Edit model card

Meissa-Qwen2.5-7B-Instruct

Meissa is designated Lambda Orionis, forms Orion's head, and is a multiple star with a combined apparent magnitude of 3.33. Its name means the "shining one".

This model is fine tuned over writing and role playing datasets (maybe the first on qwen2.5-7b), aiming to enhance model's performance in novel writing and roleplaying.

The model is fine-tuned over Orion-zhen/Qwen2.5-7B-Instruct-Uncensored

Training details

I used SFT method. Datasets used are listed below:

  • anthracite-org/stheno-filtered-v1.1
  • MinervaAI/Aesir-Preview
  • Epiculous/Synthstruct-Gens-v1.1-Filtered-n-Cleaned
  • anthracite-org/nopm_claude_writing_fixed
  • Gryphe/Sonnet3.5-Charcard-Roleplay
  • nothingiisreal/DirtyWritingPrompts
  • Orion-zhen/tagged-pixiv-novel
Downloads last month
57
Safetensors
Model size
7.62B params
Tensor type
BF16
·
Inference Examples
Unable to determine this model's library. Check the docs .

Model tree for Orion-zhen/Meissa-Qwen2.5-7B-Instruct

Base model

Qwen/Qwen2.5-7B
Finetuned
(1)
this model
Quantizations
1 model

Datasets used to train Orion-zhen/Meissa-Qwen2.5-7B-Instruct

Collection including Orion-zhen/Meissa-Qwen2.5-7B-Instruct