{"adoption": {"forks": 262, "observed_at": "2026-08-28T04:04:36.059276+00:00", "stars": 1392}, "canonical_url": "https://ross.abutalabs.com/products/deep-learning-pytorch-huggingface", "card": {"archived": false, "artifact_type": "learning-resource", "description": null, "domain": ["deep-learning", "large-language-models", "machine-learning", "tutorials"], "enriched": true, "function": ["machine-learning", "deep-learning", "llm-training", "llm-inference", "rag"], "health_score": 25, "homepage": null, "language": "Jupyter Notebook", "license": "MIT", "license_family": "permissive", "maturity": "active", "member_repos": ["philschmid/deep-learning-pytorch-huggingface"], "name": "philschmid/deep-learning-pytorch-huggingface", "platform": ["python", "cross-platform"], "pushed_at": "2025-02-27T14:37:20+00:00", "repo": "philschmid/deep-learning-pytorch-huggingface", "stars": 1392, "tags": ["pytorch", "hugging-face", "transformers", "jupyter-notebooks", "fine-tuning", "lora", "deepspeed", "dpo", "quantization", "example-code", "gpu"], "topics": [], "urls": [], "use_cases": ["learn how to fine-tune LLMs with Hugging Face TRL", "instruction-tune Llama 2 with QLoRA", "fine-tune an embedding model for RAG", "quantize open LLMs with GPTQ", "scale distributed training with FSDP and DeepSpeed", "align LLMs with DPO", "run efficient LLM inference and benchmarks"], "what_it_is": "A collection of Jupyter notebook tutorials and examples for deep learning with PyTorch and Hugging Face libraries like Transformers, Datasets, TRL, and Accelerate. It covers fine-tuning LLMs (FLAN-T5, Llama, Falcon, Gemma), quantization, DPO alignment, embedding models for RAG, and inference techniques.", "when_to_avoid": ["you need a production-ready training framework rather than tutorials", "you work outside the PyTorch/Hugging Face ecosystem", "you need non-LLM deep learning topics like computer vision"], "when_to_choose": ["you want hands-on, up-to-date notebooks for LLM fine-tuning with PyTorch and Hugging Face", "you need practical examples of LoRA, QLoRA, DPO, or GPTQ quantization", "you are learning distributed training with DeepSpeed or FSDP"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/deep-learning-pytorch-huggingface", "repo": "philschmid/deep-learning-pytorch-huggingface", "role": "main", "score": 35}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:04:36.059276+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T04:39:33.216091+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "84abe288c2a701a2489310c38e8b241d8fa4a4cd623acd512ce96aca03eff16d", "fetched_at": "2026-08-28T04:04:36.059276+00:00", "kind": "readme", "missing": false, "url": "https://github.com/philschmid/deep-learning-pytorch-huggingface"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:04:36.059276+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T04:39:33.216091+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "84abe288c2a701a2489310c38e8b241d8fa4a4cd623acd512ce96aca03eff16d", "fetched_at": "2026-08-28T04:04:36.059276+00:00", "kind": "readme", "missing": false, "url": "https://github.com/philschmid/deep-learning-pytorch-huggingface"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T04:39:33.216091+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "84abe288c2a701a2489310c38e8b241d8fa4a4cd623acd512ce96aca03eff16d", "fetched_at": "2026-08-28T04:04:36.059276+00:00", "kind": "readme", "missing": false, "url": "https://github.com/philschmid/deep-learning-pytorch-huggingface"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:04:36.059276+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:04:36.059276+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:04:36.059276+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T04:39:33.216091+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "84abe288c2a701a2489310c38e8b241d8fa4a4cd623acd512ce96aca03eff16d", "fetched_at": "2026-08-28T04:04:36.059276+00:00", "kind": "readme", "missing": false, "url": "https://github.com/philschmid/deep-learning-pytorch-huggingface"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:04:36.059276+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:04:36.059276+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T04:39:33.216091+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "84abe288c2a701a2489310c38e8b241d8fa4a4cd623acd512ce96aca03eff16d", "fetched_at": "2026-08-28T04:04:36.059276+00:00", "kind": "readme", "missing": false, "url": "https://github.com/philschmid/deep-learning-pytorch-huggingface"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:04:36.059276+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:04:36.059276+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:04:36.059276+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T04:39:33.216091+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "84abe288c2a701a2489310c38e8b241d8fa4a4cd623acd512ce96aca03eff16d", "fetched_at": "2026-08-28T04:04:36.059276+00:00", "kind": "readme", "missing": false, "url": "https://github.com/philschmid/deep-learning-pytorch-huggingface"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:04:36.059276+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:04:36.059276+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T04:39:33.216091+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "84abe288c2a701a2489310c38e8b241d8fa4a4cd623acd512ce96aca03eff16d", "fetched_at": "2026-08-28T04:04:36.059276+00:00", "kind": "readme", "missing": false, "url": "https://github.com/philschmid/deep-learning-pytorch-huggingface"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T04:39:33.216091+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "84abe288c2a701a2489310c38e8b241d8fa4a4cd623acd512ce96aca03eff16d", "fetched_at": "2026-08-28T04:04:36.059276+00:00", "kind": "readme", "missing": false, "url": "https://github.com/philschmid/deep-learning-pytorch-huggingface"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T04:39:33.216091+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "84abe288c2a701a2489310c38e8b241d8fa4a4cd623acd512ce96aca03eff16d", "fetched_at": "2026-08-28T04:04:36.059276+00:00", "kind": "readme", "missing": false, "url": "https://github.com/philschmid/deep-learning-pytorch-huggingface"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T04:39:33.216091+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "84abe288c2a701a2489310c38e8b241d8fa4a4cd623acd512ce96aca03eff16d", "fetched_at": "2026-08-28T04:04:36.059276+00:00", "kind": "readme", "missing": false, "url": "https://github.com/philschmid/deep-learning-pytorch-huggingface"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 8, "longevity": 97, "rhythm": 35}, "computed_at": "2026-09-02T17:46:02.011165+00:00", "flags": ["no_releases"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 1366, "days_push": 552, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 35, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}