뉴스 및 전체 검색
뉴스, 도구, 모델, 가이드, 주제, 워크플로, 프롬프트를 함께 검색합니다.
AI 모델 56
“AI Code Guide”
Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled
🔥 **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. 👉 **GitHub Repository: Jackrong-llm-finetuning-guide** Visit the repo to dive into the codebase and reproduce the results locally or on Colab. **🔗 Qwopus3.5-27b Complete Fine-Tuning Guide (PDF)** * **The Full Pipeline:** A step-by-step walkthrough—from downloading the base model and unifying heterogeneous data, to configuring trainer hyperparameters and publishing to Hugging Face. * **Beginner Friendly:** Includes an introductory guide to getting started with Google Colab and Unsloth. * *Feedback welcome! If you spot any areas for improvement, please let me know and I will update it promptly.*
GIST-Embedding-v0
*GISTEmbed: Guided In-sample Selection of Training Negatives for Text Embedding Fine-tuning* The model is fine-tuned on top of the BAAI/bge-base-en-v1.5 using the MEDI dataset augmented with mined triplets from the MTEB Classification training dataset (excluding data from the Amazon Polarity Classification task). The model does not require any instruction for generating embeddings. This means that queries for retrieval tasks can be directly encoded without crafting instructions.
E1-600m
This repository contains the model weights for the Profluent E1 family of models - our best in class single sequence and retrieval augmented protein representation models. They are designed to be drop-in replacement for ESM family of models. Please use them with code in https://github.com/Profluent-AI/E1 Your use of the Profluent-E1 model code is governed by the Apache License 2.0, while your use of the Profluent-E1 model weights and the full release of the Profluent-E1 model is governed by a similarly permissive license with additional attribution requirements - see the NOTICE file for details. You can use, share, and modify Profluent-E1 for free, but you must follow our ATTRIBUTION guidelines to give credit, include the license when you share and follow some other basic rules. Profluent is not responsible for what you build, and may terminate your rights to use Profluent-E1 if you breach the license.
Qwen3.8-27B-NVFP4
> [!Note] > This model works with vLLM. It also works with SGLang, but only with the v0.5.19, because the `lm_head` is FP8 rather than 4-bit. This NVFP4 quant uses Unsloth Dynamic V3.0 (preview) for SOTA quantization performance. Developer Role Support so Qwen3.8 can work in agentic tools like Codex and more! MTP for fast inference is available. Qwen3.8 can now be run and fine-tuned in Unsloth Desktop . Read our guide . Tool calling improvements: Makes parsing nested objects to make tool calling succeed more. See below for 4-bit Qwen3.8-27B run inside of Unsloth Desktop:
Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-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.
Qwen3.5-9B-Claude-4.6-Opus-Reasoning-Distilled-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.