KnowLine-4B-Gen5.5
PelaAI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。
基础资料已收录 · 缺失资料后续补充
输入 文本→ 输出 文本
价格待核验多模态与渠道费用须分别核对
查看详情 ↗DISCOVER & COMPARE
探索 AI 模型 2428
PII-Tracer
perplexity-aiPII 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.
译文排队中 · 当前显示来源原文
输入 文本→ 输出 文本
价格待核验多模态与渠道费用须分别核对
查看详情 ↗PII-Tracer-GGUF
perplexity-aiThis 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.
译文排队中 · 当前显示来源原文
输入 文本→ 输出 文本
价格待核验多模态与渠道费用须分别核对
查看详情 ↗PII-Tracer-MLX
perplexity-aiMLX 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.*`.
译文排队中 · 当前显示来源原文
输入 文本→ 输出 文本
价格待核验多模态与渠道费用须分别核对
查看详情 ↗pplx-decider-flash-gguf-v1.2
perplexity-aipplx-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:
译文排队中 · 当前显示来源原文
输入 文本→ 输出 文本
价格待核验多模态与渠道费用须分别核对
查看详情 ↗pplx-decider-flash-v1.2
perplexity-ai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。
输入 文本→ 输出 文本
价格待核验多模态与渠道费用须分别核对
查看详情 ↗pplx-decider-v1.1-27b
perplexity-aipplx-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.
译文排队中 · 当前显示来源原文
输入 文本→ 输出 文本
价格待核验多模态与渠道费用须分别核对
查看详情 ↗pplx-decider-v1.2
perplexity-ai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。
输入 文本→ 输出 文本
价格待核验多模态与渠道费用须分别核对
查看详情 ↗pplx-decider-v1-27b
perplexity-aiAccuracy 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:
译文排队中 · 当前显示来源原文
输入 文本→ 输出 文本
价格待核验多模态与渠道费用须分别核对
查看详情 ↗pplx-pii-masking-vllm
perplexity-ai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。
基础资料已收录 · 缺失资料后续补充
输入 文本→ 输出 文本
价格待核验多模态与渠道费用须分别核对
查看详情 ↗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。
基础资料已收录 · 缺失资料后续补充
输入 文本→ 输出 文本
价格待核验多模态与渠道费用须分别核对
查看详情 ↗bert-imdb-model
philipobiorah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。
基础资料已收录 · 缺失资料后续补充
输入 文本→ 输出 文本
价格待核验多模态与渠道费用须分别核对
查看详情 ↗programming-language-identification
philomath-1209This Model is a fine-tuned version of *huggingface/CodeBERTa-small-v1* on *cakiki/rosetta-code* Dataset for 26 Programming Languages as mentioned below. Model is trained for 25 epochs on Azure for nearly 26000 Datapoints for above Mentioned 26 Programming Languages extracted from Dataset having 1006 of total Programming Language. 'ARM Assembly': 'AppleScript' 'C' 'C#' 'C++' 'COBOL' 'Erlang' 'Fortran' 'Go' 'Java' 'JavaScript' 'Kotlin' 'Lua 'Mathematica/Wolfram Language' 'PHP' 'Pascal' 'Perl' 'PowerShell' 'Python' 'R 'Ruby' 'Rust' 'Scala' 'Swift' 'Visual Basic .NET' 'jq'
译文排队中 · 当前显示来源原文
输入 文本→ 输出 文本
价格待核验多模态与渠道费用须分别核对
查看详情 ↗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。
基础资料已收录 · 缺失资料后续补充
输入 文本→ 输出 文本
价格待核验多模态与渠道费用须分别核对
查看详情 ↗distilbert-onnx-banking77
philschmid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。
基础资料已收录 · 缺失资料后续补充
输入 文本→ 输出 文本
价格待核验多模态与渠道费用须分别核对
查看详情 ↗distilroberta-base-ner-conll2003
philschmid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。
输入 文本→ 输出 文本
价格待核验多模态与渠道费用须分别核对
查看详情 ↗MiniLM-L6-H384-uncased-sst2
philschmid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。
输入 文本→ 输出 文本
价格待核验多模态与渠道费用须分别核对
查看详情 ↗tiny-bert-sst2-distilled
philschmidThis model is a fine-tuned version of google/bert_uncased_L-2_H-128_A-2 on the glue dataset. It achieves the following results on the evaluation set: - Loss: 1.7305 - Accuracy: 0.8326 The following hyperparameters were used during training: - learning_rate: 0.0007199555649276667 - train_batch_size: 1024 - eval_batch_size: 1024 - seed: 33 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 7 - mixed_precision_training: Native AMP
译文排队中 · 当前显示来源原文
输入 文本→ 输出 文本
价格待核验多模态与渠道费用须分别核对
查看详情 ↗Phocinae-Largha-150M-v1
Phocinae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。
基础资料已收录 · 缺失资料后续补充
输入 文本→ 输出 文本
价格待核验多模态与渠道费用须分别核对
查看详情 ↗ner-bert-base-cased-pt-lenerbr
pierreguillou**ner-bert-base-portuguese-cased-lenerbr** is a NER model (token classification) in the legal domain in Portuguese that was finetuned on 20/12/2021 in Google Colab from the model pierreguillou/bert-base-cased-pt-lenerbr on the dataset LeNER_br by using a NER objective. Due to the small size of BERTimbau base and finetuning dataset, the model overfitted before to reach the end of training. Here are the overall final metrics on the validation dataset (*note: see the paragraph "Validation metrics by Named Entity" to get detailed metrics*): - **f1**: 0.8926146010186757 - **precision**: 0.8810222036028488 - **recall**: 0.9045161290322581 - **accuracy**: 0.9759397808828684 - **loss**: 0.18803243339061737 **Note**: the model pierreguillou/bert-base-cased-pt-lenerbr is a language model that was created through the finetuning of the model BERTimbau base on the dataset LeNER-Br language modeling by using a MASK objective. This first specialization of the language model before finetuning on the NER task improved a bit the model quality. To prove it, here are the results of the NER model finetuned from the model BERTimbau base (a non-specialized language model): - **f1**: 0.8716487228203504 - **precision**: 0.8559286898839138 - **recall**: 0.8879569892473118 - **accuracy**: 0.9755893153732458 - **loss**: 0.1133928969502449
译文排队中 · 当前显示来源原文
输入 文本→ 输出 文本
价格待核验多模态与渠道费用须分别核对
查看详情 ↗ner-bert-large-cased-pt-lenerbr
pierreguillou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。
基础资料已收录 · 缺失资料后续补充
输入 文本→ 输出 文本
价格待核验多模态与渠道费用须分别核对
查看详情 ↗senda
pin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。
基础资料已收录 · 缺失资料后续补充
输入 文本→ 输出 文本
价格待核验多模态与渠道费用须分别核对
查看详情 ↗Winnow-12B-GGUF
Piotr1215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。
输入 文本→ 输出 文本
价格待核验多模态与渠道费用须分别核对
查看详情 ↗gliner2-polish-pii
piotrmaciejbednarski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。
基础资料已收录 · 缺失资料后续补充
输入 文本→ 输出 文本
价格待核验多模态与渠道费用须分别核对
查看详情 ↗暂未找到匹配模型
可以调整厂商、分类或输入输出条件；新模型正持续收录。
COST EXPLORER
好模型，也要算好成本。
调整月度 Token 用量，直观比较不同模型的预估 API 开支。
1 M = 100 万 Token · 美元计价
仅比较同一渠道的基础文本 Token 报价
仅比较同一渠道的基础文本 Token 报价
使用已采集且单位可比的 USD / 百万 Token 渠道报价。报价为采集时快照；不计缓存优惠、阶梯价、推理额外输出与税费，请以来源的当前报价为准。
MODEL HANDBOOK
读懂模型，再做选择
API 价格应该怎么比较？+
先区分输入、输出和缓存价格，再使用同一任务和用量估算总费用。图像、音频和视频可能按张、时长或分辨率计费，不能直接与 Token 单价比较。
开放权重，就代表可以免费商用吗？+
不一定。必须逐一核对具体模型版本的许可证、商用限制及使用政策。自己部署还需要考虑显存、推理资源和运维费用。
排行榜第一，就是最适合我的模型吗？+
榜单取决于测试任务、版本与评测方法。建议用实际业务样本比较准确性、时延、稳定性和成本，再选择模型。