PII masking model for conversational data. A ~600M-parameter bidirectional Qwen3 encoder (`perplexity-ai/pplx-embed-v1-0.6b` backbone, run encoder-only via `is_causal=false`) with two heads: `predict` and `mask` wrap `model(input_ids, attention_mask)`, which returns the 37 BIOES tag logits per token and one sensitivity logit per document. The implementation is `modeling_pii_masking.py` in this repo: it builds the encoder with the standard Transformers `Qwen3Model` run bidirectionally via `config.is_causal = False` (hence `transformers>=5.2`, which passes `is_causal` through to the attention backend), applies this repo's fine-tuned weights and the two heads, and decodes spans with the constrained BIOES Viterbi included in the file. Input is truncated to `max_seq_len` (4096) tokens; chunk longer documents before calling `predict`. `model.save_pretrained(dir)` also saves the tokenizer, so the saved directory loads and predicts on its own. `model.safetensors` holds the fine-tuned backbone (bf16, `backbone.*`), both heads (fp32, `token_cls_head.*` / `sensitivity_head.*`), and the Viterbi bias scalars (`viterbi.*`). `max_seq_len` is 4096 tokens.
翻訳待ち・原文を表示
入力 テキスト→ 出力 テキスト
This repository provides PII-Tracer, the detector introduced in PII-TRACE. GGUF packaging of `perplexity-ai/PII-Tracer`, a PII masking model for conversational data. The model uses a ~600M-parameter bidirectional Qwen3 encoder with a `perplexity-ai/pplx-embed-v1-0.6b` backbone and two heads: - **Token classification head** (1024 → 37): BIOES tags over 9 PII categories (`private_person`, `account_number`, `private_url`, `private_date`, `private_address`, `private_email`, `private_phone`, `other_pii`, `secret`), decoded with a constrained Viterbi decoder. - **Sensitivity head** (1024 → 1): conversation-level sensitivity classifier on mean-pooled hidden states.
翻訳待ち・原文を表示
入力 テキスト→ 出力 テキスト
MLX weights for PII-Tracer, a PII masking model for conversational data. The model uses a ~600M-parameter bidirectional Qwen3 encoder with a `perplexity-ai/pplx-embed-v1-0.6b` backbone and two heads: The backbone's linear projections use **8-bit affine quantization with group size 64**. Embeddings and normalization weights remain bf16; both heads remain fp32. The weights file is approximately 779 MB. Quantized projections retain the `backbone.*` key names and store packed `uint32` `weight` tensors with bf16 `scales` and `biases`. The unquantized heads use `token_cls_head.*` and `sensitivity_head.*`.
翻訳待ち・原文を表示
入力 テキスト→ 出力 テキスト
基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
入力 テキスト→ 出力 テキスト
基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
基本情報を収録・詳細は順次追加
分類準備中
入力 未確認→ 出力 未確認
llama.cpp GGUF build of the pplx-computer qwen3.8 27B checkpoint (`Qwen3_5ForConditionalGeneration`, dense hybrid GDN linear-attention + full attention every 4th of 64 layers), converted 2026-08-26 from the raw bf16 checkpoint. Ships **two speculative-decoding drafts — pick one**: the checkpoint's native MTP head, or the DFlash2 block-diffusion drafter. DFlash2 is **not** in llama.cpp master: build PR #27342 (`z-lab:dflash2`, verified at `f7aadef`). On master the draft fails with `done_getting_tensors: wrong number of tensors; expected 81, got 58`. DFlash2 drafts longer blocks per verification step (higher throughput ceiling); native MTP has a higher acceptance rate and runs on unpatched llama.cpp. Default to MTP unless you already run the PR build.
翻訳待ち・原文を表示
分類準備中
入力 未確認→ 出力 未確認
MLX 4-bit build of the `qwen3.8_27b_rft_sdpo_10kdata_tools_88` RFT checkpoint (Qwen3.8-27B, RFT/SDPO tools post-training) — the same weights as `perplexity-ai/pplx-computer-qwen-3-8-27b-dflash2-20260824` (NVFP4), converted here from the original **bf16** checkpoint, not from the NVFP4 quant.
翻訳待ち・原文を表示
入力 テキスト · 画像→ 出力 テキスト
pplx-decider-flash-v1.2 is the small version of pplx-decider-v1.2: the same joint request format, the same API and the same text and image support, at about one seventh of the size. It is built on Qwen3.5-4B, **distilled from the 27B decision models** on their training requests (the student learns the teachers' full probability distributions, not just their answers). It combines several training runs through model souping (weight averaging). Use it when latency or cost matters more than the last points of accuracy. On our evaluations it keeps most of the 27B model's Decision Index and vision scores (see below). Distillation also improves results on decision tasks held out from all training. Stock `llama-server` does not implement this checkpoint's protocol v3; its `/v1/systemone` uses protocol v1. A compatible runtime must:
翻訳待ち・原文を表示
入力 テキスト→ 出力 テキスト
基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
入力 テキスト→ 出力 テキスト
pplx-decider-v1.1-27b is an update of our pplx-decider-v1-27b model, that boost the Decision Index score from 56.4 to 61.56, now outperforming Jev by more than 3.5 points, while using the same backbone. Most of the gains are driven by the lifting of the causal mask and training on more data, including data from tasksource. This is the **native decision-checkpoint layout**: a `Qwen3_5Model` backbone plus `readout.safetensors` containing a BF16 `[255, 5120]` decision head. The Transformers class name does not change the base model identity, Qwen3.8-27B. Use Python 3.12+, authenticated Hugging Face access to this private repository, and a CUDA GPU with room for roughly 49 GiB of weights plus working memory. Download the repository and install its pinned `requirements.txt` dependencies.
翻訳待ち・原文を表示
入力 テキスト→ 出力 テキスト
基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
入力 テキスト→ 出力 テキスト
Accuracy across 11 benchmarks. The pplx-decider-v1-27b results were measured through the Perplexity API. uv installs the dependencies; the script downloads the model from Hugging Face. In an environment with these dependencies installed, use `Decider` directly: Use `{"type": "noul", "instructions": "Does this message express urgency?"}` for a yes/no probability. For images, pass `images=["screenshot.png"]` to `predict`, or run:
翻訳待ち・原文を表示
入力 テキスト→ 出力 テキスト
`pplx-embed-v1` and `pplx-embed-context-v1` are state-of-the-art text embedding models optimized for real-world, web-scale retrieval tasks. > [!IMPORTANT] > `pplx-embed-v1` and `pplx-embed-context-v1` natively produce *unnormalized* int8-quantized embeddings. Ensure that you compare them via *cosine similarity*. Many modern embedding models rely on instruction tuning, where users prepend an instruction string to the text being embedded. This can yield a 2%-3% lift on benchmarks, but it also introduces prompt-selection overhead and can make indexing pipelines brittle (small instruction changes can shift embedding space). We deliberately **avoid** this requirement: you can embed the text you want to index directly, without having to choose or maintain an instruction prefix.
翻訳待ち・原文を表示
入力 テキスト→ 出力 埋め込み
`pplx-embed-v1` and `pplx-embed-context-v1` are state-of-the-art text embedding models optimized for real-world, web-scale retrieval tasks. > [!IMPORTANT] > `pplx-embed-v1` and `pplx-embed-context-v1` natively produce *unnormalized* int8-quantized embeddings. Ensure that you compare them via *cosine similarity*. Many modern embedding models rely on instruction tuning, where users prepend an instruction string to the text being embedded. This can yield a 2%-3% lift on benchmarks, but it also introduces prompt-selection overhead and can make indexing pipelines brittle (small instruction changes can shift embedding space). We deliberately **avoid** this requirement: you can embed the text you want to index directly, without having to choose or maintain an instruction prefix.
翻訳待ち・原文を表示
入力 テキスト→ 出力 埋め込み
`pplx-embed-v1` and `pplx-embed-context-v1` are state-of-the-art text embedding models optimized for real-world, web-scale retrieval tasks. - Use **`pplx-embed-v1`** for independent text embedding (queries, documents, semantic search) - Use **`pplx-embed-context-v1`** for document chunks in RAG systems where surrounding context matters > [!IMPORTANT] > `pplx-embed-v1` and `pplx-embed-context-v1` natively produce *unnormalized* int8-quantized embeddings. Ensure that you compare them via *cosine similarity*.
翻訳待ち・原文を表示
入力 テキスト→ 出力 埋め込み
`pplx-embed-v1` and `pplx-embed-context-v1` are state-of-the-art text embedding models optimized for real-world, web-scale retrieval tasks. - Use **`pplx-embed-v1`** for independent text embedding (queries, documents, semantic search) - Use **`pplx-embed-context-v1`** for document chunks in RAG systems where surrounding context matters > [!IMPORTANT] > `pplx-embed-v1` and `pplx-embed-context-v1` natively produce *unnormalized* int8-quantized embeddings. Ensure that you compare them via *cosine similarity*.
翻訳待ち・原文を表示
入力 テキスト→ 出力 埋め込み
基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
基本情報を収録・詳細は順次追加
入力 テキスト→ 出力 埋め込み
基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
入力 テキスト→ 出力 埋め込み
基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
入力 テキスト→ 出力 埋め込み
基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
基本情報を収録・詳細は順次追加
入力 テキスト→ 出力 埋め込み
基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
基本情報を収録・詳細は順次追加
入力 テキスト→ 出力 テキスト
基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
基本情報を収録・詳細は順次追加
分類準備中
入力 未確認→ 出力 未確認
