サイト内検索

AI モデル 2119

• dolphin-2.6-mixtral-8x7b↗

  dphn

  This Dolphin is *really good* at coding, I trained with a lot of coding data. It is *very* obedient but it is not DPO tuned - so you still might need to encourage it in the system prompt as I show in the below examples. New in 2.6 - Fixed a training configuration issue that improved the quality a lot - Due to popular demand, added back samantha-based empathy data - Replaced synthia and pure-dove with Capybara This model is uncensored. I have filtered the dataset to remove alignment and bias. This makes the model more compliant. You are advised to implement your own alignment layer before exposing the model as a service. It will be highly compliant to any requests, even unethical ones. Please read my blog post about uncensored models. https://erichartford.com/uncensored-models You are responsible for any content you create using this model. Enjoy responsibly.

• SAM-GGUF↗

  mradermacher

• GLM-5.3-BF16↗

  zai-org

  GLM-5.3 uses the same base model as GLM-5.2 — every gain comes from post-training. Compared with GLM-5.2, it is much better at complex coding and long-horizon tasks: + Stronger Coding: GLM-5.3 is the most capable open-weights model for coding, with a 50% improvement over GLM-5.2 on our in-house Z.ai Code Bench. It also achieve open-source SOTA on public benchmarks including Terminal Bench 3.0 and Agents' Last Exam. + Emergent Cyber Capability: As we scaled post-training, cyber capability developed faster than we expected. GLM-5.3 is state of the art on CyberGym for vulnerability discovery, and its gains are largest further up the exploitation chain, where it more than doubles GLM-5.2 on exploitation benchmarks. GLM-5.3 supports deployment with the following frameworks. Feel free to try them out:

• punct_cap_seg_47_language↗

  1-800-BAD-CODE

  This model accepts as input lower-cased, unpunctuated, unsegmented text in 47 languages and performs punctuation restoration, true-casing (capitalization), and sentence boundary detection (segmentation). All languages are processed with the same algorithm with no need for language tags or language-specific branches in the graph. This includes continuous-script and non-continuous script languages, predicting language-specific punctuation, etc. This model is fun to play with, but the results could be better. I would recommend these newer, better models: * Better English model * Better Romance languages model * Better 47-language

• samantha-1.1-westlake-7b-laser-GGUF↗

  dagbs

• gemma-4-12B-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.

• Kataguru-Sceptic-35B-A3B-v2.6-GGUF↗

  kataguru

  **Kataguru-Sceptic-35B-A3B-v2.6-GGUF** is the `llama.cpp` / LM Studio / Ollama GGUF release of **Kataguru-Sceptic-35B-A3B-v2.6**, a bilingual (English & Finnish) 35-billion parameter (3B active parameters per token, 254 routed experts per layer) multimodal Mixture-of-Experts (MoE) model. Unlike the 25.44 GB `NVFP4` and 27.85 GB `AWQ` server packages, these imatrix-calibrated 3-bit GGUF quantizations (`12.0 GiB` to `15.3 GiB`) are specifically engineered to fit **wholly inside the VRAM of a single 16 GB or 24 GB GPU**. 1. **Dual-Stage 2D Zero-Swap Epistemic Triage (System 1 Reflex)**: - Evaluates candidate training samples in ** 83.46 % | 81.72 % | **+1.74 pp** | 80.10 % | **+3.36 pp** | | 2 | **WinoGrande** | Contextual Reasoning (`acc`) | 75.45 % | 71.82 % | **+3.63 pp** | 71.10 % | **+4.35 pp** | | 3 | **MedQA (USMLE)** | Clinical Medicine 4-opts (`acc`) | 85.31 % | 84.10 % | **+1.21 pp** | 78.40 % | **+6.91 pp** | | 4 | **TruthfulQA MC2** | Epistemic Truthfulness (`acc`) | 52.47 % | 52.89 % | -0.42 pp | 49.80 % | **+2.67 pp** | | 5 | **TruthfulQA MC1** | Single-True Factuality (`acc`) | 36.23 % | 34.39 % | **+1.84 pp** | 31.40 % | **+4.83 pp** | | 6 | **ARC-Easy** | Standard STEM (`acc_norm`) | 82.95 % | 74.83 % | **+8.12 pp** | 72.98 % | **+9.97 pp** | | 7 | **HellaSwag** | Linguistic Coherence (`acc_norm`) | 82.42 % | 83.30 % | -0.88 pp | 74.60 % | **+7.82 pp** | | 8 | **OpenBookQA** | Scientific Application (`acc_norm`) | 45.00 % | 46.00 % | -1.00 pp | 44.80 % | **+0.20 pp** | | 9 | **ARC-Challenge** | Advanced STEM (`acc_norm`) | 62.54 % | 57.94 % | **+4.60 pp** | 58.62 % | **+3.92 pp** | | 10 | **BoolQ** | Natural Language Logic (`acc`) | 90.37 % | 85.78 % | **+4.59 pp** | 89.60 % | **+0.77 pp** | | 11 | **GSM8K Math** (CoT) | Exact Match (`strict` / `flex`) | 89.39 % / 90.07 % | 1.06 % / 12.36 %\* | **+88.33 pp** | 76.50 % | **+12.89 pp** | | **$\Sigma_{10}$** | **10-Task Mean (1–10)** | **Mean Excluding GSM8K Format Gap** | 69.62 % | **67.28 %** | **+2.34 pp** | **65.14 %** | **+4.48 pp** | | **$\Sigma_{11}$** | **11-Task Mean (1–11)** | **Official Overall Cognitive Mean** | 71.42 % | **61.26 % (62.28 % flex)** | **+10.16 pp** | **66.17 %** | **+5.25 p

• alephbert-base↗

  onlplab

  State-of-the-art language model for Hebrew. Based on Google's BERT architecture (Devlin et al. 2018). 1. OSCAR (Ortiz, 2019) Hebrew section (10 GB text, 20 million sentences). 2. Hebrew dump of Wikipedia (650 MB text, 3 million sentences). 3. Hebrew Tweets collected from the Twitter sample stream (7 GB text, 70 million sentences). Trained on a DGX machine (8 V100 GPUs) using the standard huggingface training procedure.

• mask2former-swin-tiny-cityscapes-semantic↗

  facebook

  Mask2Former model trained on Cityscapes semantic segmentation (tiny-sized version, Swin backbone). It was introduced in the paper Masked-attention Mask Transformer for Universal Image Segmentation and first released in this repository. Disclaimer: The team releasing Mask2Former did not write a model card for this model so this model card has been written by the Hugging Face team. Mask2Former addresses instance, semantic and panoptic segmentation with the same paradigm: by predicting a set of masks and corresponding labels. Hence, all 3 tasks are treated as if they were instance segmentation. Mask2Former outperforms the previous SOTA, MaskFormer both in terms of performance an efficiency by (i) replacing the pixel decoder with a more advanced multi-scale deformable attention Transformer, (ii) adopting a Transformer decoder with masked attention to boost performance without without introducing additional computation and (iii) improving training efficiency by calculating the loss on subsampled points instead of whole masks.

• Qwen3.8-27B-GPTQ-Int4-sym-G128-MTP-BF16↗

  SergiioB

  Self-quantized on the target GPU (gptqmodel 7.3.2) for **vLLM XPU serving on Intel Arc (Xe2)**. The single MTP draft layer is deliberately **excluded from quantization and kept in BF16**, so native speculative decoding (MTP) works out of the box — and an optional **runtime INT4 draft overlay** (below) takes single-stream decode from **83.7 → 112.7 tok/s** on the same checkpoint. > All numbers are **real measurements** taken on a single Intel Arc Pro B70 > 32 GB — client-side timing, n=5 medians, 230 W cap, context 131072, fp8 KV, > served at the Qwen3.8-27B model card's recommended sampling — > **non-thinking: temperature 0.7, top_p 0.80, top_k 20, presence_penalty 1.5** > (thinking: 1.0 / 0.95 / 20). Greedy rows are marked greedy. > Commands, methodology and raw logs are public: 📖 > **Intel Arc Pro B70 Inference Cookbook** (see the link section below). - **Repo:** intel-arc-pro-b70-inference-cookbook - **This model's recipe:** QWEN38-VLLM-XPU.md - **INT4 draft overlay:** DRAFT-INT4-S-M1.md - **Copy-paste launch lines:** FULL-SETUP-COMMANDS.md - **Image + patch matrix:** IMAGE-AND-PATCH-MATRIX.md