サイト内検索

AI モデル 84759

• Bonsai-4B-mlx-1bit↗

  prism-ml

• granite-3.0-8b-instruct-GGUF↗

  QuantFactory

• Qwen2.5-Math-7B-PRM800K↗

  阿里巴巴 · Qwen

• Qwen3 4B (Non-reasoning)↗

  阿里巴巴 · Qwen

• Llama-3.1-8B-Instruct-NVFP4↗

  RedHatAI

  This model is a quantized version of Meta-Llama-3.1-8B-Instruct. It was evaluated on a several tasks to assess the its quality in comparison to the unquatized model. This model was obtained by quantizing the weights and activations of Meta-Llama-3.1-8B-Instruct to FP4 data type, ready for inference with vLLM>=0.9.1 This optimization reduces the number of bits per parameter from 16 to 4, reducing the disk size and GPU memory requirements by approximately 75%. Only the weights and activations of the linear operators within transformers blocks are quantized using LLM Compressor.

• Qwen3.8-27B-speculator.dspark↗

  RedHatAI

• Heejindo_-_rationale_model_e3_save5000_f2-gguf↗

  RichardErkhov

• ViraIntelligentDataMining_-_PersianLLaMA-13B-Instruct-gguf↗

  RichardErkhov

• ArmoRM-Llama3-8B-v0.1↗

  RLHFlow

  + **Blog**: https://rlhflow.github.io/posts/2024-05-29-multi-objective-reward-modeling/ + **Tech Report**: https://arxiv.org/abs/2406.12845 + **Model**: ArmoRM-Llama3-8B-v0.1 + Finetuned from model: FsfairX-LLaMA3-RM-v0.1 - **Code Repository:** https://github.com/RLHFlow/RLHF-Reward-Modeling/ + **Architecture** The second entry, "Arithmetic Control of LLMs for Diverse User Preferences: Directional Preference Alignment with Multi-Objective Rewards", is another recent work of ours that trained a multi-objective reward model and adopted it for LLM alignment, which motivated us to develop the current work.

• minimax_h3_ref2va_fp8_e4m3fn↗

  rzgar

  Quantized versions of the **MiniMax H3 Ref2VA** (reference-to-video-audio) diffusion model. Both keep the text-conditioning path (`token_refiner`, conditioning projections, audio heads) in full precision. _minimal 5 step (talking heads, less motions) | balanced 8-steps (shift 8) | Action-rich scenes above 12 (shift max 12)_