Llamacpp Quantizations of EVA-UNIT-01/EVA-Qwen2.5-7B-v0.0
Original: https://huggingface.co/EVA-UNIT-01/EVA-Qwen2.5-7B-v0.0
EVA Qwen2.5 7B
A RP/storywriting specialist model, full-parameter finetune of Qwen2.5-7B on mixture of synthetic and natural data.
A continuation of nothingiisreal's Celeste 1.x series, made to improve stability and versatility, without losing unique, diverse writing style of Celeste.
Prompt format is ChatML.
Recommended sampler values:
- Temperature: 0.87
- Top-P: 0.81
- Repetition Penalty: 1.05
Recommended SillyTavern presets (via CalamitousFelicitousness):
Training data:
- Celeste 70B 0.1 data mixture minus Opus Instruct subset. See that model's card for details.
- Kalomaze's Opus_Instruct_25k dataset, filtered for refusals.
- A subset (1k rows) of ChatGPT-4o-WritingPrompts by Gryphe
- A subset (2k rows) of Sonnet3.5-Charcards-Roleplay by Gryphe
- A cleaned subset (~3k rows) of shortstories_synthlabels by Auri
- Synthstruct and SynthRP datasets by Epiculous
Hardware used:
- 4xA6000 for 5 hours.
Model was trained by Kearm and Auri.
Special thanks:
- to Gryphe, Lemmy, Kalomaze, Nopm and Epiculous for the data
- to Alpindale for helping with FFT config for Qwen2.5
- and to InfermaticAI's community for their continued support for our endeavors
- Downloads last month
- 440
Model tree for Luni/EVA-UNIT-01_EVA-Qwen2.5-7B-v0.0-GGUF
Base model
Qwen/Qwen2.5-7B