Xiaojian9992024/Qwen2.5-7B-MS-Destroyer

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 Qwen/Qwen2.5-7B-Instruct as a base.

Models Merged

The following models were included in the merge:

• Xiaojian9992024/Qwen2.5-Dyanka-7B-Preview + prithivMLmods/Deepthink-Reasoning-Adapter
• prithivMLmods/Viper-Coder-HybridMini-v1.3 + bunnycore/Qwen-2.5-7b-s1k-lora_model
• cooperleong00/Qwen2.5-7B-Instruct-Jailbroken
• prithivMLmods/Omni-Reasoner-Merged
• HumanLLMs/Human-Like-Qwen2.5-7B-Instruct
• prithivMLmods/Novaeus-Promptist-7B-Instruct
• HoangHa/Pensez-v0.1-e5
• lightblue/Karasu-DPO-7B
• prithivMLmods/QwQ-LCoT2-7B-Instruct
• IIC/RigoChat-7b-v2 + Lekhansh/Qwen2.5_7b_notesCorrector

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: HoangHa/Pensez-v0.1-e5 # French
  - model: prithivMLmods/QwQ-LCoT2-7B-Instruct # QwQ-like model
  - model: lightblue/Karasu-DPO-7B # Japanese
  - model: HumanLLMs/Human-Like-Qwen2.5-7B-Instruct # Human-like convos
  - model: cooperleong00/Qwen2.5-7B-Instruct-Jailbroken # Uncensored Questions
  - model: prithivMLmods/Viper-Coder-HybridMini-v1.3+bunnycore/Qwen-2.5-7b-s1k-lora_model # Coding and Reasoning Hybrid, now with CoT
  - model: prithivMLmods/Novaeus-Promptist-7B-Instruct # Prompt Enchancement
  - model: IIC/RigoChat-7b-v2+Lekhansh/Qwen2.5_7b_notesCorrector # This is for the Espanos! + Bonus Notes Corrector
  - model: Xiaojian9992024/Qwen2.5-Dyanka-7B-Preview+prithivMLmods/Deepthink-Reasoning-Adapter # Dyanka with a CoT LoRA
  - model: prithivMLmods/Omni-Reasoner-Merged
merge_method: model_stock
parameters:
base_model: Qwen/Qwen2.5-7B-Instruct
dtype: bfloat16
tokenizer_source: Qwen/Qwen2.5-7B-Instruct