全站搜索
AI 模型 2119
- JQ2_K-JQ6_K-Test-Models↗
eaddario
Quantization test results for **K2-Horizon-7B** (dense) and **LFM2.5-8B-A1B** (MoE), comparing standard llama.cpp quantization against a fork that adds five new non-linear super-block types: **JQ2_K** to **JQ6_K**. On both models, four of the five new types perform materially better than their counterpart on every measured metric (mean and 99% KLD, Δp RMS, top-1 agreement). `JQ2_K` is the exception. The size of the gain depends on the model: on the dense `K2-Horizon-7B`, `JQ3_K` and `JQ6_K` cut the mean KLD by more than half, while on the MoE `LFM2.5-8B-A1B` the improvements range from 13.8% to 23.2%. The five new types are non-linear (NL) super-block (K) types. Each new type spends exactly the same index payload as its K-quant counterpart:
- SambaLingo-Serbian-Base-i1-GGUF↗
mradermacher
- Qwen-image_SamsungCam_UltraReal↗
Danrisi
- resnet18.a3_in1k↗
timm
This model features: * ReLU activations * single layer 7x7 convolution with pooling * 1x1 convolution shortcut downsample Recipe details: * ResNet Strikes Back `A3` recipe * LAMB optimizer with BCE loss * Cosine LR schedule with warmup - **Model Type:** Image classification / feature backbone - **Model Stats:** - Params (M): 11.7 - GMACs: 0.9 - Activations (M): 1.3 - Image size: train = 160 x 160, test = 224 x 224 - **Papers:** - ResNet strikes back: An improved training procedure in timm: https://arxiv.org/abs/2110.00476 - Deep Residual Learning for Image Recognition: https://arxiv.org/abs/1512.03385 - **Original:** https://github.com/huggingface/pytorch-image-models
- Qwen3.8-27B-MTP-GGUF↗
Jackrong
This release bundles the MTP head directly into the model, enabling speculative decoding without loading a separate draft model. > 📌 Results are from an internal benchmark using identical runtime, GPU, > Flash Attention, and sampling settings. Actual performance may vary > depending on prompt length, reasoning depth, output length, and hardware. > [!Note] > This repository contains model weights and configuration files for the post-trained model in the Hugging Face Transformers format. > > These artifacts are compatible with Hugging Face Transformers, vLLM, SGLang, TokenSpeed, etc.
- samantha-mistral-instruct-7b-GGUF↗
mradermacher
- Qwen2.5-7B-Instruct-1M-GGUF↗
Mungert
Our latest quantization method introduces **precision-adaptive quantization** for ultra-low-bit models (1-2 bit), with benchmark-proven improvements on **Llama-3-8B**. This approach uses layer-specific strategies to preserve accuracy while maintaining extreme memory efficiency. All tests conducted on **Llama-3-8B-Instruct** using: - Standard perplexity evaluation pipeline - 2048-token context window - Same prompt set across all quantizations **Key**: - PPL = Perplexity (lower is better) - Δ PPL = Percentage change from standard to DynamicGate - Speed = Inference time (CPU avx2, 2048 token context) - Size differences reflect mixed quantization overhead
- SlimSAM-uniform-77↗
Zigeng
> **0.1% Data Makes Segment Anything Slim** > Zigeng Chen, Gongfan Fang, Xinyin Ma, Xinchao Wang > Learning and Vision Lab, National University of Singapore > Paper: [[Arxiv]](https://arxiv.org/abs/2312.05284) > Code: [[GitHub]](https://github.com/czg1225/SlimSAM) **SlimSAM** is a novel SAM compression method, which efficiently reuses pre-trained SAMs without the necessity for extensive retraining. This is achieved by the efficient reuse of pre-trained SAMs through a unified pruning-distillation framework. To enhance knowledge inheritance from the original SAM, we employ an innovative alternate slimming strategy that partitions the compression process into a progressive procedure. Diverging from prior pruning techniques, we meticulously prune and distill decoupled model structures in an alternating fashion. Furthermore, a novel label-free pruning criterion is also proposed to align the pruning objective with the optimization target, thereby boosting the post-distillation after pruning. SlimSAM achieves approaching performance while reducing the parameter counts to **0.9\% (5.7M)**, MACs to **0.8\% (21G)**, and requiring mere **0.1\% (10k)** of the training data when compared to the original SAM-H. Extensive experiments demonstrate that our method realize significant superior performance while utilizing over **10 times** less training data when compared to other SAM compression methods.
- Swift-1.5-Qwen3.8-27B-Uncensored-NVFP4↗
ajgazin
NVFP4 checkpoint of ajgazin/Swift-1.5-Qwen3.8-27B-Uncensored-MTP, an abliterated Swift 1.5 Qwen3.8-27B (UkisAI's reasoning-efficient fine-tune of Qwen3.8-27B). For vLLM and SGLang. GGUFs for llama.cpp: Swift-1.5-Qwen3.8-27B-Uncensored-Dynamic-MTP-GGUF. Sampling, as for Swift and Qwen: temperature 1.0, top_p 0.95, top_k 20, min_p 0. The model thinks before answering by default. Same format, recipe, module split and tensor layout as the Swift 1.0 version, which was load-tested on an RTX 5090 with vLLM 0.29.0 (native W4A4, MTP decoding and image input working). This checkpoint was not load-tested separately.
- AuK-Base-and-Flash-GGUF↗
audio-cpp
These GGUF files are for use with audio.cpp. The card's `base_model` points to the Tencent AuK base model. This package also includes optional files converted from AuK-Flash; Flash is a separate distilled variant and is not the pinned base model. > **Output quality:** We validate parity with upstream Python for the tested configuration, not whether AuK's output meets every quality expectation. If a result is disappointing, listen to the corresponding Python reference WAV linked below first. A similar Python result points to the upstream model's behavior, not necessarily an audio.cpp conversion issue. The quantized component combinations have not received the same 16-task parity validation. Pass the downloaded directory to `audiocpp_cli --model`. Keep the `config/` and `tokenizer/` directories alongside the GGUF files. The default components are `auk-base-f32.gguf`, `qwen2.5-omni-3b-bf16.gguf`, and `auk-vae-f32.gguf`. AuK-Flash requires `--session-option auk.variant=flash`; its default generator is `auk-flash-f32.gguf`. The Qwen component is Qwen2.5-Omni-3B.