전체 검색

AI 모델 2119

• Julia-1↗

  SupersonicLabs

  Julia 1 is the **first model in the Julia family and the first released test of our training system**. At 144.3M parameters, it turns a state, a question, and possible answers into one clear decision. The same interface handles classification, routing, ordered scores, and Boolean decisions. Measured on **2026-09-24** with H200 BF16 inference and strict encoding. These are results for the checkpoint in this repository. MASSIVE measures 18 scenario labels across 52 locales with 2,974 examples per locale. It does not measure intent classification or slot filling. The all-locale value is macro accuracy.

• sample1↗

  ko-yoshida

• speechless-mistral-dolphin-orca-platypus-samantha-7b-i1-GGUF↗

  mradermacher

• resnext50_32x4d.a1h_in1k↗

  timm

  This model features: * ReLU activations * single layer 7x7 convolution with pooling * 1x1 convolution shortcut downsample * grouped 3x3 bottleneck convolutions Recipe details: * Based on ResNet Strikes Back `A1` recipe * LAMB optimizer * Stronger dropout, stochastic depth, and RandAugment than paper `A1` recipe * Cosine LR schedule with warmup - **Model Type:** Image classification / feature backbone - **Model Stats:** - Params (M): 25.0 - GMACs: 4.3 - Activations (M): 14.4 - Image size: train = 224 x 224, test = 288 x 288 - **Papers:** - ResNet strikes back: An improved training procedure in timm: https://arxiv.org/abs/2110.00476 - Aggregated Residual Transformations for Deep Neural Networks: https://arxiv.org/abs/1611.05431 - Deep Residual Learning for Image Recognition: https://arxiv.org/abs/1512.03385 - **Original:** https://github.com/huggingface/pytorch-image-models

• pythia-2.8b-deduped↗

  EleutherAI

  The *Pythia Scaling Suite* is a collection of models developed to facilitate interpretability research (see paper). It contains two sets of eight models of sizes 70M, 160M, 410M, 1B, 1.4B, 2.8B, 6.9B, and 12B. For each size, there are two models: one trained on the Pile, and one trained on the Pile after the dataset has been globally deduplicated. All 8 model sizes are trained on the exact same data, in the exact same order. We also provide 154 intermediate checkpoints per model, hosted on Hugging Face as branches. The Pythia model suite was designed to promote scientific research on large language models, especially interpretability research. Despite not centering downstream performance as a design goal, we find the models match or exceed the performance of similar and same-sized models, such as those in the OPT and GPT-Neo suites. Previously, we released an early version of the Pythia suite to the public. However, we decided to retrain the model suite to address a few hyperparameter discrepancies. This model card lists the changes ; see appendix B in the Pythia paper for further discussion. We found no difference in benchmark performance between the two Pythia versions. The old models are still available, but we suggest the retrained suite if you are just starting to use Pythia. **This is the current release.**

• Qwen3.8-27B-NVFP4-GGUF↗

  LibertAIDAI

  NVFP4 GGUF quantizations of Qwen/Qwen3.8-27B for llama.cpp, built for native NVFP4 tensor-core math on Blackwell GPUs. The NVFP4 weights come from our own ModelOpt post-training quantization of the BF16 release, using NVIDIA's dense recipe: NVFP4 at group size 16 on the language-model MLP linears only, calibrated on 512 samples of cnn_dailymail at sequence length 512. Attention (both the full-attention and Gated-DeltaNet linear-attention layers), the vision tower, the MTP block, embeddings and `lm_head` are left in BF16. That is 192 quantized linears, 64 layers by gate, up and down. An MTP variant with the speculative draft head is published separately at Qwen3.8-27B-NVFP4-MTP-GGUF.

• kimi-k3-dflash2↗

  lightseekorg

  Draft model for speculative decoding on `moonshotai/Kimi-K3`, served with TokenSpeed (`--speculative-algorithm DFLASH`). Acceptance length `acc_len = 1 + accepted/steps` at 7 speculative proposals, served with TokenSpeed DFLASH on two GB300 nodes (8 GPUs, TP8), MLA target and drafter. Target is `moonshotai/Kimi-K3` with the serving flags shown at the bottom of this card. Production sampling only: `temperature=1.0`, `top_p=0.95`, reasoning effort `max`, no `top_k`. RULER multi-key needle retrieval over natural-text paragraphs, with only the input length varying. `retrieval` is exact match on the needle value, recorded so that acceptance cannot be credited to a model that has stopped reading its context.

• Yi-1.5-6B-Chat↗

  01-ai

  Yi-1.5 is an upgraded version of Yi. It is continuously pre-trained on Yi with a high-quality corpus of 500B tokens and fine-tuned on 3M diverse fine-tuning samples. Compared with Yi, Yi-1.5 delivers stronger performance in coding, math, reasoning, and instruction-following capability, while still maintaining excellent capabilities in language understanding, commonsense reasoning, and reading comprehension. Model | Context Length | Pre-trained Tokens | :------------: | :------------: | :------------: | | Yi-1.5 | 4K, 16K, 32K | 3.6T

• wavlm-large↗

  Microsoft

  The large model pretrained on 16kHz sampled speech audio. When using the model, make sure that your speech input is also sampled at 16kHz. **Note**: This model does not have a tokenizer as it was pretrained on audio alone. In order to use this model **speech recognition**, a tokenizer should be created and the model should be fine-tuned on labeled text data. Check out this blog for more in-detail explanation of how to fine-tune the model. - 60,000 hours of Libri-Light - 10,000 hours of GigaSpeech - 24,000 hours of VoxPopuli

• wav2vec2-large-xlsr-53-polish↗

  jonatasgrosman

  Fine-tuned facebook/wav2vec2-large-xlsr-53 on Polish using the train and validation splits of Common Voice 6.1. When using this model, make sure that your speech input is sampled at 16kHz. This model has been fine-tuned thanks to the GPU credits generously given by the OVHcloud :) The script used for training can be found here: https://github.com/jonatasgrosman/wav2vec2-sprint