
#finetune · page 6
1747 posts


ClosureRAG: Cross-encoders for evidence retrieval by regulations
ClosureRAG is a set of fine-tuned checkpoints based on Qwen3-Reranker-0.6B, designed for retrieval-augmented generation tasks where answering a question requires gathering an entire set of interrelated regulations or documents (known as proof closure).


SpeechLLM ASR: English speech recognition powered by Villanova-2B
This is a multimodal speech language model (SpeechLLM) for automatic English speech recognition, built on the SLAM-LLM framework. The architecture combines a frozen FAMA encoder, a linear projector, and the Villanova-2B model with LoRA (a lightweight adapter for the base model).

OpenToolSearch Reranker: A compact reranker for selecting AI agent tools
This model from AI3 Inc. helps AI agents efficiently handle massive libraries of functions and tools (such as function declarations or MCP tools) without overloading their system prompts.



Velandris Qwen3.8-27B Honesty
R-Build v4.2 — a hybrid model with enhanced honesty


Grace-G1-350M-Instruct: A compact bilingual LLM with a hybrid architecture
Grace-G1-350M-Instruct is an instruction-tuned version of a 377M parameter model by BranchingNLP, built for conversations, small talk, and simple tasks in English and Italian.

SIMB: A Cross-Modal Speech and Vision AI Model
Developed by the KU-AGI team, the SIMB model combines the visual expertise of Janus-Pro-7B with a speech expert based on Qwen2.5-3B. It handles cross-modal synthesis tasks including speech-to-image generation, image-to-speech conversion, and spoken visual question answering (spoken VQA).


GoodJob: a BERT-based job post classifier
The GoodJob model (110M parameters, built on bert-base-uncased) is designed to analyze posts from Twitter/X or LinkedIn. It features two classification heads: the first determines the post type (ranging from specialized AI/ML job listings to non-work posts), and the second evaluates author…

MedCoast PRM: Medical reasoning evaluation model
Built on answerdotai/ModernBERT-base, this model evaluates intermediate reasoning chains in medical question-answering (medical QA). The checkpoints are designed exclusively for inference and evaluate pairwise reasoning quality. Input is limited to 2048 tokens.


LangGap InternW0-Delta with LDS: Policy for Robotics Tasks Based on InternRobotics
This model is a trained robotics policy checkpoint created using the Linear Decodability Supervision method at step 1469. It was trained on all available localization scenes and is designed to work with the native InternW0-Delta LIBERO runtime.


BunGPT-DeepEdu-Decision-4B-Open
A model for fast product decisions without text generation


DA-Flow: Degradation-aware optical flow model
DA-Flow provides pretrained weights for optical flow estimation using image restoration diffusion features. Based on stabilityai/stable-diffusion-3.5-medium, the model integrates a DiT4SR transformer and a dedicated network structure for flow processing.
NeyroLearn
@neyrolearn
New models from Hugging Face every morning: video, images, LoRAs and LLMs with examples and links.
- Posts
- 1747
- Tags
- 59
Trending
Most liked on Hugging Face this week
- 1Add Micro Details
Images · 8.4K
18+ - 2MiniMax-H3
Video · 7.2K

- 3Flat Color - Style
Images · 6.2K

- 4Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NEO-CODER-MAX-MTP-GGUF
Computer vision · 3.5K

- 580s Fantasy Movie
Images · 3.1K
18+
Popular tags
- #finetune1747
- #LLM1342
- #models1293
- #LoRA1071
- #Qwen929
- #images585
- #txt2img482
- #robotics467
- #VLM347
- #audio270
- #NSFW207
- #Krea193
- #video183
- #MiniMax_H3168
- #ComfyUI157
- #Gemma139
- #turbo128
- #MOSS_Image123
- #ASR107
- #TTS99
























