我的收藏提交工具
FOXAI SEARCH

全站搜索

AI 模型 2119

  • privacy-filter-multilingual-v2↗

    OpenMed

    Fine-tuned `openai/privacy-filter` for **fine-grained PII extraction** across **54 categories** in **16 languages**. This v2 checkpoint is the more performant successor to `OpenMed/privacy-filter-multilingual`, with stronger multilingual PII masking behavior while keeping the same 16-language, fine-grained OpenMed label space and runtime interface. - **Base model**: `openai/privacy-filter` — 1.4B-parameter MoE (50M active per token), BIOES token-classification head - **Task**: Token classification for PII detection (BIOES scheme) - **Languages (16)**: Arabic, Bengali, Chinese, Dutch, English, French, German, Hindi, Italian, Japanese, Korean, Portuguese, Spanish, Telugu, Turkish, Vietnamese - **Training data**: The original language-balanced multilingual OpenMed/AI4Privacy mix, followed by a v2 source-balanced privacy-masking adaptation mix from AI4Privacy OpenPII, Nemotron, Gretel, and Privy-style PII data - **Recipe**: `opf train` (OpenAI's official fine-tuning CLI) — full fine-tune, AdamW, balanced language and source sampling, bf16 - **Labels**: 54 PII categories → 217 BIOES classes (1 `O` + 54 × B/I/E/S) The base model ships with 8 coarse PII categories and English-only training. This model trades that for a **6.75× more granular vocabulary** spanning identity, contact, address, financial, vehicle, digital, and crypto labels — all evaluated across 16 languages.

  • DeepSeek-V4.1-Flash-1017-Uncensored-GSQ-RCO-IQ2_XXS-GGUF↗

    Abiray

    This repository provides a **standalone, weight-baked abliterated (uncensored) GGUF build** of `ISTA-DASLab/DeepSeek-V4.1-Flash-1017-GSQ-RCO-GGUF` (`IQ2_XXS`, 2.00 bpw) using the rank-1 EN+RU refusal-direction abliteration from `AtomicChat/DeepSeek-V4.1-Flash-1017-Uncensored-GGUF`. - **Zero LoRA Required at Runtime:** All 86 abliterated residual-writing tensors are baked directly into the 4 GGUF backbone shards. No `--lora` adapter flags are needed. - **Same Size as Original (`138.58 GB` vs. `138.24 GB`):** Adds only `+0.34 GB` (`+0.25%`) across the entire 4-shard 763B model. - **100% GSQ-RCO Intelligence Preserved:** All **28 1-bit `IQ1_M` GSQ-calibrated routed-expert layers** and both **`blk.{1,14}.engram_wkv.weight` (`Q5_K`)** projections from ISTA-DASLab are preserved 100% untouched, while all **80 dense residual writers** (`blk.{0..39}.attn_output_b.weight` in `Q6_K` and `blk.{0..39}.ffn_down_shexp.weight` in `Q8_0`/`Q5_K`) plus the **6 exact-type 2-bit routed-expert layers** (`blk.7, 8, 10, 18` in `IQ2_XXS` and `blk.33, 39` in `IQ2_XS`) carry the full refusal-direction removal. > **Important:** Like the upstream ISTA-DASLab release, this 4-shard backbone pairs with the shared **`DeepSeek-V4.1-Flash-Engram-IQ4_NL.gguf`** (`110.60 GB`) lookup file from `ISTA-DASLab/DeepSeek-V4.1-Flash-1017-GSQ-RCO-GGUF`. Place all 4 shards and the Engram file in the same directory.

  • FLUX.1-dev-gguf↗

    city96

    This is a direct GGUF conversion of black-forest-labs/FLUX.1-dev As this is a quantized model not a finetune, all the same restrictions/original license terms still apply. The model files can be used with the ComfyUI-GGUF custom node.

  • bert_uncased_L-12_H-768_A-12↗

    Google

    This is the set of 24 BERT models referenced in Well-Read Students Learn Better: On the Importance of Pre-training Compact Models (English only, uncased, trained with WordPiece masking). We have shown that the standard BERT recipe (including model architecture and training objective) is effective on a wide range of model sizes, beyond BERT-Base and BERT-Large. The smaller BERT models are intended for environments with restricted computational resources. They can be fine-tuned in the same manner as the original BERT models. However, they are most effective in the context of knowledge distillation, where the fine-tuning labels are produced by a larger and more accurate teacher. Our goal is to enable research in institutions with fewer computational resources and encourage the community to seek directions of innovation alternative to increasing model capacity.

  • wav2vec2-large-xlsr-53-persian↗

    jonatasgrosman

    Fine-tuned facebook/wav2vec2-large-xlsr-53 on Persian 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

  • Kokoro-82M-ONNX↗

    onnx-community

    Kokoro is a frontier TTS model for its size of 82 million parameters (text in/audio out). - Samples - Usage - JavaScript - Python - Quantizations First, install the `kokoro-js` library from NPM using:

  • GLM-5.3-Flash-VQ-GGUF↗

    Baekpica

    > [!WARNING] > **Experimental low-bit release.** The routed experts, which hold most of the > weights, are stored at 1.625 or 2.625 bits per weight depending on the layer > (about 2.1 on average), far below common 4-bit GGUF quants. You may see > failures the source model rarely shows: reasoning that loops or never > reaches an answer, text that breaks mid-character (shown as `�`) or switches > language mid-word, and weaker answers in general. This is exploratory > quantization research, not a drop-in replacement for the source model. > > **The files can change.** This line of conversions is still being researched > (as of 2026-10-21, weighted Lloyd fitting of the codebooks is being tested), > so any file here may be replaced by a new revision. Replacements so far: > three since the first release on 2026-10-15. The non-expert weights were > requantized (Q4_K v3, 2026-10-16), then the 8-bit residual stage that > protects sensitive routed layers was added to layers 3–16 and widened to 19 > layers (2026-10-18). The earlier files remain at the tags `vq-original`, > `q4k-v3` and `r13p8-l3-16`. To keep a fixed build, download a pinned commit: > `hf download Baekpica/GLM-5.3-Flash-VQ-GGUF --revision `. > > **Problems or odd output?** Feel free to post them in the > Community tab, > even as rough notes. The prompt, sampling settings and runtime commit help > most. > **Status, 2026-10-18:** the files are the 19-layer R13+8 revision: the > residual stage now covers routed layers 3–17, 22, 27, 41 and 44 (before: > 3–16). Loading needs a ds4-dfm-rs build with GVQ1 container v2 support > (`main` since PR #96, > merge `34c46d18`); the runtime binds the residual stage on any routed layer, > so no runtime change is needed. Speed and memory of this revision on DGX > Spark are not measured yet. Previous revisions are kept at the tags > `r13p8-l3-16` > (R13+8 on layers 3–16) and > `q4k-v3` > (all routed layers R13). Experimental custom GVQ1 / GGUF v3 conversion of the official Z.AI GLM-5.3-Flash (`91b69215804f2d2036a8867f6ce44848e278dcda`) for DGX Spark (GB10), run by ds4-dfm-rs. Standard llama.cpp/Ollama/Transformers loading is not claimed.

  • Samrudh-1-Brahma-7B↗

    dwivedula

  • sd-turbo-gguf↗

    samoudi

  • jina-reranker-v3↗

    jinaai

    > [!IMPORTANT] > **Prefer `jina-reranker-v3.5`** for new projects — it is a drop-in upgrade with stronger domain / multilingual / structured rankings and faster listwise inference. Same API; switch the model id from `jinaai/jina-reranker-v3` to `jinaai/jina-reranker-v3.5`. > [!TIP] > GGUF with quantizations and MLX versions are now available. `jina-reranker-v3` is a 0.6B parameter multilingual document reranker with a novel *last but not late interaction* architecture. Unlike ColBERT's separate encoding with multi-vector matching, this model performs causal self-attention between query and documents within the same context window, extracting contextual embeddings from the last token of each document.