Jeff_Geema-GGUF
arunb74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。
Basic profile indexed · More details to follow
Input Text→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗DISCOVER & COMPARE
Explore AI models 2428
tner-xlm-roberta-base-ontonotes5
asahi417XLM-RoBERTa finetuned on NER. - **Developed by:** Asahi Ushio - **Shared by [Optional]:** Hugging Face - **Model type:** Token Classification - **Language(s) (NLP):** en - **License:** More information needed - **Related Models:** XLM-RoBERTa - **Parent Model:** XLM-RoBERTa - **Resources for more information:** - GitHub Repo - Associated Paper - Space This model can be used in conjunction with the tner library. The model should not be used to intentionally create hostile or alienating environments for people.
Input Text→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗tner-xlm-roberta-large-bc5cdr
asahi417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。
Basic profile indexed · More details to follow
Input Text→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗This model was created using xlm-roberta-base bodel and fine-tuned it using CoNLL 2003 dataset. On top of the trained model, we trained it again using a Sinhala NER data that was also formatted to the CoNLL format.
Input Text→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗query_wellformedness_score
Ashishkr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。
Basic profile indexed · More details to follow
Input Text→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗french_emotion_camembert
astrosbd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。
Basic profile indexed · More details to follow
Input Text→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗koelectra-ko-pii-ner
atonlee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。
Input Text→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗SecureModernBERT-NER
attack-vector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。
Input Text→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗legal-bert-ner-base-cased-ptbr-onnx
augustaklugConversão sem fusões do modelo `dominguesm/legal-bert-ner-base-cased-ptbr` para uso com Transformers.js em WebGPU e WASM. O tokenizer diferencia maiúsculas e minúsculas e tem `model_max_length=512`. Além de PESSOA, ORGANIZACAO e LOCAL, o modelo produz TEMPO, LEGISLACAO e JURISPRUDENCIA. O benchmark da Epryx compara somente as três primeiras classes. Em oito frases jurídicas (129 tokens válidos), o FP16 preservou 129/129 predições `argmax` do ONNX FP32. O erro absoluto médio nos logits foi 0,001120 e o máximo foi 0,007393.
Input Text→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗crp-safety-deberta-v1
AutoCyberAI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。
Basic profile indexed · More details to follow
Input Text→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗setfit
automatedMotiveCoder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。
Basic profile indexed · More details to follow
Input Text→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗EthicalEye
autopilot-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。
Input Text→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗AutoTrust-JEV-27B-v1.1
autotrustAutoTrust-JEV-27B v1.1 is a text decision model that assigns probabilities to the answer options supplied with each question. This card reports its measured performance on the Decision Index 0.3 public suite. **Public index: 67.31** | **37 indexed benchmarks** | **140,178 completed scoreable requests** This is a complete local evaluation using the official evaluation kit, self-reported pending maintainer verification. No private or Full score is reported.
Input Text→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗GEV-26B-Decide-NVFP4
autotrust> [!IMPORTANT] > **Try AutoTrust/GuruSearch live (new, 11 October 2026).** A recommendation and search demo in which every ranking is a > calibrated System 1 decision, made in about half a second: > * **Recommendation:** the latest headlines from 6 news feeds, ranked by importance. > * **Search:** results from Google News, Bing News and Yahoo News re-ranked by relevance, side by side with the > search engines' own order, plus a short answer with citations. This repository is **autotrust/GEV-26B-Decide with its 3,840 routed expert MLPs (30 layers × 128 experts) quantized to NVFP4**. Everything else is the bf16 model unchanged: attention, the dense MLP of every layer, the routers, the vision tower, the lm_head, the System 1 adapter, the decision head and the temperatures. The rest of this card is the card of GEV-26B-Decide; its benchmark tables are the bf16 results, and the NVFP4 comparison is below. GPQA Diamond and HLE are the Decision Index items; the bf16 row is the model's `transformers` engine, the NVFP4 row is vLLM with this checkpoint. The differences are within run-to-run noise (198 questions: about ±7 points).
Input Text→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗JEV-27B
autotrust> [!IMPORTANT] > **Try AutoTrust/GuruSearch live (new, 11 October 2026).** A recommendation and search demo in which every ranking is a > calibrated System 1 decision, made in about half a second: > * **Recommendation:** the latest headlines from 6 news feeds, ranked by importance. > * **Search:** results from Google News, Bing News and Yahoo News re-ranked by relevance, side by side with the > search engines' own order, plus a short answer with citations. **autotrust/JEV-27B-VL**, autotrust/JEV-27B with vision, is now online. **Fast, calibrated System 1 decisions that are indistinguishable from the closed TypeSafe Jev 1.13 by KL, and deliberate System 2 generation and reasoning from an untouched Qwen3.8-27B — one set of weights, one vLLM engine, routed per request. It succeeds JEV-9B with closer System 1 fidelity, stronger transfer to unseen tasks and a stronger System 2, and it answers a single decision in about half the time the hosted API takes.**
Input Text→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗JEV-35B-NVFP4
autotrust> [!IMPORTANT] > **Try AutoTrust/GuruSearch live (new, 11 October 2026).** A recommendation and search demo in which every ranking is a > calibrated System 1 decision, made in about half a second: > * **Recommendation:** the latest headlines from 6 news feeds, ranked by importance. > * **Search:** results from Google News, Bing News and Yahoo News re-ranked by relevance, side by side with the > search engines' own order, plus a short answer with citations. This repository is **autotrust/JEV-35B with its 10,240 routed expert MLPs (40 layers × 256 experts) quantized to NVFP4**. Everything else is the bf16 model unchanged: attention, linear attention, the shared expert, the routers, the vision tower, the MTP layer, the lm_head, the System 1 adapter, the decision head and the temperatures. Below the NVFP4 comparison, the rest of this card is the JEV-35B card; its tables are the bf16 results unless marked otherwise. * **Text: −0.57 on the Decision Index.** All five areas within 1.2 skill points of bf16 (Knowledge 0.422, Language 0.628, Retrieval 0.706, Tools 0.753, Arts 0.413); the largest per-benchmark changes are Home appliance simulator −5.7, CRUXEval −4.7 and GPQA +5.4. * **Images: −0.85 on the vision rebuild**, a small but real loss (paired bootstrap 95 % interval −1.5 to −0.2), mostly on CharXiv charts (−5.3). * **Robot arm: 13 of 20 scenes against 15 of 20.** Four scenes changed outcome (3 lost, 1 gained), within noise (sign test p = 0.63); every grasped cube still reached the tray (13/13). * **Speed:** the same latency as bf16 on one B200 for single requests; the gain is memory (one 32–48 GB GPU is enough). * **Games** (seed 0, one run each, noisy): 2048 largest tile 64 (bf16 32), Snake 5 food (bf16 11), Quick, Draw! 85.9 % on finished sketches (bf16 86.3 %), chess mate-in-one 45 % (bf16 47 %), Connect Four 1 win of 6 (bf16 0).
Input Text→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗JEV-Gemma4-26B-A4B
autotrust> [!IMPORTANT] > **Try AutoTrust/GuruSearch live (new, 11 October 2026).** A recommendation and search demo in which every ranking is a > calibrated System 1 decision, made in about half a second: > * **Recommendation:** the latest headlines from 6 news feeds, ranked by importance. > * **Search:** results from Google News, Bing News and Yahoo News re-ranked by relevance, side by side with the > search engines' own order, plus a short answer with citations. This bundle serves two systems from one set of base weights. **System 2** is the unmodified `google/gemma-4-26B-A4B-it` (a 26 B-parameter mixture-of-experts model with ≈ 4 B active parameters per token, text and image input): generation and reasoning, bit-identical to the base model. **System 1** adds a LoRA adapter and a 24-slot decision head and returns calibrated probabilities for three typed primitives in one prefill pass: * `noul`: true / false * `choice`: 2–16 options (wider questions are read in groups of ≤ 16 plus a final) * `score`: 0–5
Input Text→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗bev-decider-0.4B
avbiswas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。
Basic profile indexed · More details to follow
Input Text→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗bert-base-uncased-sst2
aviator-neural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。
Basic profile indexed · More details to follow
Input Text→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗heBERT_NER
avichrHeBERT is a Hebrew pretrained language model. It is based on Google's BERT architecture and it is BERT-Base config. HeBert was trained on three dataset: 1. A Hebrew version of OSCAR: ~9.8 GB of data, including 1 billion words and over 20.8 millions sentences. 2. A Hebrew dump of Wikipedia: ~650 MB of data, including over 63 millions words and 3.8 millions sentences 3. Emotion User Generated Content (UGC) data that was collected for the purpose of this study (described below). The ability of the model to classify named entities in text, such as persons' names, organizations, and locations; tested on a labeled dataset from Ben Mordecai and M Elhadad (2005), and evaluated with F1-score.
Input Text→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗HeBERT is a Hebrew pre-trained language model. It is based on Google's BERT architecture and it is BERT-Base config (Devlin et al. 2018). HeBert was trained on three datasets: 1. A Hebrew version of OSCAR (Ortiz, 2019): ~9.8 GB of data, including 1 billion words and over 20.8 million sentences. 2. A Hebrew dump of Wikipedia: ~650 MB of data, including over 63 million words and 3.8 million sentences 3. Emotion UGC data was collected for the purpose of this study. (described below) We evaluated the model on emotion recognition and sentiment analysis, for downstream tasks. Our User-Generated Content (UGC) is comments written on articles collected from 3 major news sites, between January 2020 to August 2020, Total data size of ~150 MB of data, including over 7 million words and 350K sentences. 4000 sentences annotated by crowd members (3-10 annotators per sentence) for 8 emotions (anger, disgust, expectation, fear, happy, sadness, surprise, and trust) and overall sentiment/polarity In order to validate the annotation, we search for an agreement between raters to emotion in each sentence using Krippendorff's alpha (krippendorff, 1970). We left sentences that got alpha > 0.7. Note that while we found a general agreement between raters about emotions like happiness, trust, and disgust, there are few emotions with general disagreement about them, apparently given the complexity of finding them in the text (e.g. expectation and surprise).
Input Text→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗Laya
AXERA-TECH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。
Basic profile indexed · More details to follow
Input Text→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗This model is a fine-tuned version of cahya/bert-base-indonesian-1.5G on the indonlu dataset. It achieves the following results on the evaluation set: - Loss: 0.3390 - Accuracy: 0.9373 The following hyperparameters were used during training: - learning_rate: 2e-05 - train_batch_size: 16 - eval_batch_size: 16 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 10
Input Text→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗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。
Basic profile indexed · More details to follow
Input Text→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗No matching models
Adjust provider, category or input/output filters. New models are added continuously.
COST EXPLORER
Great models. Clear costs.
Adjust monthly token usage to compare estimated API costs.
1 M = 1 million tokens · USD
Compares base text-token rates within the same channel
Compares base text-token rates within the same channel
Uses collected, comparable USD-per-million-token rates. Snapshots exclude cache discounts, tiers, extra reasoning output and taxes. Check current source prices.
MODEL HANDBOOK
Understand before you choose
How should API prices be compared?+
Separate input, output and cache rates, then estimate the same workload. Image, audio and video rates may use items, duration or resolution rather than tokens.
Do open weights mean free commercial use?+
Not necessarily. Check each version’s license, commercial restrictions and policies. Self-hosting also incurs compute and maintenance costs.
Is the top-ranked model the best for me?+
Rankings depend on tasks, versions and methods. Compare accuracy, latency, reliability and costs on your own workload.