全站搜索

AI 模型 84757

• tiny-random-whisper↗

  optimum-intel-internal-testing

• vit-with-hidden_states↗

  optimum-intel-internal-testing

• tiny_random_bert_neuron↗

  optimum

• PP-OCRv4_server_rec↗

  PaddlePaddle

  PP-OCRv4_server_rec is a text line recognition model within the PP-OCRv4_rec series, developed by the PaddleOCR team. PP-OCRv4 is an upgrade over PP-OCRv3. The overall framework retains the same pipeline as PP-OCRv3, with optimizations made to several modules such as data, network structure, and training strategy for both detection and recognition models. It supports text line recognition in general Chinese and English scenarios, but mainly focuses on Chinese. The key accuracy metrics are as follow: 80.61 71.2 M The server-side model of PP-OCRv4, offering high inference accuracy and deployable on various servers. **Note**: If any character (including punctuation) in a line was incorrect, the entire line was marked as wrong. This ensures higher accuracy in practical applications.

• GLM-5.3-Flash-MLX-mixed-4_8bit↗

  pipenetwork

  MLX (Apple Silicon) build of **GLM-5.3-Flash** — 320B-A18B hybrid of 34 Kimi-Delta linear-attention layers and 11 DeepSeek-sparse-attention (NoPE MLA + lightning indexer) layers with manifold-constrained hyper-connections — quantized to **4-bit experts / 8-bit everything else**. **These files are modified**: converted from the upstream bfloat16 release (GLM-5.3-Flash-BF16) to MLX and quantized; the architecture is unchanged. The multi-token-prediction layer (layer 45) is not included. The vision tower is carried in bfloat16. `glm5_next` landed in mlx-vlm `main` on 2026-08-26 (no release carries it yet). Validating that port against `transformers` 5.16 at tiny scale found two numerical bugs and two epsilon mismatches, which the runtime in https://github.com/PipeNetwork/glm53-flash-mlx fixes; parity is **1e-6** end to end, exact on cached decode.

• F0BFJZHiZgOCUXPC↗

  PS4Research

• DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored-GGUF↗

  QuantFactory

  language: - en - de - fr - it - pt - hi - es - th - zh - ko - ja license: llama3.1 pipeline_tag: text-generation tags: - roleplay - llama3 - sillytavern - idol - facebook - meta - pytorch - llama - llama-3 extra_gated_fields: First Name: text Last Name: text Date of birth: date_picker Country: country Affiliation: text Job title: type: select options: - Student - Research Graduate - AI researcher - AI developer/engineer - Reporter - Other This is quantized version of aifeifei798/DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored created using llama.cpp - pip install datasets openai - start you openai Server,change Uncensored_Test/harmful_behaviors.py client to you Openai Server address and api_key

• Qwen2-1.5B-Instruct-GGUF↗

  QuantFactory

• gemma-4-E2B-it-dspark-GGUF↗

  rasyosef

• Qwen2-Wukong-5B-Instruct-Sliced↗

  RESMPDEV