전체 검색

AI 모델 2119

• GLM-5.3-Flash-UNCENSORED-NVFP4↗

  dealignai

  > [!IMPORTANT] > **Serving note — read before your first request (vLLM / SGLang with a reasoning parser).** > > - **`reasoning_effort` only accepts `"low"` and `"high"`.** Anything else — `medium`, `xhigh`, > `off`, or omitting it — silently resolves to **`max`**, the deepest mode. Template line: > `reasoning_effort ... in ['low','high'] else 'max'`. > - **At `max`, a small `max_tokens` returns an EMPTY reply.** The model spends the whole budget > inside ` ` and you get `finish_reason="length"` with `content=""`. In multi-turn the empty > turn poisons the history and the conversation does not recover. Measured: `max` + `max_tokens > 2000` dies from turn ~4; `max` + `6000` is clean; `low` and `high` are clean at 2000. > **It is budget exhaustion, not a loop** — sampling changes do not rescue it. > - **Do NOT pass `enable_thinking`.** This template has no such variable (only `clear_thinking` and > `reasoning_effort`). Passing it — or a top-level `reasoning_effort: "none"` — turns the parser off > while the model still thinks, dumping raw reasoning into `content`. > - **Reasoning is returned in `message.reasoning`**, not `message.reasoning_content` > (vLLM renamed the output field; the input side still accepts both). > - `clear_thinking` must be nested inside `chat_template_kwargs` — a top-level key is ignored. > > > Use `"high"` for hard tasks; if you want `max`, give it `max_tokens >= 6000`. > > > **Video and image parameters — measured, because several are accepted then silently ignored.** > > - 🔴 **`media_io_kwargs.video.fps` must stay BELOW the clip's own frame rate.** Requesting a value > at or above it makes the placeholder builder count 3x the real tokens and **kills the engine**: > `ValueError: Attempted to assign N = N multimodal tokens to 3N placeholders` -> `EngineDeadError`, > server down until restarted. Upstream: vLLM #55644 / #55647. `fps: 2` is the safe, accurate choice. > - **`max_frames` and `num_frames` are not interchangeable across builds.** On vLLM nightly > `max_frames` is honoured and `num_frames` ignored; on the older `0.1.dev*` line it is the exact > reverse. A client that sets only one silently gets full-rate sampling on the other build

• Depth-Anything-V2-Metric-Indoor-Large-hf↗

  depth-anything

  This model represents a fine-tuned version of Depth Anything V2 for indoor metric depth estimation using the synthetic Hypersim datasets. Depth Anything V2 was introduced in the paper of the same name by Lihe Yang et al. It uses the same architecture as the original Depth Anything release but employs synthetic data and a larger capacity teacher model to achieve much finer and robust depth predictions. This fine-tuned version for metric depth estimation was first released in this repository. **Six metric depth models** of three scales for indoor and outdoor scenes, respectively, were released and are available:

• flux-3-image-klein-prompt-upsampler-GGUF↗

  prithivMLmods

  > **FLUX 3 Image Klein Prompt Upsampler** is Black Forest Labs' 9B vision-language model, a full fine-tune of Qwen3.5-9B with the vision tower frozen, that expands a short image request into the detailed prompt FLUX 3 Image Klein works best with. The card says Klein is not meant to run without an upsampler in front of it, because short prompts sent as typed give generic output. One model covers three modes, selected by the system prompt: text-to-image, editing with up to 10 reference images, and layout with optional bounding boxes. Output prompts spell out medium and style, scene, lighting and camera, and each subject's colors, materials and position, with any text to render kept verbatim in quotes. For edits it looks at the references and writes the instruction around what is in them, covering what changes and what stays. Bounding boxes are kept exactly, in a box table after the prompt, and the prompt cites each box by id. Training had two stages: supervised training on pairs of short requests and expanded prompts, then preference tuning on pairs of the model's own prompts, rendered with FLUX 3 Image Klein at the same seed and ranked on the resulting image. The card gives no benchmark numbers. Its one example turns "A man walking with his dog, afternoon sun" into a 220-word prompt. It is loaded by default in the official inference code and has an `enable_prompt_upsampler` switch in ComfyUI. With Diffusers, you run the Transformers block yourself and pass the caption as `prompt`. The limitations section says output is English only, though the request can be in any language, the prompts are tuned only for FLUX 3 Image Klein, and references are downscaled (at most 1 MP for one), so small details can be described wrongly. The model does not refuse requests, and the inference code offers optional prompt and image safety checks (`--safety`). The weights, a 18.8 GB bfloat16 file, are released under Apache 2.0.

• Juggernaut-X-v10↗

  RunDiffusion

  The ground-up retrain — GPT-4V captions, sharper prompt adherence, native text rendering. > Juggernaut X (v10) is a **ground-up retrain** of the Juggernaut SDXL line. Not a fine-tune of v9 — the entire dataset was re-captioned with **GPT-4 Vision**, image classifications were rebuilt from scratch, and the model was trained fresh against an expanded, higher-quality image set. The result: noticeably better prompt adherence, cleaner shot-type control, and native text-rendering capability. - 🧠 **Retrained from the ground up** — not fine-tuned on top of a previous Juggernaut. - 👁️ **GPT-4 Vision captioning** — dataset re-captioned with detailed, structured language descriptions. - 🎯 **Stronger prompt adherence** — does what you ask more often, with less wrestling. - 📸 **Cleaner shot-type classification** — Full Body, Mid Shot, Portrait, etc., now distinct in the model's understanding. - 🔤 **Native text rendering** — handles legible signage, labels, and short phrases directly. - 🖼️ **RunDiffusion Photo** refinement — same photographic backbone that made v9 popular.

• tmax-4b-gguf↗

  samuelchristlie

• sentence-t5-large↗

  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-large-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-large model. The weights are stored in FP16.

• vit-small-patch16-224↗

  WinKawaks

  Google didn't publish vit-tiny and vit-small model checkpoints in Hugging Face. I converted the weights from the timm repository. This model is used in the same way as ViT-base.

• JEV-35B-NVFP4↗

  autotrust

  > [!IMPORTANT] > **Try AutoTrust/GuruSearch live (new, 11 October 2026).** A recommendation and search demo in which every ranking is a > calibrated System 1 decision, made in about half a second: > * **Recommendation:** the latest headlines from 6 news feeds, ranked by importance. > * **Search:** results from Google News, Bing News and Yahoo News re-ranked by relevance, side by side with the > search engines' own order, plus a short answer with citations. This repository is **autotrust/JEV-35B with its 10,240 routed expert MLPs (40 layers × 256 experts) quantized to NVFP4**. Everything else is the bf16 model unchanged: attention, linear attention, the shared expert, the routers, the vision tower, the MTP layer, the lm_head, the System 1 adapter, the decision head and the temperatures. Below the NVFP4 comparison, the rest of this card is the JEV-35B card; its tables are the bf16 results unless marked otherwise. * **Text: −0.57 on the Decision Index.** All five areas within 1.2 skill points of bf16 (Knowledge 0.422, Language 0.628, Retrieval 0.706, Tools 0.753, Arts 0.413); the largest per-benchmark changes are Home appliance simulator −5.7, CRUXEval −4.7 and GPQA +5.4. * **Images: −0.85 on the vision rebuild**, a small but real loss (paired bootstrap 95 % interval −1.5 to −0.2), mostly on CharXiv charts (−5.3). * **Robot arm: 13 of 20 scenes against 15 of 20.** Four scenes changed outcome (3 lost, 1 gained), within noise (sign test p = 0.63); every grasped cube still reached the tray (13/13). * **Speed:** the same latency as bf16 on one B200 for single requests; the gain is memory (one 32–48 GB GPU is enough). * **Games** (seed 0, one run each, noisy): 2048 largest tile 64 (bf16 32), Snake 5 food (bf16 11), Quick, Draw! 85.9 % on finished sketches (bf16 86.3 %), chess mate-in-one 45 % (bf16 47 %), Connect Four 1 win of 6 (bf16 0).

• rubert-base-cased-sentence↗

  DeepPavlov

  Sentence RuBERT \(Russian, cased, 12-layer, 768-hidden, 12-heads, 180M parameters\) is a representation‑based sentence encoder for Russian. It is initialized with RuBERT and fine‑tuned on SNLI\[1\] google-translated to russian and on russian part of XNLI dev set\[2\]. Sentence representations are mean pooled token embeddings in the same manner as in Sentence‑BERT\[3\]. \[1\]: S. R. Bowman, G. Angeli, C. Potts, and C. D. Manning. \(2015\) A large annotated corpus for learning natural language inference. arXiv preprint arXiv:1508.05326 \[2\]: Williams A., Bowman S. \(2018\) XNLI: Evaluating Cross-lingual Sentence Representations. arXiv preprint arXiv:1809.05053

• ModernBERT-large-zeroshot-v2.0↗

  MoritzLaurer

  This model is answerdotai/ModernBERT-large fine-tuned on the same dataset mix as the `zeroshot-v2.0` models in the Zeroshot Classifiers Collection. The following hyperparameters were used during training: - learning_rate: 9e-06 - train_batch_size: 16 - eval_batch_size: 32 - seed: 42 - gradient_accumulation_steps: 2 - total_train_batch_size: 32 - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments - lr_scheduler_type: linear - lr_scheduler_warmup_ratio: 0.06 - num_epochs: 2