Saved toolsSubmit a tool
FOXAI SEARCH

Search FoxAI

AI Models 2119

  • DeepSeek-V4-Flash-0731-oQ4e-mtp↗

    Jundot

    > [!NOTE] > **Updated 2026-10-29:** Re-quantized with the improved oQe quantization in oMLX 0.7.3. Please re-download if you have an earlier copy. This model was quantized using oQ (oMLX v0.7.3) mixed-precision quantization with improved oQe (jundot/omlx#4930). A mixed-precision MLX checkpoint of deepseek-ai/DeepSeek-V4-Flash-0731, the official release of DeepSeek-V4-Flash with enhanced agentic capabilities. It has the same structure as DeepSeek-V4-Flash-DSpark, with a speculative decoding module attached. It includes the language model and the DSpark MTP weights.

  • PAW-27B-X3.1-GGUF↗

    lackonendes

    _If this model is useful to you, support the work by following @nawariokra on X, or buy me a coffee on Ko-fi._ Run `Qwen/Qwen3.8-27B` with good quality on a single RTX 3090 (24 GB VRAM) at full 262,144-token context — 129 tok/s generation, up to 1268 tok/s prompt processing. This is an update to our earlier PAW-27B-X3 release, with lower quality loss at the same file sizes. Two example scenes, generated in one shot from a text prompt (three.js/WebGL code, output by this model, rendered in a browser):

  • SambaLingo-Bulgarian-Base-i1-GGUF↗

    mradermacher

  • csm-1b↗

    unsloth

    **2025/03/13** - We are releasing the 1B CSM variant. Code is available on GitHub: SesameAILabs/csm. CSM (Conversational Speech Model) is a speech generation model from Sesame that generates RVQ audio codes from text and audio inputs. The model architecture employs a Llama backbone and a smaller audio decoder that produces Mimi audio codes. CSM sounds best when provided with context. You can prompt or provide context to the model using a `Segment` for each speaker utterance.

  • DiffuRefill-1B↗

    Asilarkness

    **Status: pretraining, about half way.** Step ~100k of 200k, ~46B effective training tokens, merge round 290. The weights here are a live pretraining checkpoint: fluent English, facts still unreliable, not instruction-tuned. Use `global_ema.pt`; it is the best checkpoint at every round. A 1.08B masked-diffusion language model decoded with **confidence-targeted re-infilling**: draft the whole sequence in a handful of parallel denoising passes, then spend a few more passes rewriting only the tokens the model is least sure about. An autoregressive model needs one pass per token; this one needs ~20 passes for a whole sequence, whatever its length. Tracked every round on fixed, deterministic batches, so the change between two rounds carries no sampling noise:

  • DeepSeek-R1-Distill-Llama-8B-heretic↗

    saidutta69

    A decensored variant of deepseek-ai/DeepSeek-R1-Distill-Llama-8B, produced with Heretic v1.4.0 (directional ablation / "abliteration"). Refusal behavior is suppressed via targeted weight edits to the attention output and MLP down-projections rather than fine-tuning, so the base model's knowledge and instruction-following are left largely intact. **Who this is for:** developers who want a capable 8B reasoning model distilled from DeepSeek-R1 onto Llama - strong reasoning that answers directly. Best run on an 8-12 GB GPU or via the Q4_K_M/Q5_K_M GGUF on consumer hardware. Not a capability upgrade over base DeepSeek-R1-Distill-Llama-8B - same model, refusal guardrails removed. Weights only, at this model's ~8.0B native size; add ~1 GB for context. OOM? Drop one quant level. Headroom to spare? Go one up.

  • wav2vec2-large-960h-lv60-self↗

    facebook

    The large model pretrained and fine-tuned on 960 hours of Libri-Light and Librispeech on 16kHz sampled speech audio. Model was trained with Self-Training objective. When using the model make sure that your speech input is also sampled at 16Khz. We show for the first time that learning powerful representations from speech audio alone followed by fine-tuning on transcribed speech can outperform the best semi-supervised methods while being conceptually simpler. wav2vec 2.0 masks the speech input in the latent space and solves a contrastive task defined over a quantization of the latent representations which are jointly learned. Experiments using all labeled data of Librispeech achieve 1.8/3.3 WER on the clean/other test sets. When lowering the amount of labeled data to one hour, wav2vec 2.0 outperforms the previous state of the art on the 100 hour subset while using 100 times less labeled data. Using just ten minutes of labeled data and pre-training on 53k hours of unlabeled data still achieves 4.8/8.2 WER. This demonstrates the feasibility of speech recognition with limited amounts of labeled data. The original model can be found under https://github.com/pytorch/fairseq/tree/master/examples/wav2vec#wav2vec-20.

  • gemma-4-E4B-it-qat-w4a16-ct↗

    Google

    Hugging Face | GitHub | Launch Blog | Documentation | Technical Report > [!Note] > This model card is for the new versions of the Gemma 4 family optimized with Quantization-Aware Training (QAT), which allows preserving similar quality to bfloat16 while dramatically reducing the memory requirements to load the model. > Four versions of the QAT checkpoints are available: > * **Unquantized QAT checkpoints** (Q4_0): Half-precision weights extracted from the QAT pipeline, ideal for custom downstream compilation and research. Available for Gemma 4 E2B, E4B, 12B, 26B A4B, and 31B, and their drafter models. > * **GGUF** (Q4_0): Ready-to-deploy formats for broad ecosystem compatibility. Available for Gemma 4 E2B, E4B, 12B, 26B A4B, and 31B. > * **Mobile-optimized** (wNa8o8): A custom schema engineered explicitly for mobile hardware efficiency. It features targeted 2-bit decoding layers, optimized KV caches, and static activations to maximize VRAM savings. Available for Gemma 4 E2B and E4B. > * **Compressed Tensors** (w4a16): QAT checkpoints serialized in the compressed-tensors format for native, optimized inference with vLLM. Available for Gemma 4 E2B, E4B, 12B, and 31B. > * **Assistant Compatibility**: When using multi-token prediction (speculative decoding) with an assistant model alongside a QAT target model, the assistant model must also be a QAT checkpoint with the same precision to ensure compatibility. Gemma is a family of open models built by Google DeepMind. Gemma 4 models are multimodal, handling text and image input (with audio supported on E2B, E4B, and 12B) and generating text output. This release includes open-weights models in both pre-trained and instruction-tuned variants. Gemma 4 features a context window of up to 256K tokens and maintains multilingual support in over 140 languages.

  • pubmedbert-base-embeddings↗

    NeuML

    This is a PubMedBERT-base model fined-tuned using sentence-transformers. It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search. The training dataset was generated using a random sample of PubMed title-abstract pairs along with similar title pairs. PubMedBERT Embeddings produces higher quality embeddings than generalized models for medical literature. Further fine-tuning for a medical subdomain will result in even better performance. This model can be used to build embeddings databases with txtai for semantic search and/or as a knowledge source for retrieval augmented generation (RAG).

  • PixArt-Sigma-XL-2-1024-MS↗

    PixArt-alpha

    PixArt-Σ consists of pure transformer blocks for latent diffusion: It can directly generate 1024px, 2K and 4K images from text prompts within a single sampling process. For research purposes, we recommend our `generative-models` Github repository (https://github.com/PixArt-alpha/PixArt-sigma), which is more suitable for both training and inference and for which most advanced diffusion sampler like SA-Solver will be added over time. Hugging Face provides free PixArt-Σ inference. - **Repository:** https://github.com/PixArt-alpha/PixArt-sigma - **Demo:** https://huggingface.co/spaces/PixArt-alpha/PixArt-Sigma > [!IMPORTANT] > Make sure to upgrade diffusers to >= 0.28.0: > > In addition make sure to install `transformers`, `safetensors`, `sentencepiece`, and `accelerate`: > > For `diffusers = 2.0`, you can improve the inference speed by 20-30% with torch.compile. Simple wrap the unet with torch compile before running the pipeline: