全站搜索

AI 模型 84760

• vietnamese-correction↗

  bmd1905

• Boogu-Image-0.1-Edit↗

  Boogu

• reka-flash-3-GGUF↗

  brittlewis12

• byteff2↗

  字节跳动

• twitter-roberta-base-irony↗

  cardiffnlp

  This is a roBERTa-base model trained on ~58M tweets and finetuned for irony detection with the TweetEval benchmark. This model has integrated into the TweetNLP Python library.

• Z-Image-Lora↗

  CBLKG

  + Always use full LoRa name with "vrtlxxxx" trigger in prompt like "Alba Baptista (vrtlalbabaptista) in a swimming pool". "Woman" or "1girl" will NOT work due to my way i do captions. + When using a Lora with multiple triggers (vrtlxx,vrtlyy) do not use the real character name but only trigger or a combination of it. "vrtlMain" always combines all trigger-words. + Previews made with settings: ZI Turbo Q8 / Euler / beta / 9 steps / CFG1 / auraflow 6 + Prompt for Previews: First Last (vrtlLora), , beautifully done head, modern casual styled hair, wearing a top crop knotted beige unbuttoned shirt with green four leaf clover pattern that shows a deep and wide cleavage, a embroidered badge with the shape of a ladybug that absolutely must have the black letters "ZI" below on shirt right side, upper body portraiture, centered, frontal, eye contact, blank dark gray gradient background.

• gpt-oss-120b-Uncensored-GGUF↗

  ccharnkij

• minimax-h3-fused-turbo-int8-convrot↗

  cgc-0521

  One 21 GB ComfyUI diffusion-model file that does MiniMax-H3 text/image-to-video **and** reference-to-video in **4 steps**, with a distilled turbo and a motion-smoothing style LoRA already folded into the weights. `diffusion_models/minimax_h3_fused_refdelta_r1024_turbo8_mystic07_int8_convrot.safetensors` -> `ComfyUI/models/diffusion_models/` **Hardware.** The timings below are from a 96 GB card with everything resident. Smaller cards work too: ComfyUI's model management loads and offloads the transformer, text encoder and VAEs as they are needed, so the same graphs run, just slower, and the 21 GB file is the smallest footprint this recipe has. **AMD / ROCm:** the recipe was developed on an AMD box; use patientx's ComfyUI ROCm fork, , which also carries a ROCm build of the SLA attention node.

• FusOn-pLM↗

  ChatterjeeLab

• DeepSeek-R1-Distill-Qwen-7B↗

  DeepSeek

  We introduce our first-generation reasoning models, DeepSeek-R1-Zero and DeepSeek-R1. DeepSeek-R1-Zero, a model trained via large-scale reinforcement learning (RL) without supervised fine-tuning (SFT) as a preliminary step, demonstrated remarkable performance on reasoning. With RL, DeepSeek-R1-Zero naturally emerged with numerous powerful and interesting reasoning behaviors. However, DeepSeek-R1-Zero encounters challenges such as endless repetition, poor readability, and language mixing. To address these issues and further enhance reasoning performance, we introduce DeepSeek-R1, which incorporates cold-start data before RL. DeepSeek-R1 achieves performance comparable to OpenAI-o1 across math, code, and reasoning tasks. To support the research community, we have open-sourced DeepSeek-R1-Zero, DeepSeek-R1, and six dense models distilled from DeepSeek-R1 based on Llama and Qwen. DeepSeek-R1-Distill-Qwen-32B outperforms OpenAI-o1-mini across various benchmarks, achieving new state-of-the-art results for dense models. **NOTE: Before running DeepSeek-R1 series models locally, we kindly recommend reviewing the Usage Recommendation section.** - We directly apply reinforcement learning (RL) to the base model without relying on supervised fine-tuning (SFT) as a preliminary step. This approach allows the model to explore chain-of-thought (CoT) for solving complex problems, resulting in the development of DeepSeek-R1-Zero. DeepSeek-R1-Zero demonstrates capabilities such as self-verification, reflection, and generating long CoTs, marking a significant milestone for the research community. Notably, it is the first open research to validate that reasoning capabilities of LLMs can be incentivized purely through RL, without the need for SFT. This breakthrough paves the way for future advancements in this area.