{"adoption": {"forks": 222, "observed_at": "2026-08-28T04:05:59.381156+00:00", "stars": 1960}, "canonical_url": "https://ross.abutalabs.com/products/qwen-vl-series-finetune", "card": {"archived": false, "artifact_type": "library", "description": "An open-source implementaion for fine-tuning Qwen-VL series by Alibaba Cloud.", "domain": ["machine-learning", "deep-learning", "large-language-models", "computer-vision"], "enriched": true, "function": ["llm-training", "machine-learning", "deep-learning"], "health_score": 79, "homepage": null, "language": "Python", "license": "Apache-2.0", "license_family": "permissive", "maturity": "active", "member_repos": ["2U1/Qwen-VL-Series-Finetune"], "name": "2U1/Qwen-VL-Series-Finetune", "platform": ["python"], "pushed_at": "2026-08-22T20:39:07+00:00", "repo": "2U1/Qwen-VL-Series-Finetune", "stars": 1960, "tags": ["fine-tuning", "vision-language-model", "qwen-vl", "multimodal", "lora", "dpo", "grpo", "liger-kernel", "huggingface", "gpu"], "topics": ["multimodal", "qwen2-vl", "vision-language", "vision-language-model", "qwen3-vl", "qwen2-5-vl", "qwen3-5", "vlm"], "urls": [], "use_cases": ["fine-tune qwen2-vl on custom image datasets", "train qwen3-vl with lora on my own data", "run dpo training on a vision language model", "grpo training for multimodal models", "fine-tune qwen2.5-vl for video understanding", "train a vlm classifier on custom categories", "reduce gpu memory when fine-tuning vision language models"], "what_it_is": "An open-source Python repository providing training scripts for fine-tuning Alibaba's Qwen-VL series of vision-language models (Qwen2-VL, Qwen2.5-VL, Qwen3-VL, Qwen3.5) using HuggingFace Transformers and Liger-Kernel. It supports SFT, DPO, GRPO, LoRA/DoRA, classification, and multi-image/video training with memory optimizations.", "when_to_avoid": ["you want to fine-tune non-Qwen vision-language models (use the author's sibling repos or generic frameworks like LLaMA-Factory)", "you need inference/serving rather than training", "you prefer a GUI or no-code fine-tuning workflow"], "when_to_choose": ["you need to fine-tune any Qwen-VL series model with SFT, DPO, or GRPO", "you want memory-efficient training via Liger-Kernel and attention optimizations", "you need LoRA/DoRA, partial layer freezing, or mixed-modality (image/video) training support"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/qwen-vl-series-finetune", "repo": "2U1/Qwen-VL-Series-Finetune", "role": "main", "score": 67}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:05:59.381156+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T03:05:41.056688+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d373ca69eeba2bf49013834c2bf6a855378d5590e18e9298a66a25a507b468c7", "fetched_at": "2026-08-28T04:05:59.381156+00:00", "kind": "readme", "missing": false, "url": "https://github.com/2U1/Qwen-VL-Series-Finetune"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:05:59.381156+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T03:05:41.056688+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d373ca69eeba2bf49013834c2bf6a855378d5590e18e9298a66a25a507b468c7", "fetched_at": "2026-08-28T04:05:59.381156+00:00", "kind": "readme", "missing": false, "url": "https://github.com/2U1/Qwen-VL-Series-Finetune"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T03:05:41.056688+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d373ca69eeba2bf49013834c2bf6a855378d5590e18e9298a66a25a507b468c7", "fetched_at": "2026-08-28T04:05:59.381156+00:00", "kind": "readme", "missing": false, "url": "https://github.com/2U1/Qwen-VL-Series-Finetune"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:05:59.381156+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:05:59.381156+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:05:59.381156+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T03:05:41.056688+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d373ca69eeba2bf49013834c2bf6a855378d5590e18e9298a66a25a507b468c7", "fetched_at": "2026-08-28T04:05:59.381156+00:00", "kind": "readme", "missing": false, "url": "https://github.com/2U1/Qwen-VL-Series-Finetune"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:05:59.381156+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:05:59.381156+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T03:05:41.056688+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d373ca69eeba2bf49013834c2bf6a855378d5590e18e9298a66a25a507b468c7", "fetched_at": "2026-08-28T04:05:59.381156+00:00", "kind": "readme", "missing": false, "url": "https://github.com/2U1/Qwen-VL-Series-Finetune"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:05:59.381156+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:05:59.381156+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:05:59.381156+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T03:05:41.056688+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d373ca69eeba2bf49013834c2bf6a855378d5590e18e9298a66a25a507b468c7", "fetched_at": "2026-08-28T04:05:59.381156+00:00", "kind": "readme", "missing": false, "url": "https://github.com/2U1/Qwen-VL-Series-Finetune"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:05:59.381156+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:05:59.381156+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T03:05:41.056688+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d373ca69eeba2bf49013834c2bf6a855378d5590e18e9298a66a25a507b468c7", "fetched_at": "2026-08-28T04:05:59.381156+00:00", "kind": "readme", "missing": false, "url": "https://github.com/2U1/Qwen-VL-Series-Finetune"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T03:05:41.056688+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d373ca69eeba2bf49013834c2bf6a855378d5590e18e9298a66a25a507b468c7", "fetched_at": "2026-08-28T04:05:59.381156+00:00", "kind": "readme", "missing": false, "url": "https://github.com/2U1/Qwen-VL-Series-Finetune"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T03:05:41.056688+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d373ca69eeba2bf49013834c2bf6a855378d5590e18e9298a66a25a507b468c7", "fetched_at": "2026-08-28T04:05:59.381156+00:00", "kind": "readme", "missing": false, "url": "https://github.com/2U1/Qwen-VL-Series-Finetune"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T03:05:41.056688+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d373ca69eeba2bf49013834c2bf6a855378d5590e18e9298a66a25a507b468c7", "fetched_at": "2026-08-28T04:05:59.381156+00:00", "kind": "readme", "missing": false, "url": "https://github.com/2U1/Qwen-VL-Series-Finetune"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 99, "longevity": 51, "rhythm": 35}, "computed_at": "2026-09-03T02:20:16.233290+00:00", "flags": ["no_releases"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 722, "days_push": 11, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 67, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}