Search FoxAI

AI Models 2119

• Qwen3-4B-Alucard↗

  WasamiKirua

• timesfm-2.0-500m-pytorch↗

  Google

  TimesFM (Time Series Foundation Model) is a pretrained time-series foundation model developed by Google Research for time-series forecasting. * Paper: A decoder-only foundation model for time-series forecasting, ICML 2024. * Google Research blog * GitHub repo - It performs univariate time series forecasting for context lengths up to 2048 time points and any horizon lengths, with an optional frequency indicator. Note that it can go even beyond 2048 context even though it was trained with that as the maximum context. - It focuses on point forecasts. We experimentally offer 10 quantile heads but they have not been calibrated after pretraining. - It ideally requires the context to be contiguous (i.e. no "holes"), and the context and the horizon to be of the same frequency. In case there are nans we fill in the missing values with linear interpolation before calling the model.

• sam3↗

  Justin331

• bert-base-swedish-cased↗

  KB

  The National Library of Sweden / KBLab releases three pretrained language models based on BERT and ALBERT. The models are trained on aproximately 15-20GB of text (200M sentences, 3000M tokens) from various sources (books, news, government publications, swedish wikipedia and internet forums) aiming to provide a representative BERT model for Swedish text. A more complete description will be published later on. - **bert-base-swedish-cased** (*v1*) - A BERT trained with the same hyperparameters as first published by Google. - **bert-base-swedish-cased-ner** (*experimental*) - a BERT fine-tuned for NER using SUC 3.0. - **albert-base-swedish-cased-alpha** (*alpha*) - A first attempt at an ALBERT for Swedish. The examples below require Huggingface Transformers 2.4.1 and Pytorch 1.3.1 or greater. For Transformers<2.4.0 the tokenizer must be instantiated manually and the `do_lower_case` flag parameter set to `False` and `keep_accents` to `True` (for ALBERT).

• mHuBERT-147↗

  utter-project

  **MODEL DETAILS:** 3rd iteration, K=1000, HuBERT base architecture (95M parameters), 147 languages. mHuBERT-147 are compact and competitive multilingual HuBERT models trained on 90K hours of open-license data in 147 languages. Different from *traditional* HuBERTs, mHuBERT-147 models are trained using faiss IVF discrete speech units. Training employs a two-level language, data source up-sampling during training. See more information in our paper. 1. Summary 2. Training Data and Code 3. ML-SUPERB Scores 4. Languages and Datasets 5. Intermediate Checkpoints 6. Citing and Funding Information

• wav2vec2-large-xlsr-japanese-hiragana↗

  vumichien

  Fine-tuned facebook/wav2vec2-large-xlsr-53 on Japanese using the Common Voice and Japanese speech corpus of Saruwatari-lab, University of Tokyo JSUT. When using this model, make sure that your speech input is sampled at 16kHz. The model can be used directly (without a language model) as follows: **WER:** 24.74%, **CER:** 10.99% The Common Voice `train`, `validation` datasets and Japanese speech corpus datasets were used for training.

• Hetman-2b↗

  YSamchuk

• Qwen3.8-27B-Coder390-EfficientThink-Opus5.5-GPT6Astra-Grok4.7-DSV4Pro-K3-SFT-RLOO-MTP-DFlash2↗

  Arkha7

  A model post-trained with several rounds of SFT and RLOO on top of Qwen3.8-27B-EfficientThink-SFT-SimPO-DFlash2, which is itself the official Qwen3.8-27B post-trained with SFT and SimPO. It is built to fix the original model's habit of failing to stop: it already has an answer, yet keeps re-deriving until it hits the 94K cap with no final answer. This repository provides five safetensors tiers, **BF16**, **static FP8 Block128**, **NVFP4 W4A16**, **NVFP4 W4A4**, and **NVFP4 W4A4-W8A8** (mixed precision), all fully multimodal (text + image/video) with the official BF16 MTP bundled; all load in SGLang without patches, and the FP8 package is also smoke-tested on vLLM. It also has **NInfer W4A4 / W4A4-W8A8** (`NVFP4-NInfer/`), **INT8 W8A8** (`INT8/W8A8/`, text only), and **GGUF Q2 / Q3 / Q4 LynnStyle, Q6_K, and Q8_0** (`GGUF/`, `GGUF-NInfer/`, built-in MTP). **Lineage**: official Qwen3.8 27B (177 / 444 / 83) → our SFT + SimPO110 final, i.e. the EfficientThink base (171 / 442 / 89) → K3 continuation SFT → week-2 SFT (week2dose, update-225) → first RLOO round (182 groups) → another SFT round (merge-sft-100), giving sft-base-rloo (177 / 448 / 90) → second RLOO round (172 groups) → **Coder390** (178 / 445 / 90, dynamic FP8). Numbers are GPQA / MMLU / LCB, all full suites under the same 100K protocol. **Training base**: this model starts from our own EfficientThink SFT + SimPO model (the SimPO110 final) and goes through several rounds of SFT and RLOO, which is itself a post-trained version of the official Qwen3.8-27B: Qwen3.8-27B-EfficientThink-SFT-SimPO-DFlash2.

• Qwen3-Embedding-4B-FP8-Dynamic↗

  DCC-BS

  Embeddings are the pooled last hidden state; the head is unused and left unquantised. Cosine similarity is scale-sensitive, so compare rankings rather than raw distances when validating this checkpoint. `WikipediaRetrievalMultilingual` from MTEB — retrieval over Wikipedia in 16 languages, scored by `ndcg_at_10`. Serving Qwen/Qwen3-Embedding-4B in bf16 leaves little room for KV cache on a small GPU: the weights take what the cache needs, and the context length has to be cut until it fits. Halving the weights gives that memory back — the same card serves a longer context without any other change.

• Samantha-Mythomax-l2-13b-merge-fixed-i1-GGUF↗

  mradermacher