전체 검색

AI 모델 2119

• Flint-40B-A2.5B-abliterated-GGUF↗

  dima6312

  An abliterated (uncensored) Flint: RecursiveSI's Flint 40B-A2.5B with its refusal direction removed, for security research and coding work: exploit analysis, malware triage, detection engineering, CTFs and red-team tooling that the original model often declines. **Summary:** held-out MITRE ATT&CK refusals 15% → 0% (n=100, Q8_0). No significant drop on HumanEval+, MBPP+, GSM8K, MMLU-Pro, CyberMetric or WMDP-cyber (paired, same items). KL divergence from the original on harmless prompts: 0.0146. Builds: BF16, GGUF (Q8_0 to Q3_K_M), NVFP4 for NVIDIA Blackwell, MLX 4-bit for Apple silicon. **Not sure?** Take the GGUF `Q4_K_M` (24 GB). It runs in llama.cpp and in apps built on it, including LM Studio (its llama.cpp runtime 2.63.0 includes Flint). The MLX builds are for Mac users who already run mlx-lm.

• Qwen3.6-35B-A3B-Claude-4.6-Opus-Reasoning-Distilled-GGUF↗

  hesamation

  GGUF quantizations of `hesamation/Qwen3.6-35B-A3B-Claude-4.6-Opus-Reasoning-Distilled`, a reasoning SFT fine-tune of `Qwen/Qwen3.6-35B-A3B` on Claude Opus 4.6-style chain-of-thought distillation data. The source fine-tune is text-only. The Qwen3.6 base architecture includes a vision encoder, but this fine-tuning run did not train on image or video examples. Treat these GGUF files as text-generation/runtime quantizations of the merged fine-tuned checkpoint. - **Developed by:** @hesamation - **Source model:** `hesamation/Qwen3.6-35B-A3B-Claude-4.6-Opus-Reasoning-Distilled` - **Base model:** `Qwen/Qwen3.6-35B-A3B` - **License:** apache-2.0

• indobert-large-p2↗

  indobenchmark

  IndoBERT is a state-of-the-art language model for Indonesian based on the BERT model. The pretrained model is trained using a masked language modeling (MLM) objective and next sentence prediction (NSP) objective. IndoBERT was trained and evaluated by Bryan Wilie\*, Karissa Vincentio\*, Genta Indra Winata\*, Samuel Cahyawijaya\*, Xiaohong Li, Zhi Yuan Lim, Sidik Soleman, Rahmad Mahendra, Pascale Fung, Syafri Bahar, Ayu Purwarianti.

• MERT-v1-330M↗

  m-a-p

  The development log of our Music Audio Pre-training (m-a-p) model family: - 02/06/2023: arxiv pre-print and training codes released. - 17/03/2023: we release two advanced music understanding models, MERT-v1-95M and MERT-v1-330M , trained with new paradigm and dataset. They outperform the previous models and can better generalize to more tasks. - 14/03/2023: we retrained the MERT-v0 model with open-source-only music dataset MERT-v0-public - 29/12/2022: a music understanding model MERT-v0 trained with **MLM** paradigm, which performs better at downstream tasks. - 29/10/2022: a pre-trained MIR model music2vec trained with **BYOL** paradigm. The m-a-p models share the similar model architecture and the most distinguished difference is the paradigm in used pre-training. Other than that, there are several nuance technical configuration needs to know before using: - **Model Size**: the number of parameters that would be loaded to memory. Please select the appropriate size fitting your hardware. - **Transformer Layer-Dimension**: The number of transformer layers and the corresponding feature dimensions can be outputted from our model. This is marked out because features extracted by **different layers could have various performance depending on tasks**. - **Feature Rate**: Given a 1-second audio input, the number of features output by the model. - **Sample Rate**: The frequency of audio that the model is trained with.

• ERNIE-Image-Turbo-GGUF↗

  unsloth

  This is a GGUF quantized version of ERNIE-Image-Turbo. unsloth/ERNIE-Image-Turbo-GGUF uses Unsloth Dynamic 2.0 methodology for SOTA performance. - Important layers are upcasted to higher precision. - Uses tooling from ComfyUI-GGUF by city96. ERNIE-Image-Turbo is an open text-to-image generation model developed by the ERNIE-Image team at Baidu. It is the distilled release of ERNIE-Image, built on the same single-stream Diffusion Transformer (DiT) family and designed for fast generation with strong fidelity in only 8 inference steps. The model retains strong controllability in practical generation scenarios where accurate content realization matters as much as aesthetics. In particular, ERNIE-Image-Turbo remains strong on complex instruction following, text rendering, and structured image generation, making it well suited for posters, comics, multi-panel layouts, and other content creation tasks that require both visual quality and efficiency. It also supports a broad range of visual styles, including realistic photography, design-oriented imagery, and stylized aesthetic outputs. **Highlights:** - **Fast and efficient**: As the distilled checkpoint of ERNIE-Image, ERNIE-Image-Turbo delivers strong generation quality with only 8 inference steps, making it suitable for latency-sensitive applications. - **Text rendering**: ERNIE-Image-Turbo performs well on dense, long-form, and layout-sensitive text, making it a strong choice for posters, infographics, UI-like images, and other text-heavy visual content. - **Instruction following**: The model is able to follow complex prompts involving multiple objects, detailed relationships, and knowledge-intensive descriptions with strong reliability. - **Structured generation**: ERNIE-Image-Turbo is effective for structured visual tasks such as posters, comics, storyboards, and multi-panel compositions, where layout and organization are critical. - **Style coverage**: In addition to clean and readable design-oriented outputs, the model also supports realistic photography and distinctive stylized aesthetics, including softer and more cinematic visual tones. - **Practical deployment**: Thanks to its compact size, ERNIE-Image-Turbo

• distilcamembert-base-sentiment↗

  cmarkea

  We present DistilCamemBERT-Sentiment, which is DistilCamemBERT fine-tuned for the sentiment analysis task for the French language. This model is built using two datasets: Amazon Reviews and Allociné.fr to minimize the bias. Indeed, Amazon reviews are similar in messages and relatively shorts, contrary to Allociné critics, who are long and rich texts. This modelization is close to tblard/tf-allocine based on CamemBERT model. The problem of the modelizations based on CamemBERT is at the scaling moment, for the production phase, for example. Indeed, inference cost can be a technological issue. To counteract this effect, we propose this modelization which **divides the inference time by two** with the same consumption power thanks to DistilCamemBERT. The dataset comprises 204,993 reviews for training and 4,999 reviews for the test from Amazon, and 235,516 and 4,729 critics from Allocine website. The dataset is labeled into five categories:

• sam-vit-large↗

  facebook

  0. TL;DR 1. Model Details 2. Usage 3. Citation The **Segment Anything Model (SAM)** produces high quality object masks from input prompts such as points or boxes, and it can be used to generate masks for all objects in an image. It has been trained on a dataset of 11 million images and 1.1 billion masks, and has strong zero-shot performance on a variety of segmentation tasks. The abstract of the paper states: > We introduce the Segment Anything (SA) project: a new task, model, and dataset for image segmentation. Using our efficient model in a data collection loop, we built the largest segmentation dataset to date (by far), with over 1 billion masks on 11M licensed and privacy respecting images. The model is designed and trained to be promptable, so it can transfer zero-shot to new image distributions and tasks. We evaluate its capabilities on numerous tasks and find that its zero-shot performance is impressive -- often competitive with or even superior to prior fully supervised results. We are releasing the Segment Anything Model (SAM) and corresponding dataset (SA-1B) of 1B masks and 11M images at https://segment-anything.com to foster research into foundation models for computer vision.

• KAT-Coder-V2.5-Dev-APEX-I-MiniPlus-V2.1-GGUF↗

  IsValorum

  If you consider these releases to be of high quality and they help you in your day-to-day workflow, consider supporting on Ko-fi. Every contribution directly sustains future cloud compute hours and helps support my university studies. > > *Independently computed on private cloud clusters. If this handcrafted release saves you VRAM and runs faster on your GPU, consider fueling the community compute fund on Ko-fi.* > > Explore the new canonical V3 releases. MiniPlus prioritizes Q5-class to near-Q6 fidelity without a fixed file-size ceiling; NanoPlus targets Q4-class quality at a practical footprint. > > - **Qwen3.8 27B — MiniPlus V3** — 14.16 GB **(+13.21% improvement in WikiText-2 PPL vs GSQ-RCO IQ3_S)**. > - **Qwen3.8 27B — NanoPlus V3** — 11.35 GB **(+11.49% improvement in WikiText-2 PPL vs GSQ-RCO IQ3_S)**. > - **Swift-1.5 Qwen3.8 27B Uncensored MTP — MiniPlus V3** — 14.28 GB **(+5.70% improvement in WikiText-2 PPL vs GSQ-RCO IQ3_S)**. > - **Swift-1.5 Qwen3.8 27B Uncensored MTP — NanoPlus V3** — 11.08 GB **(+2.26% improvement in WikiText-2 PPL vs GSQ-RCO IQ3_S)**. > > Percentages compare the reported WikiText-2 PPL with GSQ-RCO IQ3_S (7.07). The linked 27B cards document the evaluation protocol and model variants. > > **Explore the APEX-I MiniPlus V2.1 collection** > > ### EXPLORE THE ESTABLISHED 35B MoE MINIPLUS LINEUP > These are complementary APEX-I-MiniPlus V2.1 releases, not alternate downloads of the same model. Each receives the same tensor-by-tensor approach, integrated MTP where supported, and a design suitable for full or partial system-RAM inference. Choose the model whose native strengths best fit the work you want to do: > > - **Qwen3.6-35B-A3B MTP APEX-I-MiniPlus-V2.1** — a versatile frontier MoE for broad reasoning, multilingual work, agents, tool use, and multimodal tasks. > - **Best for:** General reasoning, agent workflows, tool calling, and flexible multimodal use. > - **Qwen3.6-35B-A3B MTP APEX-I-MiniPlus-V2.1 Abliterated** — the V2.1 refusal-ablated Qwen3.6 edition for users who deliberately prefer reduced refusal behavior. > - **Best for:** Workflows where an abliterated Qwen3.6 variant is explicitly desired. > - **Ornith 1.5 APEX-I-MiniP

• sam-hq-vit-base↗

  syscv-community

  Architecture of SAM-HQ compared to the original SAM model, showing the HQ-Output Token and Global-local Feature Fusion components. 0. TL;DR 1. Model Details 2. Usage 3. Citation SAM-HQ (Segment Anything in High Quality) is an enhanced version of the Segment Anything Model (SAM) that produces higher quality object masks from input prompts such as points or boxes. While SAM was trained on a dataset of 11 million images and 1.1 billion masks, its mask prediction quality falls short in many cases, particularly when dealing with objects that have intricate structures. SAM-HQ addresses these limitations with minimal additional parameters and computation cost.

• GLM-4-9B-0414-GGUF↗

  unsloth

  The GLM family welcomes new members, the **GLM-4-32B-0414** series models, featuring 32 billion parameters. Its performance is comparable to OpenAI’s GPT series and DeepSeek’s V3/R1 series. It also supports very user-friendly local deployment features. GLM-4-32B-Base-0414 was pre-trained on 15T of high-quality data, including substantial reasoning-type synthetic data. This lays the foundation for subsequent reinforcement learning extensions. In the post-training stage, we employed human preference alignment for dialogue scenarios. Additionally, using techniques like rejection sampling and reinforcement learning, we enhanced the model’s performance in instruction following, engineering code, and function calling, thus strengthening the atomic capabilities required for agent tasks. GLM-4-32B-0414 achieves good results in engineering code, Artifact generation, function calling, search-based Q&A, and report generation. In particular, on several benchmarks, such as code generation or specific Q&A tasks, GLM-4-32B-Base-0414 achieves comparable performance with those larger models like GPT-4o and DeepSeek-V3-0324 (671B). **GLM-Z1-32B-0414** is a reasoning model with deep thinking capabilities. This was developed based on GLM-4-32B-0414 through cold start, extended reinforcement learning, and further training on tasks including mathematics, code, and logic. Compared to the base model, GLM-Z1-32B-0414 significantly improves mathematical abilities and the capability to solve complex tasks. During training, we also introduced general reinforcement learning based on pairwise ranking feedback, which enhances the model's general capabilities. **GLM-Z1-Rumination-32B-0414** is a deep reasoning model with rumination capabilities (against OpenAI's Deep Research). Unlike typical deep thinking models, the rumination model is capable of deeper and longer thinking to solve more open-ended and complex problems (e.g., writing a comparative analysis of AI development in two cities and their future development plans). Z1-Rumination is trained through scaling end-to-end reinforcement learning with responses graded by the ground truth answers or rubrics and can make use of search tools du