サイト内検索

AI モデル 84760

• Nex-N2.5-mini-Sangreal-ICE↗

  gbuzhf

  Four ICE 1.6 tiers of **nex-agi's Nex-N2.5-mini** (35B total, 3B active, Qwen3.5-MoE architecture), quantized against **Sangreal** — a purpose-built 77-bucket calibration corpus — with an importance matrix measured on Nex itself, and shipping **Qwen-Sharp v22.5.0-arrow4.0** — our agent-tuned chat template, a heavily modified derivative of peculiar-ragdoll's Qwen-Sharp (spec below). Vision works through Nex's own projector, `mmproj-Nex-N2.5-mini-Q8_0.gguf`. Mean KLD to BF16, one session. **Size-matched** = bartowski's imatrix ladder for the same model, interpolated (log-linear) at each ICE file's exact byte size; negative = ICE closer to BF16. **Paired** = the same 64 chunks scored for both files against the same reference. Code at 16K context (`code.test.raw`, n_ctx 16384 × 8), mean KLD to BF16 vs file size; lower-left is better. Raw numbers in Table 2 below and in `measurements/2026-10-03/`.

• multiberts-seed_4-step_1200k↗

  Google

• bert-fa-base-uncased-sentiment-snappfood↗

  HooshvareLab

• Qwen3-4B-Domino-b16↗

  Huang2020

  This repository contains a Domino/DFlash draft model for speculative decoding with `Qwen/Qwen3-4B`. The draft model is not intended to be used as a standalone language model; it should be paired with the target model during generation. Domino keeps draft generation block-parallel while adding a lightweight causal correction head. This preserves the low drafting cost of parallel speculative decoding and improves draft-token acceptance.

• Occamy-1.0-APEX-I-NanoPlus-V2.1-Abliterated-GGUF↗

  IsValorum

• minimax_h3_pdmd_4nfe_comfyui↗

  Iwannapose

  ComfyUI-format conversion of the PDMD 4-NFE LoRA (`lora_model_0.safetensors`) — the 4-step (4 NFE) student distilled from MiniMax-H3-33B with Projected Distribution Matching Distillation, rank 128, covering attention projections and both feed-forward layers of all 50 transformer blocks + 2 token-refiner blocks. Earlier uploads (base / keys_v2 / v3 / v4 / v5) were broken conversions and have been removed: most of their keys matched nothing in the ComfyUI loader (silent no-op), and v4 missed the SwiGLU gate/value remap below. Source keys are Diffusers PEFT names (`transformer.transformer_blocks.N.attn.to_q.lora_A.weight` …); target keys follow the ComfyUI H3 layout (same scheme as the proven `minimax_h3_fl2v_turbo_8step_v1.0_768p_comfyui_bf16.safetensors`):

• robust-swedish-sentiment-multiclass↗

  KBLab

  The National Library of Sweden/KBLab releases a robust, multi-label sentiment classifier finetuned on Megatron-BERT-large-165K. The model was trained on approximately 75K Swedish texts from multiple linguistic domains and datasets.

• svara-tts-v1-openvino-int4↗

  kenpath

• isnet-general-use-onnx↗

  Ko033

• Qwen3.8-27B-Huihui-Abliterated-oQ4e-MTP-MLX↗

  KostkaIT