Two-model narrative fusion
According to the model card, Euryale-v2.1 at 0.55 supplies storytelling and emotional depth while Nevoria-70b at 0.45 supplies logic, context handling, and coherence.
Open Source Model Profile · WasamiKirua
L3-Odyssey-70B is a 70.55B-parameter Llama text-generation merge from WasamiKirua. According to the model card, it fuses Euryale-v2.1 and Nevoria-70b for roleplay and storytelling.
L3-Odyssey-70B is published by WasamiKirua as a text-generation model. The captured configuration identifies LlamaForCausalLM, and Safetensors metadata reports 70,553,706,496 parameters. According to the model card, it merges two Llama 3 70B models for flexible roleplay and storytelling.
According to the model card, Euryale-v2.1 at 0.55 supplies storytelling and emotional depth while Nevoria-70b at 0.45 supplies logic, context handling, and coherence.
According to the model card, the merge uses DARE-TIES at 0.75 density on Steelskull/L3.3-MS-Nevoria-70b as base, with bfloat16 dtype.
Captured hub tags and the model card both frame the model around roleplay, storytelling, versatility, and conversational use.
According to the model card, standard Llama 3 settings apply, with 1.0 to 1.15 recommended for storytelling.
Source: WasamiKirua/L3-Odyssey-70B
Captured: Unknown. Processed: 2026-09-07T19:35:53.033919+00:00.
🌌 L3-Odyssey-70B (The Versatile Storyteller) L3-Odyssey-70B is a state-of-the-art 70-billion parameter model designed for ultimate flexibility in high-quality Roleplay (RP) and immersive storytelling. It is a fusion of two Llama 3 legends: Sao10K/L3-70B-Euryale-v2.1 and Steelskull/L3.3-MS-Nevoria-70b . The goal of this merge is to create a true narrative chameleon . By blending the unparalleled emotional intelligence and creative prose of Euryale with the superior logic, context handling, and instruction-following of Nevoria (based on Llama 3.3), L3-Odyssey adapts to any genre, tone, or writing style you request. 🤝 The "Odyssey" S…
F001F002F003F004F005F006F008F009F010F011F012F013F014F015F016F017