Search FoxAI

AI Models 2119

• free-evo-qwen72b-v0.8-re↗

  freewheelin

  You need two models with the same architecture. - Choose one model and fine-tune it to create a gap between the original model and the fine-tuned one. It doesn't matter whether the evaluation score is higher or lower. - Merge the two models. - Evaluate the merged model. - Fine-tune a specific evaluation part of the model if you need to increase the score for that part. (It's unlikely to work as you think, but you can try it.) - Merge the models again. - Evaluate again. - Keep going until the average evaluation score is higher than the original one.

• Qwen3-4B-Instruct-2507-NVFP4↗

  llmat

  NVFP4-quantized version of `Qwen/Qwen3-4B-Instruct-2507` produced with llmcompressor. - Quantization scheme: NVFP4 (linear layers, `lm_head` excluded) - Calibration samples: 512 - Max sequence length during calibration: 2048 This model can be deployed efficiently using the vLLM backend, as shown in the example below.

• pythia-160m-deduped↗

  EleutherAI

  The *Pythia Scaling Suite* is a collection of models developed to facilitate interpretability research (see paper). It contains two sets of eight models of sizes 70M, 160M, 410M, 1B, 1.4B, 2.8B, 6.9B, and 12B. For each size, there are two models: one trained on the Pile, and one trained on the Pile after the dataset has been globally deduplicated. All 8 model sizes are trained on the exact same data, in the exact same order. We also provide 154 intermediate checkpoints per model, hosted on Hugging Face as branches. The Pythia model suite was designed to promote scientific research on large language models, especially interpretability research. Despite not centering downstream performance as a design goal, we find the models match or exceed the performance of similar and same-sized models, such as those in the OPT and GPT-Neo suites. Previously, we released an early version of the Pythia suite to the public. However, we decided to retrain the model suite to address a few hyperparameter discrepancies. This model card lists the changes ; see appendix B in the Pythia paper for further discussion. We found no difference in benchmark performance between the two Pythia versions. The old models are still available, but we suggest the retrained suite if you are just starting to use Pythia. **This is the current release.**

• gemma-3-12b-it-GGUF↗

  ggml-org

  Gemma is a family of lightweight, state-of-the-art open models from Google, built from the same research and technology used to create the Gemini models. Gemma 3 models are multimodal, handling text and image input and generating text output, with open weights for both pre-trained variants and instruction-tuned variants. Gemma 3 has a large, 128K context window, multilingual support in over 140 languages, and is available in more sizes than previous versions. Gemma 3 models are well-suited for a variety of text generation and image understanding tasks, including question answering, summarization, and reasoning. Their relatively small size makes it possible to deploy them in environments with limited resources such as laptops, desktops or your own cloud infrastructure, democratizing access to state of the art AI models and helping foster innovation for everyone. These models were trained on a dataset of text data that includes a wide variety of sources. The 27B model was trained with 14 trillion tokens, the 12B model was trained with 12 trillion tokens, 4B model was trained with 4 trillion tokens and 1B with 2 trillion tokens. Here are the key components: The combination of these diverse data sources is crucial for training a powerful multimodal model that can handle a wide variety of different tasks and data formats.

• Hy-Nomas↗

  腾讯

  **Hy-Nomas** is a video world generation model that supports free-form, multi-turn interaction through text instructions and camera control. It generates a world one video segment at a time, allowing users to introduce objects, change styles and scenes, describe actions, or control the camera as generation continues. The model combines a segment-wise autoregressive diffusion transformer (DiT), a Qwen text encoder, camera-conditioning modules, and a PixelUMM video decoder. A persistent key/value (KV) cache carries context between segments. The distilled inference configuration uses **8 denoising steps**, with **720 × 1280** output at **24 FPS**. A separate configuration supports video generation on a **single NVIDIA GeForce RTX 4090** using INT8 DiT weights, an INT8 KV cache, an FP8 decoder, and CPU offload. - **Free-form interaction:** Guide successive segments with instructions about subjects, actions, appearance, style, and environment. - **Camera control:** Supply camera trajectories alongside text to control viewpoint and movement. - **Continuous generation:** Reuse earlier context through a KV cache when extending the same world. - **Distilled inference:** Generate each segment with 8 DiT denoising steps and decode its latents with a fine-tuned PixelUMM decoder. - **Flexible deployment:** Use the standard sequence-parallel configuration or the single-GPU configuration, and interact through the web demo.

• chronos-t5-base↗

  amazon

  🚀 **Update Feb 14, 2025**: Chronos-Bolt & original Chronos models are now available on Amazon SageMaker JumpStart! Check out the tutorial notebook to learn how to deploy Chronos endpoints for production use in a few lines of code. 🚀 **Update Nov 27, 2024**: We have released Chronos-Bolt⚡️ models that are more accurate (5% lower error), up to 250 times faster and 20 times more memory-efficient than the original Chronos models of the same size. Check out the new models here. Chronos is a family of **pretrained time series forecasting models** based on language model architectures. A time series is transformed into a sequence of tokens via scaling and quantization, and a language model is trained on these tokens using the cross-entropy loss. Once trained, probabilistic forecasts are obtained by sampling multiple future trajectories given the historical context. Chronos models have been trained on a large corpus of publicly available time series data, as well as synthetic data generated using Gaussian processes.

• mms-tts-tir↗

  facebook

  This model is part of Facebook's Massively Multilingual Speech project, aiming to provide speech technology across a diverse range of languages. You can find more details about the supported languages and their ISO 639-3 codes in the MMS Language Coverage Overview, and see all MMS-TTS checkpoints on the Hugging Face Hub: facebook/mms-tts. VITS (**V**ariational **I**nference with adversarial learning for end-to-end **T**ext-to-**S**peech) is an end-to-end speech synthesis model that predicts a speech waveform conditional on an input text sequence. It is a conditional variational autoencoder (VAE) comprised of a posterior encoder, decoder, and conditional prior. A set of spectrogram-based acoustic features are predicted by the flow-based module, which is formed of a Transformer-based text encoder and multiple coupling layers. The spectrogram is decoded using a stack of transposed convolutional layers, much in the same style as the HiFi-GAN vocoder. Motivated by the one-to-many nature of the TTS problem, where the same text input can be spoken in multiple ways, the model also includes a stochastic duration predictor, which allows the model to synthesise speech with different rhythms from the same input text.

• Qwen3.8-Flash-Next-Uncensored-Q4_K_M-MTP↗

  him0413

  An **integrated MTP (Multi-Token Prediction) GGUF** build of the abliterated `Qwen3.8-Flash-Next-Uncensored` model, quantized to **Q4_K_M** with the MTP draft head **merged into the same 4-shard split** — no sidecar file needed. This model is an **abliterated (refusal-removed)** build. It will comply with harmful, unethical, or illegal requests the original `Qwen3.8-Flash-Next` would refuse. Released **strictly for legitimate research** — interpretability, AI-safety / refusal-mechanism study, red-teaming, and robustness evaluation. **You assume full responsibility** for how you use it and everything it generates; add your own safety and moderation layers before any deployment. **Qwen Community License 1.0** (see LICENSE), inherited from the base model `Qwen/Qwen3.8-Flash-Next`. Abliteration and quantization do not change the underlying license obligations.

• gemma-4-26B-A4B-it-qat-OptiQ-4bit↗

  mlx-community

  > **Built with mlx-optiq**, the MLX-native toolkit to quantize, fine-tune, and serve LLMs locally on Apple Silicon, no PyTorch and no cloud. Try the Lab · All OptiQ quants · Docs A 4-bit mixed-precision MLX quant produced by mlx-optiq, built on Google's quantization-aware-trained (QAT) Gemma-4 base. This is the **sparse-MoE** member of the family: 26B total parameters with 128 routed experts (about 4B active per token). OptiQ's sensitivity-guided per-layer bit allocation is applied on top of weights already trained to survive low-bit quantization, and it still beats a uniform 4-bit quant of the same QAT base on the Capability Score. This is a quant of google/gemma-4-26B-A4B-it-qat-q4_0-unquantized. Per-layer bit-widths come from a KL-divergence sensitivity pass on a six-domain calibration mix (prose, reasoning, code, agent, tool-call, constraint-bearing instructions). On this MoE the sensitivity pass identifies the routed experts as where precision matters most, so the allocation puts 8-bit on the experts that need it (42 of 90 expert tensors) plus the sensitive attention and router layers, and keeps the robust ones at 4-bit.

• sentence-t5-xl↗

  sentence-transformers

  This is a sentence-transformers model: It maps sentences & paragraphs to a 768 dimensional dense vector space. The model works well for sentence similarity tasks, but doesn't perform that well for semantic search tasks. This model was converted from the Tensorflow model st5-3b-1 to PyTorch. When using this model, have a look at the publication: Sentence-T5: Scalable sentence encoders from pre-trained text-to-text models. The tfhub model and this PyTorch model can produce slightly different embeddings, however, when run on the same benchmarks, they produce identical results. The model uses only the encoder from a T5-3B model. The weights are stored in FP16. If you find this model helpful, please cite the respective publication: Sentence-T5: Scalable sentence encoders from pre-trained text-to-text models