Skip to content

EthenEthenEthen

LoginPlatformTry Ethen

Open Source Model Profile · YOYO-AI

ZYH-LLM-Qwen2.5-14B

ZYH-LLM-Qwen2.5-14B is a 14.77B-parameter Qwen2 merge from YOYO-AI. Its model card documents della and sce merging across five Qwen2.5 variants.

Publisher
YOYO-AI
Task
text-generation
Model type
qwen2
License
apache-2.0
Library
Unknown
Publication status
Approved for indexing

Model overview

ZYH-LLM-Qwen2.5-14B is published by YOYO-AI as a text-generation model. Safetensors metadata reports 14,770,033,664 parameters, with Qwen2ForCausalLM and model type qwen2. According to the model card, it is a fourth-generation merge of five Qwen2.5-14B variants.

Recorded capabilities

Five-source Qwen2.5 merge

According to the model card, the merge combines Qwen2.5-Coder-14B, two Qwen2.5-14B-instruct variants, the 1M-instruct variant, and Qwen2.5-14B.

Della and sce methods

The model card lists della and sce as the merging methods for this fourth-generation release dated February 5, 2025.

Bilingual merge tags

Hub tags record merge, qwen2, conversational, en, zh, and a Qwen/Qwen2.5-14B base-model tag with a featherless-ai snapshot entry.

Use cases in the source record

  • Conversational text generation in English and Chinese using a Qwen2.5-14B-lineage merged model.
  • Experiments comparing Qwen2.5 coder and instruct merge variants documented in the publisher model card.

Limitations and unknowns

  • No evaluation results were extracted from this record.
  • No context-window value was extracted from this record.
  • Provider state is historical snapshot data, not independently refreshed current availability.
  • Performance comparisons to prior merged models are publisher statements and were not independently verified.

Source and provenance

Source: YOYO-AI/ZYH-LLM-Qwen2.5-14B

Captured: Unknown. Processed: 2026-09-07T19:35:17.439761+00:00.

upgraded version： The fourth-generation model of ZYH-LLM-Qwen2.5 has been released! Model name: ZYH-LLM-Qwen2.5-14B 🎉 This model's performance is absolutely phenomenal, surpassing all my previously released merged models! 🚀 To highlight its uniqueness, I've created a brand new series separate from all previous releases! 💫 📅 Release date: February 5, 2025 🧩 Merging methods: della and sce 🛠️ Models used: Qwen2.5-Coder-14B Qwen2.5-Coder-14B-instruct Qwen2.5-14B-instruct Qwen2.5-14B-instruct-1M Qwen2.5-14B ✨ Coming soon: GGUF format version! 📥 Don't miss out on trying it - stay tuned for download! 🚨💻

F001F002F003F004F005F006F007F008F009F010F011