Results for “huggingface-transformers”

Quantize large language models to 8/4/3/2/1-bit precision without calibration data, using multiple optimized backends and integrations with HuggingFace Transformers, vLLM, and PEFT/LoRA.

Generate high-quality sentence and text embeddings for semantic similarity, clustering, and retrieval using 5000+ pre-trained models. Supports multilingual and domain-specific embeddings for RAG and semantic search.

Quantize large language models to 8/4/3/2/1-bit precision without calibration data, using multiple optimized backends for deployment with vLLM or HuggingFace Transformers.

Fine-tune LLMs using LoRA, QLoRA, and PEFT with Hugging Face, including dataset preparation, hyperparameter tuning, evaluation, and deployment.

Train and run Mamba state-space models with O(n) complexity, achieving faster inference and longer context than Transformers.

Fine-tune and align language models using reinforcement learning with TRL, including SFT, DPO, PPO, GRPO, and reward model training.

Half-Quadratic Quantization for LLMs without calibration data. Use when quantizing models to 4/3/2-bit precision without needing calibration datasets, for fast quantization workflows, or when deploying with vLLM or HuggingFace Transformers.

Runs chest X-ray reasoning smoke tests using the NV-Reason-CXR-3B model via local inference or a public Hugging Face Space API.

Half-Quadratic Quantization for LLMs without calibration data. Use when quantizing models to 4/3/2-bit precision without needing calibration datasets, for fast quantization workflows, or when deploying with vLLM or HuggingFace Transformers.

Fine-tune large language models by training less than 1% of parameters using LoRA, QLoRA, and 25+ adapter methods, enabling efficient adaptation on limited GPU memory.

Detects prompt injection attacks targeting LLM-based applications using regex pattern matching, heuristic scoring, and DeBERTa transformer classification.

Fine-tune large language models by training less than 1% of parameters using LoRA, QLoRA, and 25+ adapter methods, enabling efficient adaptation on consumer GPUs.

Fast tokenizers optimized for research and production. Rust-based implementation tokenizes 1GB in <20 seconds. Supports BPE, WordPiece, and Unigram algorithms. Train custom vocabularies, track alignments, handle padding/truncation. Integrates seamlessly with transformers. Use when you need high-performance tokenization or custom tokenizer training.

Merge multiple fine-tuned models using mergekit to combine capabilities without retraining, covering SLERP, TIES-Merging, DARE, Task Arithmetic, linear merging, and production deployment strategies.

Simplest distributed training API. 4 lines to add distributed support to any PyTorch script. Unified API for DeepSpeed/FSDP/Megatron/DDP. Automatic device placement, mixed precision (FP16/BF16/FP8). Interactive config, single launch command. HuggingFace ecosystem standard.

Fast tokenizers optimized for research and production. Rust-based implementation tokenizes 1GB in <20 seconds. Supports BPE, WordPiece, and Unigram algorithms. Train custom vocabularies, track alignments, handle padding/truncation. Integrates seamlessly with transformers. Use when you need high-performance tokenization or custom tokenizer training.

Train or fine-tune language and vision models using TRL or Unsloth on Hugging Face Jobs cloud infrastructure, with support for SFT, DPO, GRPO, and reward modeling, plus GGUF conversion for local deployment.

Search the Hugging Face Hub for llama.cpp-compatible GGUF models, select the right quantization, and run them locally with llama-cli or llama-server.

Search models, datasets, Spaces, and papers on the Hugging Face Hub, retrieve repository details and documentation, run compute jobs, and use Gradio Spaces as AI tools via the Hugging Face MCP server.

Integrate a HuggingFace computer vision model into the NVIDIA TAO Toolkit ecosystem, covering the full pipeline from prerequisites to container testing.

Add distributed training support to any PyTorch script with minimal code changes using a unified API for DDP, DeepSpeed, FSDP, and mixed precision.

Run PyTorch training across GPUs with minimal changes.

Quantize large language models to 4-bit with minimal accuracy loss using GPTQ, enabling deployment of 70B+ models on consumer GPUs with 4× memory reduction and 3-4× faster inference.

Train Mixture of Experts (MoE) models using DeepSpeed or HuggingFace. Use when training large-scale models with limited compute (5× cost reduction vs dense models), implementing sparse architectures like Mixtral 8x7B or DeepSeek-V3, or scaling model capacity without proportional compute increase. Covers MoE architectures, routing mechanisms, load balancing, expert parallelism, and inference optimization.

Deploy Meta's LlamaGuard moderation model to filter LLM inputs and outputs across 6 safety categories using HuggingFace, vLLM, or FastAPI.

State-of-the-art text-to-image generation with Stable Diffusion models via HuggingFace Diffusers. Use when generating images from text prompts, performing image-to-image translation, inpainting, or building custom diffusion pipelines.

State-of-the-art text-to-image generation with Stable Diffusion models via HuggingFace Diffusers. Use when generating images from text prompts, performing image-to-image translation, inpainting, or building custom diffusion pipelines.

Parameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods. Use when fine-tuning large models (7B-70B) with limited GPU memory, when you need to train <1% of parameters with minimal accuracy loss, or for multi-adapter serving. HuggingFace's official library integrated with transformers ecosystem.

Train Mixture of Experts (MoE) models using DeepSpeed or HuggingFace. Use when training large-scale models with limited compute (5× cost reduction vs dense models), implementing sparse architectures like Mixtral 8x7B or DeepSeek-V3, or scaling model capacity without proportional compute increase. Covers MoE architectures, routing mechanisms, load balancing, expert parallelism, and inference optimization.

Parameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods. Use when fine-tuning large models (7B-70B) with limited GPU memory, when you need to train <1% of parameters with minimal accuracy loss, or for multi-adapter serving. HuggingFace's official library integrated with transformers ecosystem.