MetaphoricalCode/Dumpling-Qwen2.5-32B-v2-exl3-5bpw-hb6

Quantized using the default exllamav3 (0.0.2) quantization process.

• Original model: https://huggingface.co/nbeerbower/Dumpling-Qwen2.5-32B-v2
• exllamav3: https://github.com/turboderp-org/exllamav3

---

Dumpling-Qwen2.5-32B-v2

nbeerbower/Rombos-EVAGutenberg-TIES-Qwen2.5-32B finetuned on:

• nbeerbower/GreatFirewall-DPO
• nbeerbower/Schule-DPO
• nbeerbower/Purpura-DPO
• nbeerbower/Arkhaios-DPO
• jondurbin/truthy-dpo-v0.1
• antiven0m/physical-reasoning-dpo
• flammenai/Date-DPO-NoAsterisks
• flammenai/Prude-Phi3-DPO
• Atsunori/HelpSteer2-DPO
• jondurbin/gutenberg-dpo-v0.1
• nbeerbower/gutenberg2-dpo
• nbeerbower/gutenberg-moderne-dpo.

Method

QLoRA ORPO tuned with 8x A100 for 2 epochs. Rank 64 LoRA, 2e-5 learning rate.