-8B-Abomination-LORA as it claims to be heavily trained for RP and storywriting.
#  - Replaced Sao10K/L3-8B-Stheno-v3.1 with Sao10K/L3-8B-Stheno-v3.2.
#  - Removed victunes/TherapyLlama-8B-v1 as it might be too specific for a general merge. It was also aparently vicuna format.
#  - Removed ResplendentAI QLoRA models as they were trained on the base, but don't seem to train lm_head or embed_tokens.
#  - Removed BeaverAI/Llama-3SOME-8B-v2-rc2 as newer versions are out, and idk which is best yet. Also don't want doubledipping if I decide to Beavertrain this.