castorini/afribertalarge fine-tuned on the Kiswahili subset of AfriSenti (Muhammad et al., 2023) to classify tweets as positive / neutral / negative. best epoch selected on validation macro-F1 (seed 42). Demo: https://huggingface.co/spaces/RubaxTyra/kiswahili-sentiment-demo Limitations: trained on only 1,810 tweets; emojis and punctuation were removed from the training data; struggles with sarcasm, slang/Sheng and with negative news vs negative opinion.
SAVRN Model Hub
Open-Weight Models
An open-weight model is an AI model whose trained weights are published for anyone to download. The weights are what the model learned in training. With a copy of them you can run the model on hardware you control and train it further on your own data.
Open weights are not the same as open source. Many publishers release the weights without the training data or code, and the license sets what you may do with the model. This library puts each model's full card, architecture, files, license and published evaluations on one page.
11,442Models
3,247Datasets
285Papers
6,976Publishers
12,091Sourced relationships
Updated 2026-10-19 · How the library is built
11,442 models, sorted by most downloaded.
English grapheme-to-phoneme resources for KittenTTS and Kokoro TTS. Downloaded automatically by mlx-audio-swift when using KittenTTS or Kokoro TTS with English voices. Ported from Misaki G2P engine (MIT license).
같은 사실을 긍정적인 틀 또는 부정적인 틀로 제시하는 가치 프레이밍(valence framing)을 다룹니다. 예를 들어 "GDP 2.3% 성장"을 "견조한 성장세"로 쓰면 긍정, "성장 둔화 우려"로 쓰면 부정입니다. 코드: https://github.com/likeramm/econ-framing-bias - 방법: LLM 라벨을 소형 모델로 옮기는 지식 증류. klue/roberta-large를 파인튜닝했습니다. - 라벨: gpt-5.5가 라벨링 가이드라인 프롬프트(v2)로 판정한 결과 (OpenAI Batch API) - 학습 8,866 / 검증 1,900 / 테스트 1,901 (층화 분할, seed 42). 검증셋으로 모델을 고르고, 테스트셋으로 최종 보고 - 입력: 제목 [SEP] 본문 앞 500자, 최대 256 토큰 - 설정: lr 1e-5, batch 4 × gradient accumulation 2, 최대 6 epoch(조기 종료 patience 2), 클래스 가중 교차엔트로피, FP16, RTX 4060 테스트셋 (n=1,901, 정답 = gpt-5.5 라벨) 사람 라벨과의 일치도 (파일럿 50건, 학습 제외): 정확도 0.74, Cohen's κ 0.58 - 중립이 가장 어렵습니다. 사람과 LLM의 판단도 중립에서 가장 많이 엇갈립니다. - 사건의 좋고 나쁨에 끌리는 경향이 있습니다. "GDP 2.3% 성장…
Automated multi-class knee cartilage segmentation on magnetic resonance imaging (MRI) scans from the Osteoarthritis Initiative (OAI / OAIZIB-CM). This repository provides a deep learning testbed for benchmarking and evaluating 2D, 2.5D, and 3D segmentation architectures on femoral cartilage (FC), medial tibial cartilage (MTC), and lateral tibial cartilage (LTC). - UNet (2D Slice baseline) - Pseudo3D (2.5D Triplet channel-stacking) - nnUNet (2D residual blocks with deep supervision) - TransUNet (Hybrid CNN-Transformer encoder with ViT bottleneck) - UNet3D (Volumetric 3D U-Net with attention gates) 1. Install dependencies: 2. Generate an experiment notebook
local, typed decisions from qwen3.5-2b. one shared state is prefetched once, each question is isolated, every allowed answer is scored as a complete token sequence, and python returns validated choice, score, and noul results. this is an inference system, not rlcd training and not a clone of typesafe jev. it never calls typesafe. the published qwen checkpoint is unchanged; fp8 changes execution precision only. probabilities are normalized support over the candidates you provide, not calibrated correctness probabilities. unlike ordinary autoregressive json generation, the model does not write a response token by token. it scores only the values supplied by the caller. complete-sequence…
Reading notes and an experiment sketch for Knowledge Distillation. The repository emphasizes what still needs to be tested instead of manufacturing scores or release claims. - the scope of the research question and likely confounders - a proposed comparison with matched baselines - concrete evaluation context such as task-appropriate public benchmarks named in the main note - reproducibility checks, failure modes, and open questions - topic-relevant references Start with summary.md for the full note. Sections labeled as plans or hypotheses should not be interpreted as experimental results. If results are added later, they should include dataset versions, commands, seeds, hardware, and raw…
This repository contains a working research note about Knowledge Distillation. It organizes motivation, related work, a falsifiable hypothesis, and an evaluation plan. It is not presented as a completed paper or a release of trained models. - the scope of the research question and likely confounders - a proposed comparison with matched baselines - concrete evaluation context such as task-appropriate public benchmarks named in the main note - reproducibility checks, failure modes, and open questions - topic-relevant references Start with summary.md for the full note. Sections labeled as plans or hypotheses should not be interpreted as experimental results. If results are added later, they…
This model is a fine-tuned version of skt/kobert-base-v1 on the None dataset. It achieves the following results on the evaluation set: The following hyperparameters were used during training: - learningrate: 2e-05 - trainbatchsize: 16 - evalbatchsize: 16 - lrschedulertype: linear - numepochs: 5 - Transformers 5.17.0 - Pytorch 2.11.0+cu130 - Datasets 4.8.5 - Tokenizers 0.23.2
Kodiak is an encoder-only "System One" decision model by Cortex Agent LLC: a state (text, list of texts, or JSON) plus typed questions in, calibrated answers out, in one forward pass. Choice answers are always one of your labels, scores stay inside your range, and every question can come back as "not answerable from this state" with its own probability. The large model beats every open zero-shot classifier we tested on never-seen tasks (release criterion 1; decision D33). Details: - Run b-base-s1-v2-s1 (seed 1 of three, chosen by validation loss, not the eval set), step 6000. ModernBERT-large backbone (Apache-2.0). Calibration temperatures baked in; default abstain threshold from…
Kodiak is an encoder-only "System One" decision model by Cortex Agent LLC: a state (text, list of texts, or JSON) plus typed questions in, calibrated answers out, in one forward pass. Choice answers are always one of your labels, scores stay inside your range, and every question can come back as "not answerable from this state" with its own probability. Trained on the public datasets plus Generator v2 synthetic data (9,137 training examples): a 971-document-type taxonomy, ~45% real web passages, questions labeled stated / inferred / unanswerable, and two AI critics. Compared with the same model trained on the v1 synthetic data at equal size, averaged over three training runs each: So v2…
Native-context conversion of Kokoro-82M v1.0. It accepts phonemes and generates mono 24 kHz Float PCM. The bundle includes afheart and amadam; measurements use afheart at speed 1. Glade is a native Swift library for speech inference on Apple silicon, using Core AI, Core ML, and model-specific host implementations. Its runtime source is currently private. This repository distributes the model assets and runtime metadata used by that library. Python is export/measurement tooling, not an application dependency. Mac qualification is included; iPhone and Watch qualification is not claimed. Download weights and configuration from one snapshot. The profile retains up to 510 phoneme symbols, with…
The fp32 onnx/model.onnx from onnx-community/Kokoro-82M-v1.0-ONNX at revision 1939ad2a, with the graph cut at decoder.generator.convpost. The weights are unchanged. Why: on onnxruntime-web 1.27 WebGPU, the full graph's iSTFT tail (ConvTranspose/ScatterND) returns zeros for every sample past about 65,528 (2.7 s at 24 kHz). Callers then have to feed short phrases, and that audibly flattens the prosody. Inputs: inputids int64 [1, n], style float32 [1, 256], speed float32 [1] (same as upstream). iSTFT to run in the caller (nfft 20, hop 5; istftbasis.json = the 22x20 inverse basis): This matches the full graph's waveform to within 6e-7 (max abs, CPU). Kokoro-82M is by hexgrad, released under…
Model Collections
Hand-picked starting points, each with the reason it exists.
Collection · 4 entries
Embedding models for retrieval
Sentence and document embedding models used to build retrieval systems. Dimension and sequence length matter more than size here, and both come from the publisher.
Collection · 4 entries
Models that fit on one accelerator
Models whose publisher-reported parameter count puts them within reach of a single accelerator at common precisions. Memory needed depends on precision and serving configuration, so treat the parameter count as the starting point, not the answer.
Collection · 6 entries
Open-weight text models worth knowing
Widely used open-weight language models, chosen because each one is a distinct family rather than a variant of the one above it. Selection, not a ranking.
Collection · 3 entries
Speech and audio models
Recognition and synthesis models, grouped so the two directions are easy to compare.
Open-Weight Models Explained
What is an open-weight model?
An AI model whose trained weights are published for anyone to download, so it can be run, tested and fine-tuned on hardware the user controls.
Is an open-weight model the same as open source?
Not always. Open weights means the trained model can be downloaded. Open source usually also means the training code and data are available and the license allows broad reuse. Many open-weight models release the weights only.
Can I use an open-weight model commercially?
It depends on the license. Apache 2.0 and MIT allow commercial use. Other licenses limit it, for example to non-commercial use or below a set number of users. Every model page here shows its license.
How much memory does an open-weight model need?
About two bytes per parameter at 16-bit precision, so a 7-billion-parameter model needs roughly 14 GB for its weights, plus memory for the context it processes. Each model page lists its parameter count and the size of its files.
Related SAVRN Research
The hub sits beside SAVRN's market data and infrastructure research: what models cost to run, and what it takes to run them.
SAVRN Index
What open models cost to run
The same open-weight model priced by every host that serves it, per million tokens.
Research Hub
Data center trackers and maps
Moratoriums, permits, power, water and capital behind the facilities that run these models.
Method
How the Model Hub is built
Sources, evidence labels, refresh behaviour, and the limits of every comparison here.