サイト内検索
AI モデル 450
- Huihui-Qwen3.8-27B-abliterated-GGUF↗
huihui-ai
This is an uncensored version of Qwen/Qwen3.8-27B created with abliteration (see remove-refusals-with-transformers to know more about it). This is a crude, proof-of-concept implementation to remove refusals from an LLM model without using TransformerLens. The newly added **Huihui-Qwen3.8-27B-abliterated-Underdog-Saluki** series come from ConwayResearch/Underdog-Saluki-27B-1.0 and ukisai/Swift-1.5-Qwen3.8-27B-GSQ-RCO-GGUF. Only layers **22 to 52 (0-based indexing)** have been ablated, while the other layers remain unablated. It may come with a small disclaimer warning. Due to ConwayResearch/Underdog-Saluki-27B-1.0 not providing an imatrix file, we will attempt to perform ablation by mixing the GGUF weights of Swift-1.5 and ConwayResearch/Underdog-Saluki-27B-1.0.
- potion-retrieval-32M↗
minishlab
This Model2Vec model is optmized for retrieval tasks. It is a finetune of potion-base-32M. It's finetuned using a modified version of the training approach described in this blogpost. It uses static embeddings, allowing text embeddings to be computed orders of magnitude faster on both GPU and CPU. It is designed for applications where computational resources are limited or where real-time performance is critical. Model2vec creates a small, static model that outperforms other static embedding models by a large margin on all tasks on MTEB. This model is pre-trained using Tokenlearn. It's created using the following steps: - Distillation: first, a model is distilled from a sentence transformer model using Model2Vec. - Training data creation: the sentence transformer model is used to create training data by creating mean output embeddings on a large corpus. - Training: the distilled model is trained on the training data using Tokenlearn. - Post-training re-regularization: after training, the model is re-regularized by weighting the tokens based on their frequency, applying PCA, and finally applying SIF weighting. The results for this model can be found on the Model2Vec results page.
- Qwen3.8-27B-Uncensored-Genesis-MTP-GGUF↗
LuffyTheFox
> ⚡ **Why Genesis project exists?** During training, **ALL** models don't just learn knowledge - they also accumulate random noise in their tensors. This noise builds up and creates something I call the **Noise Gate** - a fundamental barrier that stops LLM models from learning further and makes them unstable, verbose, and prone to hallucinations. My approach reduces this noise. It repairs the signal in tensors without touching the learned knowledge and gradient using Marchenko–Pastur distribution as a core criteria. The result is a model that consistent in performance, context clarity and following instructions, because it's no longer fighting its own internal chaos. > **What is Genesis?** Genesis is post training data regeneration and calibrarion algorythm for neural networks (LLM) in GGUF format that I made with AI help during almost half a year of development. It's optimized, architecture independent, works with any model in GGUF format and based on mathematical statistics. I don't train or finetune models, I repair **purity of signal** in them instead on Google Collab Free on Tesla T4 GPU via Python based on how models learns information. On first stage I scan ssm_conv1d tensors in model, they handle long context memory. I repair balance between heads in them. On second stage, I scan blocks in model via chunks via 3 parameters and pick best one that fits to weight distribution in tensor. Best picked chunk replaces zero chunks in broken tensor without touching learned structure in model. On third stage I scan model and detect noise in tensors via custom SVD. During scanning I exclude token_embd.weight, output.weight, 1D tensors, bias and norms. Then I reduce training noise in tensors via custom SVD based on Marchenko–Pastur law with preserved training data, 99% of siginal and learned gradient. My approach fixes all of that without retraining - pure numerical surgery on the raw bytes of the file.
- Swift-1.5-Qwen3.8-Flash-Next-GGUF↗
ukisai
Website • Learn more • GGUF • GSQ-RCO GGUF • Evaluation • Enterprise licensing **GGUF quantizations.** Derived directly from Swift 1.5 Qwen3.8-Flash-Next with llama.cpp. Run a chosen quantization tier with a current llama.cpp-compatible runtime such as `llama-server`. Swift 1.5 Qwen3.8-Flash-Next is UkisAI's reasoning-efficient derivative of Qwen3.8-Flash-Next. It uses **63.4% fewer thinking tokens**, with a **1.8x speed up** while keeping the **accuracy loss Create a 3D endless runner that has the fast, playful feel of Subway Surfers, but make the world and characters your own. I want to run through a lively place, dodge things, collect rewards, and feel the pace build the longer I survive. Make it fun to control and visually memorable. Use your judgment for the setting, mechanics, and little details that make it feel like a real game. Build it so I can launch and play it locally, then tell me how to run it.
- Smaug-72B-v0.1↗
abacusai
We recently released Smaug-72B-v0.1 which has taken first place on the Open LLM Leaderboard by HuggingFace. It is the first open-source model to surpass an average score of 80%. Smaug-72B is finetuned directly from moreh/MoMo-72B-lora-1.8.7-DPO and is ultimately based on Qwen-72B. We created Smaug-72B-v0.1 using a new fine-tuning technique, DPO-Positive (DPOP), and new pairwise preference versions of ARC, HellaSwag, and MetaMath (as well as other existing datasets). We introduce the technique and the full training details in our new paper: https://arxiv.org/abs/2402.13228.
- Rhea-72b-v0.5↗
davidkim205
The Rhea project is a project that conducts research on various learning methods to improve llm model performance. We fine-tuned the existing model using the nox framework. We built a dataset for SFT learning based on the currently open dataset, and created a dataset using SGD (Self-Generated Dataset Creation Method for DPO Learning) for DPO learning. This method proposes a novel method for generating datasets for DPO (Self-supervised Learning) models. We suggest a technique where sentences generated by the model are compared with the actual correct answers from an existing dataset, and sentences where the model's generated results do not match the correct answers are added. This enables the model to autonomously create training data, thereby enhancing the performance of DPO models. Randomly selecting data from each category within the training dataset, we constructed a DPO (Direct Preference Optimization) dataset using sentences with logits lower than the mean within the model-generated sentences. * I'm sorry I can't reveal it.
- nb-wav2vec2-1b-nynorsk↗
NbAiLab
This model is finetuned on top of feature extractor XLS-R from Facebook/Meta. The finetuned model achieves the following results on the test set with a 5-gram KenLM. The numbers in parentheses are the results without the language model: - **WER: 0.1132** (0.1364) - **CER: 0.0402** (---) This is one of several Wav2Vec-models our team created during the 🤗 hosted Robust Speech Event. This is the complete list of our models and their final scores: In parallel with the event, the team also converted the Norwegian Parliamentary Speech Corpus (NPSC) to the NbAiLab/NPSC in 🤗 Dataset format and used that as the main source for training.
- Linq-Embed-Mistral↗
Linq-AI-Research
Linq-Embed-Mistral has been developed by building upon the foundations of the E5-mistral-7b-instruct and Mistral-7B-v0.1 models. We focus on improving text retrieval using advanced data refinement methods, including sophisticated data crafting, data filtering, and negative mining guided by teacher models, which are highly tailored to each task, to improve the quality of the synthetic data generated by LLM. These methods are applied to both existing benchmark dataset and highly tailored synthetic dataset generated via LLMs. Our efforts primarily aim to create high-quality triplet datasets (query, positive example, negative example), significantly improving text retrieval performance. Linq-Embed-Mistral performs well in the MTEB benchmarks (as of May 29, 2024). The model excels in retrieval tasks, ranking **`1st`** among all models listed on the MTEB leaderboard with a performance score of **`60.2`** . This outstanding performance underscores its superior capability in enhancing search precision and reliability. The model achieves an average score of **`68.2`** across 56 datasets in the MTEB benchmarks, making it the highest-ranking publicly accessible model and third overall. (Please note that NV-Emb-v1 and voyage-large-2-instruct, ranked 1st and 2nd on the leaderboard as of May 29, reported their performance without releasing their models.) This project is for research purposes only. Third-party datasets may be subject to additional terms and conditions under their associated licenses. Please refer to specific papers for more details:
- Huihui-Qwen3.6-27B-abliterated-MTP-GGUF↗
huihui-ai
This is an uncensored version of Qwen/Qwen3.6-27B created with abliteration (see remove-refusals-with-transformers to know more about it). This is a crude, proof-of-concept implementation to remove refusals from an LLM model without using TransformerLens. Please use the latest version of ggml-org/llama.cpp - **Risk of Sensitive or Controversial Outputs**: This model’s safety filtering has been significantly reduced, potentially generating sensitive, controversial, or inappropriate content. Users should exercise caution and rigorously review generated outputs.
- sec-bert-base↗
nlpaueb
SEC-BERT is a family of BERT models for the financial domain, intended to assist financial NLP research and FinTech applications. SEC-BERT consists of the following models: * **SEC-BERT-BASE** (this model): Same architecture as BERT-BASE trained on financial documents. * **SEC-BERT-NUM**: Same as SEC-BERT-BASE but we replace every number token with a [NUM] pseudo-token handling all numeric expressions in a uniform manner, disallowing their fragmentation * **SEC-BERT-SHAPE**: Same as SEC-BERT-BASE but we replace numbers with pseudo-tokens that represent the number’s shape, so numeric expressions (of known shapes) are no longer fragmented, e.g., '53.2' becomes '[XX.X]' and '40,200.5' becomes '[XX,XXX.X]'. The model was pre-trained on 260,773 10-K filings from 1993-2019, publicly available at U.S. Securities and Exchange Commission (SEC) * We created a new vocabulary of 30k subwords by training a BertWordPieceTokenizer from scratch on the pre-training corpus. * We trained BERT using the official code provided in Google BERT's GitHub repository . * We then used Hugging Face's Transformers conversion script to convert the TF checkpoint in the desired format in order to be able to load the model in two lines of code for both PyTorch and TF2 users. * We release a model similar to the English BERT-BASE model (12-layer, 768-hidden, 12-heads, 110M parameters). * We chose to follow the same training set-up: 1 million training steps with batches of 256 sequences of length 512 with an initial learning rate 1e-4. * We were able to use a single Google Cloud TPU v3-8 provided for free from TensorFlow Research Cloud (TRC), while also utilizing GCP research credits. Huge thanks to both Google programs for supporting us!