전체 검색
AI 모델 84760
- Vela-1.0-Encoder-307M-Domain↗
vllm-sr
Vela Domain identifies the subject of a request across 14 domains to help select relevant models and tools. Macro F1 (×100) on the same development sets, compared with the original mmBERT32K Domain model. Higher is better. Short requests cover English, Chinese, Spanish, French, German and Japanese. Long-context evaluation uses 28 English/Chinese examples extended to each length. Both models process the complete input in FP32. These development sets informed Vela checkpoint selection; they are not an independent test set.
- Connect-C1-0.8B-v0.1-GGUF↗
WonseokJayJung
- Qwen3-14B-sk-GGUF↗
worstplayer
- paraphrase-MiniLM-L3-v2↗
Xenova
- qwen3-8b-general-grpo-16k↗
YangyiYY
- Qwen3.8-Flash-Next-tqLLM↗
YTan2000
- adakajuan↗
adakajuan
- Gemma-4-26B-A4B-it-Uncensored-NVFP4↗
AEON-7
Complete copy-paste recipe — pull the container, pull the model (fresh), pull the DFlash drafter (fresh), then serve with the vetted DGX Spark recipe (DFlash n=10, drafter `flash_attn`, body `triton_attn`). The recipe notes below cover tag-specific drafter backends and the production GPU-util / context-tier profile; see also Container Image Details. **Recipe notes — the drafter backend is tied to the image tag:** - **On `:latest` / `:2026-07-01-v0.24.0` (current; same behavior as the `:2026-06-18-v0.23.0-dflashfix` fix lineage):** the drafter **must** use `attention_backend: flash_attn` (enabled for multimodal Gemma targets by PR #41703's `use_mm_prefix=False`). `flex_attention` **crashes at the first request** on this image (non-contiguous KV view in the new KV-sharing path). `--enable-prefix-caching` is safe and recommended — soak-validated with DFlash (see the fixes section below). - **On the rollback tag `:2026-06-04-pr44389` (pre-fix):** the reverse — only `flex_attention` loads (`flash_attn` fails with `partial multimodal token full attention not supported`), the drafter silently runs without sliding-window support (~0% acceptance beyond 2k-token contexts), and `--enable-prefix-caching` triggers a slow acceptance collapse (see below). Not recommended. - Either way the body stays on `triton_attn` (Gemma's heterogeneous head dims), and do **not** set `--kv-cache-dtype fp8` — DFlash's non-causal drafter requires BF16 KV. `--reasoning-parser gemma4` cleanly splits `enable_thinking` output into `reasoning_content`. `num_speculative_tokens=10` is the value our production fleet runs; the drafter's trained block size is 16 and z-lab ships 15 — an n=10-vs-15 re-bench on the fixed drafter is pending (the earlier "10 beats 15" result was measured on the pre-fix drafter and shouldn't be treated as settled). The model's `config.json` already ships the vision ignore-list fix (`re:.*embed_vision.*`, `re:.*vision_tower.*`) so vLLM keeps the vision tower BF16. This default profile suits agentic gateways — one large full-context chat plus many short-lived subagents under the `--max-num-seqs 64` cap. For short-context throughput benchmarking, use `--max-model-len 32768 --max
- DTS6_model↗
Albadri
- Qwen-Image-2.1-GGUF↗
AlperKTS
Quantized GGUF weights of the state-of-the-art **Qwen-Image 2.1** diffusion model for **ComfyUI** using ComfyUI-GGUF. These models allow running Qwen-Image 2.1 on consumer GPUs with significantly reduced VRAM footprint while preserving maximum visual quality, text-rendering capabilities, and composition fidelity. 1. **Diffusion Model (GGUF):** - Download any of the `.gguf` files from this repo (e.g. `qwen_image_2.1_Q8_0.gguf`). - Place it in: `ComfyUI/models/diffusion_models/` (or `ComfyUI/models/unet/`)