القائمة
Skills في هذا المستودع
جمع SkillsMP عدد ٦٤ من skills من cuba6112/skillfactory. افتح أي skill لمراجعة مصدره وتفاصيله.
cuba6112/skillfactoryعرض ٢٤ من أصل ٦٤ skills مجمعة.
Optimize PyTorch with torch.compile (TorchDynamo/Inductor), focusing on compile overhead, graph breaks, and benchmark methodology. Use when speeding up PyTorch models or debugging compile behavior; triggers: torch.compile, torchdynamo, inductor, graph break,…
لغة النص الأصلي: الإنجليزية
Audio signal processing library for PyTorch. Covers feature extraction (spectrograms, mel-scale), waveform manipulation, and GPU-accelerated data augmentation techniques. (torchaudio, melscale, spectrogram, pitchshift, specaugment, waveform, resample)
لغة النص الأصلي: الإنجليزية
Model serving engine for PyTorch. Focuses on MAR packaging, custom handlers for preprocessing/inference, and management of multi-GPU worker scaling. (torchserve, mar-file, handler, basehandler, model-archiver, inference-api)
لغة النص الأصلي: الإنجليزية
Natural Language Processing utilities for PyTorch (Legacy). Includes tokenizers, vocabulary building, and DataPipe-based dataset handling for text processing pipelines. (torchtext, tokenizer, vocab, datapipe, regextokenizer, nlp-pipeline)
لغة النص الأصلي: الإنجليزية
Computer vision library for PyTorch featuring pretrained models, advanced image transforms (v2), and utilities for handling complex data types like bounding boxes and masks. (torchvision, transforms, tvtensor, resnet, cutmix, mixup, pretrained models, vision…
لغة النص الأصلي: الإنجليزية
Core fundamentals of Unsloth for fast LLM fine-tuning, covering FastLanguageModel setup, optimized gradient checkpointing, and native inference acceleration (triggers: unsloth, FastLanguageModel, from_pretrained, get_peft_model, for_inference, gradient…
لغة النص الأصلي: الإنجليزية
Strategies for continued pretraining and domain adaptation in Unsloth (triggers: continued pretraining, CPT, domain adaptation, lm_head, embed_tokens, rsLoRA, embedding_learning_rate).
لغة النص الأصلي: الإنجليزية
Standardizing and formatting datasets for Unsloth, including chat template conversion and synthetic data generation (triggers: chat templates, ShareGPT, Alpaca, conversation_extension, add_new_tokens, standardize_sharegpt, formatting_prompts_func).
لغة النص الأصلي: الإنجليزية
Direct Preference Optimization (DPO) for aligning models with preference data without separate reward models. Triggers: dpo, preference optimization, rlhf, ref_model=none, patchdpotrainer, dpotrainer.
لغة النص الأصلي: الإنجليزية
Performing full fine-tuning (FFT) in Unsloth with 100% exact weight updates and optimized gradient checkpointing. Triggers include fft, full fine-tuning, full_finetuning, exact fine-tuning, and weight updates.
لغة النص الأصلي: الإنجليزية
Exporting fine-tuned models to GGUF format for deployment in llama.cpp, Ollama, and local serving tools. Triggers: gguf, quantization export, llama.cpp, ollama, save_pretrained_gguf, modelfile.
لغة النص الأصلي: الإنجليزية
Implementation of Group Relative Policy Optimization (GRPO) for training reasoning models, optimized for 8x memory savings (triggers: GRPO, reasoning, DeepSeek-R1, reinforcement learning, RLVR, GRPOTrainer, thinking tokens).
لغة النص الأصلي: الإنجليزية
Deploying fine-tuned models for production inference using native kernel optimization, vLLM, or SGLang. Triggers: inference, serving, vllm, sglang, for_inference, model merging, openai api.
لغة النص الأصلي: الإنجليزية
Training models on extended context lengths using optimized RoPE scaling and memory-efficient attention kernels. Triggers: long context, max_seq_length, rope scaling, large context window, flex attention.
لغة النص الأصلي: الإنجليزية
Configuring and optimizing 16-bit Low-Rank Adaptation (LoRA) and Rank-Stabilized LoRA (rsLoRA) for efficient LLM fine-tuning using triggers like lora, qlora, rslora, rank selection, lora_alpha, lora_dropout, and target_modules.
لغة النص الأصلي: الإنجليزية
Guidance on selecting and configuring supported model architectures like Llama 4, DeepSeek-R1, and Qwen3. Triggers: llama 4, deepseek-r1, qwen3, gemma 3, model selection, instruct vs base.
لغة النص الأصلي: الإنجليزية
One-step preference alignment using Odds Ratio Preference Optimization (ORPO) (triggers: ORPO, preference optimization, alignment, ORPOTrainer, log_odds_ratio, binary preference).
لغة النص الأصلي: الإنجليزية
Advanced 4-bit quantization techniques using Unsloth and BitsAndBytes for extreme VRAM efficiency (triggers: QLoRA, 4-bit, load_in_4bit, bnb-4bit, VRAM optimization, dynamic quantization).
لغة النص الأصلي: الإنجليزية
Utilizing Dynamic 4-bit quantization, FP8 training, and 8-bit optimizers to minimize VRAM usage without sacrificing accuracy. Triggers: quantization, dynamic 4-bit, fp8, bitsandbytes, adamw_8bit, qat.
لغة النص الأصلي: الإنجليزية
Supervised fine-tuning using SFTTrainer, instruction formatting, and multi-turn dataset preparation with triggers like sft, instruction tuning, chat templates, sharegpt, alpaca, conversation_extension, and SFTTrainer.
لغة النص الأصلي: الإنجليزية
Fine-tuning Speech-to-Text models like Whisper using Unsloth's optimized LoRA pipeline. Triggers: stt, whisper, transcription, audio fine-tuning, speech-to-text, audio normalization.
لغة النص الأصلي: الإنجليزية
Fine-tuning Text-to-Speech (TTS) models with Unsloth for voice cloning and synthetic speech (triggers: TTS, text-to-speech, voice cloning, Orpheus-TTS, audio fine-tuning, speech synthesis).
لغة النص الأصلي: الإنجليزية
Fine-tuning multimodal vision-language models (Llama 3.2 Vision, Qwen2.5 VL) using optimized vision layers (triggers: vision models, multimodal, Llama 3.2 Vision, Qwen2.5 VL, UnslothVisionDataCollator, finetune_vision_layers).
لغة النص الأصلي: الإنجليزية
Design vector database ingestion and retrieval pipelines (points + payloads, filtered similarity search, multi-stage hybrid retrieval, index maintenance). Use when building RAG/vector search flows or debugging retrieval quality; triggers: vector database,…
لغة النص الأصلي: الإنجليزية