新闻与全站搜索
关联新闻、工具、模型、指南、专题、工作流与提示词。
AI 模型 56
“AI Code Guide”
Qwen3.6-27B-GGUF
Developer Role Support so Qwen3.6 can work in Codex, OpenCode and more! Qwen3.6 can now be run and fine-tuned in Unsloth Studio . Read our guide . Tool calling improvements: Makes parsing nested objects to make tool calling succeed more. Example of Qwen3.6 35B-A3B (4-bit GGUF) running in Unsloth Studio with tool-calling: > [!Note] > This repository contains model weights and configuration files for the post-trained model in the Hugging Face Transformers format. > > These artifacts are compatible with Hugging Face Transformers, vLLM, SGLang, KTransformers, etc. Following the February release of the Qwen3.5 series, we're pleased to share the first open-weight variant of Qwen3.6. Built on direct feedback from the community, Qwen3.6 prioritizes stability and real-world utility, offering developers a more intuitive, responsive, and genuinely productive coding experience.
Ling-mini-2.0
Today, we are excited to announce the open-sourcing of **Ling 2.0** — a family of MoE-based large language models that combine **SOTA performance** with **high efficiency**. The first released version, Ling-mini-2.0, is compact yet powerful. It has **16B total parameters**, but only **1.4B** are activated per input token (non-embedding 789M). Trained on more than **20T tokens** of high-quality data and enhanced through multi-stage supervised fine-tuning and reinforcement learning, Ling-mini-2.0 achieves remarkable improvements in complex reasoning and instruction following. With just 1.4B activated parameters, it still reaches the top-tier level of sub-10B dense LLMs and even matches or surpasses much larger MoE models. We evaluated Ling-mini-2.0 on challenging general reasoning tasks in coding (LiveCodeBench, CodeForces) and mathematics (AIME 2025, HMMT 2025), as well as knowledge-intensive reasoning tasks across multiple domains (MMLU-Pro, Humanity's Last Exam). Compared with sub-10B dense models (e.g., Qwen3-4B-instruct-2507, Qwen3-8B-nothinking) and larger-scale MoE models (Ernie-4.5-21B-A3B-PT, GPT-OSS-20B/low), Ling-mini-2.0 demonstrated outstanding overall reasoning capabilities. Guided by Ling Scaling Laws, Ling 2.0 adopts a **1/32 activation ratio** MoE architecture, with empirically optimized design choices in expert granularity, shared expert ratio, attention ratio, aux-loss free + sigmoid routing strategy, MTP loss, QK-Norm, half RoPE, and more. This enables small-activation MoE models to achieve over **7× equivalent dense performance**. In other words, **Ling-mini-2.0 with only 1.4B activated parameters (non-embedding 789M) can deliver performance equivalent to a 7–8B dense model**.
chronos-2
**Update Jun 5, 2026:** ☁️ Deploy Chronos-2 on AWS with AutoGluon-Cloud. Real-time, serverless, or batch inference in 3 lines of code — pandas DataFrames in, forecasts out. Check out the new deployment guide. **Chronos-2** is a 120M-parameter, encoder-only time series foundation model for zero-shot forecasting. It supports **univariate**, **multivariate**, and **covariate-informed** tasks within a single architecture. Inspired by the T5 encoder, Chronos-2 produces multi-step-ahead quantile forecasts and uses a group attention mechanism for efficient in-context learning across related series and covariates. Trained on a combination of real-world and large-scale synthetic datasets, it achieves **state-of-the-art zero-shot accuracy** among public models on **fev-bench**, **GIFT-Eval**, and **Chronos Benchmark II**. Chronos-2 is also **highly efficient**, delivering over 300 time series forecasts per second on a single A10G GPU and supporting both **GPU and CPU inference**. 🧩 Chronos & Chronos-Bolt do not natively support future covariates, but they can be combined with external covariate regressors (see AutoGluon tutorial). This only models per-timestep effects, not effects across time. In contrast, Chronos-2 supports all covariate types natively.
gemma-4-12b-it
Gemma 4 12B can now be run and fine-tuned in Unsloth Studio . Read our guide . See all versions of Gemma 4 (GGUF, 16-bit etc.) in our collection . Example of Gemma 4 E4B (4-bit GGUF) running in Unsloth Studio with tool-calling: > [!Note] > This model card is for the Gemma 4 12B Unified model, which is part of the Gemma 4 family of open models. Built with the same multimodal functionality as Gemma 4 E2B and E4B (text, audio, image, and video inputs), it brings native audio and vision understanding directly to local environments without the need for separate encoders. This unified approach to multimodality makes the model encoder-free, offering a deployment size that is perfect for consumer devices and streamlined local execution. Gemma is a family of open models built by Google DeepMind. Gemma 4 models are multimodal, handling text and image input (with audio supported on E2B, E4B, and 12B) and generating text output. This release includes open-weights models in both pre-trained and instruction-tuned variants. Gemma 4 features a context window of up to 256K tokens and maintains multilingual support in over 140 languages.
Llama-3.1-Tulu-3-8B-DPO
Tülu3 is a leading instruction following model family, offering fully open-source data, code, and recipes designed to serve as a comprehensive guide for modern post-training techniques. Tülu3 is designed for state-of-the-art performance on a diversity of tasks in addition to chat, such as MATH, GSM8K, and IFEval. The Tülu3 models have limited safety training, but are not deployed automatically with in-the-loop filtering of responses like ChatGPT, so the model can produce problematic outputs (especially when prompted to do so). It is also unknown what the size and composition of the corpus was used to train the base Llama 3.1 models, however it is likely to have included a mix of Web data and technical sources like books and code. See the Falcon 180B model card for an example of this. DPO: - **Learning Rate**: 5 × 10⁻⁷ (8B), 2.0e-7 (70B, 405B) - **Learning Rate Schedule**: Linear - **Batch Size (effective)**: 128 (8B), 128 (70B), 256(405B) - **KL Penalty Coefficient**: 5 - **Warm-up Ratio**: 0.1 - **Max Sequence Length**: 2,048 - **Epochs**: 1
Qwen3.8-27B-pi-GGUF
**Qwen3.8-27B-pi** builds on Qwen3.8-27B for coding work in the Pi agent harness. It is tailored to the loop of reading a repository, editing files, running tools, and responding to their feedback. The aim is more completed work with less generated text, while retaining the base model's familiar interface. Fine-tuned for the Pi agent harness, the model is designed to work through coding tasks as an iterative process: inspect the code, make a change, check the result, and use tool feedback to guide the next step. Adjustable reasoning effort lets you balance responsiveness with deeper problem-solving, from focused edits to more involved debugging and implementation work. - **Built for Pi:** Fine-tuned for the everyday coding loop—reading repositories, editing files, running tools, and working through feedback in the Pi harness—with an emphasis on turning plans into working, checked implementations. - **Curated coding experience:** Supervised fine-tuning on filtered, successful Pi sessions helps the model learn complete coding workflows, rather than isolated answers or code snippets, including how to adapt to existing environments and check results against task requirements. - **Task quality matters:** Development also included reviewing, repairing, and exploring more demanding coding tasks—with a focus on clear requirements and checks that distinguish working solutions from incorrect ones. - **Refined through reinforcement learning:** A second training stage pairs verified task outcomes with a custom reasoning-efficiency reward built on GRPO, encouraging successful low- and medium-effort solutions to reason more economically while leaving xhigh focused on correctness. - **Available in practical formats:** Choose a deployment format that fits your hardware, including GGUF quantizations calibrated using complete Pi coding sessions.
Kimi-K2.7-Code-GGUF
To run Kimi K2.7 Code in full precision lossless, run Q8 (UD-Q8_K_XL), which is 595GB and only 10GB bigger than Q4 (UD-Q4_K_XL). See our Kimi K2.7 Code guide for quantization analysis and instructions. Kimi K2.7 Code is a coding-focused agentic model built upon Kimi K2.6. With substantial improvements on real-world long-horizon coding tasks, it strengthens end-to-end task completion across complex software engineering workflows while improving token efficiency, reducing thinking-token usage by approximately 30% compared with Kimi K2.6. 1. **General Testing Details** - Unless stated otherwise, Kimi K2.7 Code and K2.6 were tested with thinking mode enabled via Kimi Code CLI at temperature = 1.0, top-p = 0.95, and a 262,144-token context length; GPT-5.5 ran in Codex with xhigh mode, and Opus 4.8 in Claude Code with xhigh mode. Aside from these differences, all benchmarks were evaluated under the same conditions. 2. **Coding Benchmarks** - Kimi Code Bench V2 is our in-house benchmark designed to evaluate coding agents on realistic tasks. It has diversed software engineering tasks across 10+ mainstream programming languages and a full production tech stack covering tasks from internal engineering use cases, production incidents, and real-world open-source projects, with emphasis on backend services, infrastructure, performance engineering, systems programming, security, frontend development, and ML/data engineering. - Program Bench evaluates code-generation agents by asking them to recreate a program’s behavior from only a compiled binary and its documentation. It spans 200 tasks, from small CLI tools to large systems like FFmpeg and SQLite. Submissions are judged against over 248,000 fuzz-generated behavioral tests. In each task, the agent is given an executable and its documentation, but no source code, decompilation, or internet access. It must choose its own implementation language, build the full program from scratch, and pass a behavioral test suite comparing its output against the original binary. - MLS-Bench evaluates whether AI systems can invent generalizable and scalable ML methods. MLS-Bench-Lite is the official 30-task subset of MLS-Bench, covering LLM pretraining and post-training, robotics, world models, computer vision, reinforcement learning, optimization, ML systems, AI for Science, and more. Agents are given 5 hours to explore before submitting
gemma-4-12b-it-GGUF
Jun 9 Update: Added MTP support. See our MTP Guide . Gemma 4 12B can now be run and fine-tuned in Unsloth Studio . Read our guide . See all versions of Gemma 4 (GGUF, 16-bit etc.) in our collection . Example of Gemma 4 E4B (4-bit GGUF) running in Unsloth Studio with tool-calling: > [!Note] > This model card is for the Gemma 4 12B Unified model, which is part of the Gemma 4 family of open models. Built with the same multimodal functionality as Gemma 4 E2B and E4B (text, audio, image, and video inputs), it brings native audio and vision understanding directly to local environments without the need for separate encoders. This unified approach to multimodality makes the model encoder-free, offering a deployment size that is perfect for consumer devices and streamlined local execution. Gemma is a family of open models built by Google DeepMind. Gemma 4 models are multimodal, handling text and image input (with audio supported on E2B, E4B, and 12B) and generating text output. This release includes open-weights models in both pre-trained and instruction-tuned variants. Gemma 4 features a context window of up to 256K tokens and maintains multilingual support in over 140 languages.
GLM-Z1-32B-0414
The GLM family welcomes a new generation of open-source models, the **GLM-4-32B-0414** series, featuring 32 billion parameters. Its performance is comparable to OpenAI's GPT series and DeepSeek's V3/R1 series, and it supports very user-friendly local deployment features. GLM-4-32B-Base-0414 was pre-trained on 15T of high-quality data, including a large amount of reasoning-type synthetic data, laying the foundation for subsequent reinforcement learning extensions. In the post-training stage, in addition to human preference alignment for dialogue scenarios, we also enhanced the model's performance in instruction following, engineering code, and function calling using techniques such as rejection sampling and reinforcement learning, strengthening the atomic capabilities required for agent tasks. GLM-4-32B-0414 achieves good results in areas such as engineering code, Artifact generation, function calling, search-based Q&A, and report generation. Some benchmarks even rival 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 and extended reinforcement learning, as well as further training of the model on tasks involving 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 the training process, we also introduced general reinforcement learning based on pairwise ranking feedback, further enhancing the model's general capabilities. **GLM-Z1-Rumination-32B-0414** is a deep reasoning model with **rumination capabilities** (benchmarked against OpenAI's Deep Research). Unlike typical deep thinking models, the rumination model employs longer periods of deep thought 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). The rumination model integrates search tools during its deep thinking process to handle complex tasks and is trained by utilizing multiple rule-based rewards to guide and extend end-to-end reinforcement learning. Z1-Rumination shows significant improvements in research-style writing and complex retrieval tasks.
Qwen3.5-9B-Claude-4.6-Opus-Reasoning-Distilled-v2-GGUF
🔥 **Update (April 5):** I’ve released the complete training notebook, codebase, and a comprehensive PDF guide to help beginners and enthusiasts understand and reproduce this model's fine-tuning process. > ❤️ Special thanks to the **Unsloth** open-source library and @KyleHessling1 for their support. 👉 **GitHub Repository: Jackrong-llm-finetuning-guide** Visit the repo to dive into the codebase and reproduce the results locally or on Colab.