Myosotis-1.5-base-Preview
Myosotis-1.5-base is the second flagship release from us, built on the FWKV architecture. Myosotis-1.5 is engineered to never...
Myosotis-1.5-base is the second flagship release from us, built on the FWKV architecture. Myosotis-1.5 is engineered to never...
KVpop uses future-attention targets to train lightweight importance scorers; at inference it keeps a bounded sink + scored...
We reduce Qwen3.5-4B inference latency on a single A10G by quantizing both the target model and its speculative-decoding...
FlashNorm-prepared checkpoint of HuggingFaceTB/SmolLM2-135M. Mathematically equivalent to the source model. The per-channel RMSNorm weight tensors (inputlayernorm.weight, postattentionlayernorm.weight, model.norm.weight`)...
This repository contains the official PreSINQ GGUF-quantized versions of the Qwen3-1.7B model. For a detailed explanation of PreSINQ...
This repository contains the official 4-bit quantized version of the Kimi-Linear-48B model using the SINQ (Sinkhorn-Normalized Quantization) method...
This repository contains the official 4-bit quantized version of the Apertus-8B-2509 model using the calibrated version of SINQ...
BitMamba-2-255M is the ultra-efficient baseline model of the BitMamba-2 family. It integrates 1.58-bit ternary quantization (BitNet) into the...
Этот репозиторий содержит официальную 4-битную квантованную версию модели Qwen3-14B с использованием метода SINQ (Sinkhorn-Normalized Quantization), как представлено в...
Этот репозиторий содержит официальную 4-битную квантованную версию модели Qwen3-1.7B с использованием калиброванной версии метода SINQ (Sinkhorn-Normalized Quantization). SINQ...