HERETIC 1.4.0 MTP APEX MIT Ornith 1.0 35B Heretic MTP APEX English 📖 中文文档 Heretic Trial 63 BF16 merge · compatible MTP head · APEX GGUFs + mmproj 🐦 About this release Ornith 1.0 35B is an agentic coding model from DeepReinforce AI, based on Qwen3.5 MoE. This experimental derivative merges the selected Heretic 1.4.0 Trial 63 LoRA into BF16 weights. It also includes a compatible Qwen3.5 MTP head, a BF16 vision projector, and APEX mixed precision GGUFs. Refusal modified models can behave differently from the original; evaluate before deployment. License: MIT. 🧠 Model Details Architecture Qwen3.5 MoE, multimodal Parameters 35B total, 3B active per token · 256 experts, 8 active Layers 40 transformer layers + 1 MTP layer (785 BF16 tensors) Context 262,144 tokens Weights BF16 safetensors, 17 shards; audited LoRA merge License MIT ⚡ Heretic Trial 63 of 120 Selected parameters: direction index=21.66 ; attention o proj range 1.55–2.05; MLP down proj range 1.64–1.84. Refusal prescreen / full evaluation 2 / 30 · 11 / 100 Validation KL mean / p95 / max 0.0242 / 0.1477 / 0.1648 Generation health Passed · top 1 disagreement 2.0% 📊 BenchLocal Results (APEX I Compact) Mode ToolCall BugFind Herm…
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy