전체 검색

AI 모델 84759

• ThinkPRM-1.5B↗

  launch

  ThinkPRM-1.5B is a generative Process Reward Model (PRM) based on the R1-Distill-Qwen-1.5B architecture. It is fine-tuned to perform step-by-step verification of reasoning processes (like mathematical solutions) by generating an explicit verification chain-of-thought (CoT) that involves labeling every step. It is designed to be highly data-efficient, requiring significantly less supervision data than traditional discriminative PRMs while achieving strong performance. ThinkPRM-1.5B provides step-level verification scores by generating natural language critiques and correctness judgments for each step in a given solution prefix. It leverages the underlying reasoning capabilities of the base Large Reasoning Model (LRM) and enhances them through fine-tuning on a small (1K examples) dataset of synthetically generated verification CoTs. These synthetic CoTs were produced by prompting QwQ-32B-Preview and filtered against ground-truth step labels from the PRM800K dataset to ensure quality. The model uses a standard language modeling objective, making it interpretable and allowing it to scale process verification compute by generating longer or multiple verification CoTs. It demonstrated superior performance compared to LLM-as-a-judge and discriminative PRM baselines (based on the same R1-Distill-Qwen-1.5B model but trained on ~100x more labels) on benchmarks including ProcessBench, MATH-500, AIME '24, GPQA-Diamond, and LiveCodeBench.

• anime-whisper↗

  litagin

  **Anime Whisper** は、特に日本語のアニメ調演技セリフのドメインに特化した日本語音声認識モデルです。 このモデルは kotoba-whisper-v2.0 をベースモデルとして、約5,300時間373万ファイルのアニメ調の音声・台本データセット Galgame_Speech_ASR_16kHz でファインチューニングしたものです。 特にアニメ演技音声ドメインに特化していますが、それ以外の音声でも、他のモデルにはない特徴や高い性能を持っています。 **このモデルは初期プロンプト(initial prompt) との相性が悪いようで、設定をするとハルシネーションが起きて質が極めて劣化します。初期プロンプトを設定せずにご使用ください。** **Using an initial prompt causes a decline in quality, with the model exhibiting hallucinations and significantly degraded performance. Please avoid using an initial prompt.**

• Chroma1-Flash↗

  lodestones

• chrono-2012↗

  maginion

• hindi-bert↗

  monsoon-nlp

• Mistral-7B-Instruct-v0.3-llamafile↗

  mozilla-ai

  This repository contains executable weights (which we call llamafiles) that run on Linux, MacOS, Windows, FreeBSD, OpenBSD, and NetBSD for AMD64 and ARM64. The third edition of Mistral 7B was released on May 22th, 2024. It increases the vocabulary size to 32768, supports the v3 tokenizer, and introduces support for function calling. Assuming your system has at least 16GB of RAM, you can try running the following command which download, concatenate, and execute the model.

• Aether-Qwen2-0.5B-SFT-v0.0.2-GGUF↗

  mradermacher

• Ahma-SlimInstruct-V1-7B-i1-GGUF↗

  mradermacher

• Aurora-Code-1-GGUF↗

  mradermacher

• BrainMed-8B-GGUF↗

  mradermacher