Hugging Face's logo

Collections

Discover the best community collections!

Collections trending this week
DeepSeek-V4-Flash · MLX
304B MoE on Apple Silicon. deepseek_v4 is in no released runtime — ported from scratch. Take mixed-4_8bit. github.com/PipeNetwork/deepseek-v4-mlx
EffiR
Resources for paper “Making Large Language Models Efficient Dense Retrievers” (ACL 2026), including the paper and efficient Mistral-based dense retrie
OpusGLM SFT
Collection of Qwen3.5 Multimodal Models Fine-Tuned with OpusGLM Traces
Audio Models Quantized
INT8, FP8 and INT4 builds of the Aniemore speech-emotion models. Load one with from_pretrained(repo, subfolder="int4").
ReMind — Teaching Video Generators to Remember
Official ReMind release: paper, ReMind 5B checkpoints, and ReMind1M dataset for dynamic memory in causal video generators.
Audio Models Quantized
INT8, FP8 and INT4 builds of the Aniemore speech-emotion models. Load one with from_pretrained(repo, subfolder="int4").
DeepSeek-V4-Flash · MLX
304B MoE on Apple Silicon. deepseek_v4 is in no released runtime — ported from scratch. Take mixed-4_8bit. github.com/PipeNetwork/deepseek-v4-mlx
EffiR
Resources for paper “Making Large Language Models Efficient Dense Retrievers” (ACL 2026), including the paper and efficient Mistral-based dense retrie
ReMind — Teaching Video Generators to Remember
Official ReMind release: paper, ReMind 5B checkpoints, and ReMind1M dataset for dynamic memory in causal video generators.
OpusGLM SFT
Collection of Qwen3.5 Multimodal Models Fine-Tuned with OpusGLM Traces