Per-expert QLoRA adapters (rank-128, alpha-256, FP32) for Morpho-180B SFT. Base: 72B dense backbone (4-bit NF4, frozen). Each expert trains to convergence (patience 2000 steps) on its unique domain data. size == 8 + headerlen + max(dataoffsets) = 6,737,255,616 bytes, 1,120 tensors, 80 layers × 14. Size-matching alone is not verification. = header-verified complete weights on this repo (00–58: 6,737,255,616 B fp32; 59–61: 3,368,705,936 B bf16 — see precision note on the model card). 64/64 secured and converged (all experts, all sectors). SFT COMPLETE. DPO 17/31 and training (02/04/05/06/09–15/17/18/20–23 DONE on Morpho-72B-MoE-DPO); final 14 training on GPU box with AUTOSKIP. Merge gated on…
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.
12,579Models
3,583Datasets
291Papers
7,578Publishers
12,850Sourced relationships
Updated 2026-10-23 · How the library is built
12,579 models, sorted by most downloaded.
Stage 5 of the Morpho-180B pipeline (display name; SFT backbone: - Per-expert DPO, same 64 experts, same one-example-one-expert mapping as SFT. - Real preference data only (HH-RLHF, HelpSteer2, UltraFeedback, Nectar), routed per expert by the v5 taxonomy. - DPO adapters initialize from the converged SFT adapters — never from scratch. Stage 5 IN PROGRESS — 17/31 experts DONE (resumed 3x, AUTOSKIP active, final leg running on 97GB GPU box). 24 eligible experts remain in the queue; 33 thin experts (<200 pairs) keep SFT-only per policy. Each row is verified from the expert's bestloss.txt + DONE.txt on this repo. Progress tracked on the model card.
Optimized ONNX Runtime (ORT) and Static INT8 QDQ / Dynamic INT8 models for MossFormer2 2-Speaker Speech Separation at 16kHz. Optimized for mobile inference with NNAPI / XNNPACK / CPU.
This repository archives Hugging Face models from multiple experiments and datasets in the MultiAgent4SyntheticBioNLP project. Remote paths mirror the project hierarchy beginning below experiments/, while local-only model or models container directories are removed. Each run directory is directly loadable as a Transformers subfolder: Each run contains only its final inference-model artifacts. Per-run metrics.json, prepared-data/, prepared training CSVs, and checkpoints are not uploaded. These are research artifacts for studying synthetic-data augmentation in biomedical NLP. They are not intended for clinical diagnosis or treatment decisions. Review the corresponding local experiment…
Unified Flow Modeling of Language and Vision in Embedding Spaces Multimodal Flow (MF) is a fully continuous framework for multimodal understanding and generation. Language and vision remain continuous states, organized as ordered hyperchunks in a shared causal stream. The same model interface supports text continuation, image understanding, and image generation. alt="Multimodal Flow architecture" width="100%"> Chang Huang, and Huazhong University of model weights are BF16. The release contains inference weights and configuration only; training states and optimizer states are not included. Use the models with the open-source code: Text inference uses the model package directly. Image…
Muse Glimmer is a 30-billion-parameter causal language model with a dedicated perception encoder, distilled from Muse Spark and purpose-built for autonomous agentic tasks on consumer hardware. The model integrates multi-step reasoning, reliable tool use, multimodal understanding, and failure recovery into a single model that runs locally without requiring cloud infrastructure or network access. Building effective agents requires key capabilities working together to achieve the user’s goals. Muse Glimmer is trained and evaluated on these capabilities: End-to-end Agentic Task Completion. Muse Glimmer achieves strong success rates on full-task benchmarks including DeepSearch QA, MCP-Atlas…
Library tempat menyimpan Anime dan Free download. Pusat arsip Anime dengan layanan unduhan gratis untuk kebutuhan Anda.
Download them in the Files & versions tab.
The MyAwesomeModel has undergone a significant version upgrade. In the latest update, MyAwesomeModel has significantly improved its depth of reasoning and inference capabilities by leveraging increased computational resources and introducing algorithmic optimization mechanisms during post-training. The model has demonstrated outstanding performance across various benchmark evaluations, including mathematics, programming, and general logic. Its overall performance is now approaching that of other leading models. Compared to the previous version, the upgraded model shows significant improvements in handling complex reasoning tasks. For instance, in the AIME 2025 test, the model's accuracy has…
The MyAwesomeModel has undergone a significant version upgrade. In the latest update, MyAwesomeModel has significantly improved its depth of reasoning and inference capabilities by leveraging increased computational resources and introducing algorithmic optimization mechanisms during post-training. The model has demonstrated outstanding performance across various benchmark evaluations, including mathematics, programming, and general logic. Its overall performance is now approaching that of other leading models. Compared to the previous version, the upgraded model shows significant improvements in handling complex reasoning tasks. For instance, in the AIME 2025 test, the model’s accuracy has…
The MyAwesomeModel has undergone a significant version upgrade. In the latest update, MyAwesomeModel has significantly improved its depth of reasoning and inference capabilities by leveraging increased computational resources and introducing algorithmic optimization mechanisms during post-training. The model has demonstrated outstanding performance across various benchmark evaluations, including mathematics, programming, and general logic. Its overall performance is now approaching that of other leading models. Compared to the previous version, the upgraded model shows significant improvements in handling complex reasoning tasks. For instance, in the AIME 2025 test, the model’s accuracy has…
The MyAwesomeModel has undergone a significant version upgrade. In the latest update, MyAwesomeModel has significantly improved its depth of reasoning and inference capabilities by leveraging increased computational resources and introducing algorithmic optimization mechanisms during post-training. The model has demonstrated outstanding performance across various benchmark evaluations, including mathematics, programming, and general logic. Its overall performance is now approaching that of other leading models. Compared to the previous version, the upgraded model shows significant improvements in handling complex reasoning tasks. For instance, in the AIME 2025 test, the model’s accuracy has…
The MyAwesomeModel has undergone a significant version upgrade. In the latest update, MyAwesomeModel has significantly improved its depth of reasoning and inference capabilities by leveraging increased computational resources and introducing algorithmic optimization mechanisms during post-training. The model has demonstrated outstanding performance across various benchmark evaluations, including mathematics, programming, and general logic. Its overall performance is now approaching that of other leading models. Compared to the previous version, the upgraded model shows significant improvements in handling complex reasoning tasks. For instance, in the AIME 2025 test, the model’s accuracy has…
The MyAwesomeModel has undergone a significant version upgrade. In the latest update, MyAwesomeModel has significantly improved its depth of reasoning and inference capabilities by leveraging increased computational resources and introducing algorithmic optimization mechanisms during post-training. The model has demonstrated outstanding performance across various benchmark evaluations, including mathematics, programming, and general logic. Its overall performance is now approaching that of other leading models. Compared to the previous version, the upgraded model shows significant improvements in handling complex reasoning tasks. For instance, in the AIME 2025 test, the model’s accuracy has…
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.