{"adoption": {"forks": 61, "observed_at": "2026-09-03T02:15:16.915343+00:00", "stars": 1001}, "canonical_url": "https://ross.abutalabs.com/products/llama-moe", "card": {"archived": false, "artifact_type": "library", "description": "⛷️ LLaMA-MoE: Building Mixture-of-Experts from LLaMA with Continual Pre-training (EMNLP 2024)", "domain": ["large-language-models", "machine-learning", "deep-learning"], "enriched": true, "function": ["llm-training", "machine-learning", "deep-learning", "sdk"], "health_score": 24, "homepage": "https://arxiv.org/abs/2406.16554", "language": "Python", "license": "Apache-2.0", "license_family": "permissive", "maturity": "active", "member_repos": ["pjlab-sys4nlp/llama-moe"], "name": "pjlab-sys4nlp/llama-moe", "platform": ["python"], "pushed_at": "2024-12-06T04:47:07+00:00", "repo": "pjlab-sys4nlp/llama-moe", "stars": 1001, "tags": ["mixture-of-experts", "llama", "continual-pre-training", "expert-partitioning", "moe", "model-training", "huggingface", "natural-language-processing", "gpu", "linux"], "topics": ["llama", "llm", "mixture-of-experts", "moe", "continual-pre-training", "expert-partition"], "urls": [], "use_cases": ["convert a dense LLaMA model into a mixture-of-experts model", "continually pre-train an MoE LLM on my own dataset", "compare expert construction methods like clustering or co-activation graph partitioning", "train a small affordable sparse MoE model with top-K gating", "fine-tune an MoE language model with supervised fine-tuning", "monitor gate load and balance loss during MoE training"], "what_it_is": "LLaMA-MoE is a Python toolkit and model series for building Mixture-of-Experts (MoE) language models from dense LLaMA models via expert construction and continual pre-training. It provides multiple expert partitioning methods, gating strategies, and efficient training utilities with FlashAttention-v2 and streaming data loading.", "when_to_avoid": ["you need a production inference server rather than a training/research toolkit", "you lack multi-GPU resources for continual pre-training", "you want a general-purpose LLM fine-tuning framework without MoE specifics"], "when_to_choose": ["you want to build or study MoE models derived from existing dense LLMs", "you need a lightweight ~3.5B activated-parameter open model for research or deployment", "you want reproducible code from a published EMNLP 2024 paper on MoE construction"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/llama-moe", "repo": "pjlab-sys4nlp/llama-moe", "role": "main", "score": 19}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-09-03T02:15:16.915343+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T07:16:08.453454+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "fb75f77e7ac14855c0724930ca73071e741eb1a351e319bb0f5c193221197c61", "fetched_at": "2026-09-03T02:15:16.915343+00:00", "kind": "readme", "missing": false, "url": "https://github.com/pjlab-sys4nlp/llama-moe"}, {"content_hash": "ff7adda366dcb156cea28b7520d164896610aaf00fe63055f565907516bf9168", "fetched_at": "2026-08-29T13:14:17.741131+00:00", "kind": "homepage", "missing": false, "url": "https://arxiv.org/abs/2406.16554"}, {"content_hash": "cca9c3a11c56b1212864e03fb8a5511a3bdb6df53398ba4dd2ed778f931607dd", "fetched_at": "2026-08-29T13:14:17.743698+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/donate.html"}, {"content_hash": "47cbc55ff1deaca3f36b463373de863a7053d91cacf9f95725618e11610209ae", "fetched_at": "2026-08-29T13:14:17.746896+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/ourmembers.html"}, {"content_hash": "a1f16f915a9ad89ee57c3e929a1b6577d481f52c05f8015fc720b16ee8014f19", "fetched_at": "2026-08-29T13:14:17.748685+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about"}, {"content_hash": "b14a8d05a0ec337409ab63bffd91306b5317b16fac358aa6d1fe6afbaf3c8628", "fetched_at": "2026-08-29T13:14:17.745344+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/labs/index.html"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-09-03T02:15:16.915343+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T07:16:08.453454+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "fb75f77e7ac14855c0724930ca73071e741eb1a351e319bb0f5c193221197c61", "fetched_at": "2026-09-03T02:15:16.915343+00:00", "kind": "readme", "missing": false, "url": "https://github.com/pjlab-sys4nlp/llama-moe"}, {"content_hash": "ff7adda366dcb156cea28b7520d164896610aaf00fe63055f565907516bf9168", "fetched_at": "2026-08-29T13:14:17.741131+00:00", "kind": "homepage", "missing": false, "url": "https://arxiv.org/abs/2406.16554"}, {"content_hash": "cca9c3a11c56b1212864e03fb8a5511a3bdb6df53398ba4dd2ed778f931607dd", "fetched_at": "2026-08-29T13:14:17.743698+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/donate.html"}, {"content_hash": "47cbc55ff1deaca3f36b463373de863a7053d91cacf9f95725618e11610209ae", "fetched_at": "2026-08-29T13:14:17.746896+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/ourmembers.html"}, {"content_hash": "a1f16f915a9ad89ee57c3e929a1b6577d481f52c05f8015fc720b16ee8014f19", "fetched_at": "2026-08-29T13:14:17.748685+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about"}, {"content_hash": "b14a8d05a0ec337409ab63bffd91306b5317b16fac358aa6d1fe6afbaf3c8628", "fetched_at": "2026-08-29T13:14:17.745344+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/labs/index.html"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T07:16:08.453454+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "fb75f77e7ac14855c0724930ca73071e741eb1a351e319bb0f5c193221197c61", "fetched_at": "2026-09-03T02:15:16.915343+00:00", "kind": "readme", "missing": false, "url": "https://github.com/pjlab-sys4nlp/llama-moe"}, {"content_hash": "ff7adda366dcb156cea28b7520d164896610aaf00fe63055f565907516bf9168", "fetched_at": "2026-08-29T13:14:17.741131+00:00", "kind": "homepage", "missing": false, "url": "https://arxiv.org/abs/2406.16554"}, {"content_hash": "cca9c3a11c56b1212864e03fb8a5511a3bdb6df53398ba4dd2ed778f931607dd", "fetched_at": "2026-08-29T13:14:17.743698+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/donate.html"}, {"content_hash": "47cbc55ff1deaca3f36b463373de863a7053d91cacf9f95725618e11610209ae", "fetched_at": "2026-08-29T13:14:17.746896+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/ourmembers.html"}, {"content_hash": "a1f16f915a9ad89ee57c3e929a1b6577d481f52c05f8015fc720b16ee8014f19", "fetched_at": "2026-08-29T13:14:17.748685+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about"}, {"content_hash": "b14a8d05a0ec337409ab63bffd91306b5317b16fac358aa6d1fe6afbaf3c8628", "fetched_at": "2026-08-29T13:14:17.745344+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/labs/index.html"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-09-03T02:15:16.915343+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-09-03T02:15:16.915343+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-09-03T02:15:16.915343+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T07:16:08.453454+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "fb75f77e7ac14855c0724930ca73071e741eb1a351e319bb0f5c193221197c61", "fetched_at": "2026-09-03T02:15:16.915343+00:00", "kind": "readme", "missing": false, "url": "https://github.com/pjlab-sys4nlp/llama-moe"}, {"content_hash": "ff7adda366dcb156cea28b7520d164896610aaf00fe63055f565907516bf9168", "fetched_at": "2026-08-29T13:14:17.741131+00:00", "kind": "homepage", "missing": false, "url": "https://arxiv.org/abs/2406.16554"}, {"content_hash": "cca9c3a11c56b1212864e03fb8a5511a3bdb6df53398ba4dd2ed778f931607dd", "fetched_at": "2026-08-29T13:14:17.743698+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/donate.html"}, {"content_hash": "47cbc55ff1deaca3f36b463373de863a7053d91cacf9f95725618e11610209ae", "fetched_at": "2026-08-29T13:14:17.746896+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/ourmembers.html"}, {"content_hash": "a1f16f915a9ad89ee57c3e929a1b6577d481f52c05f8015fc720b16ee8014f19", "fetched_at": "2026-08-29T13:14:17.748685+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about"}, {"content_hash": "b14a8d05a0ec337409ab63bffd91306b5317b16fac358aa6d1fe6afbaf3c8628", "fetched_at": "2026-08-29T13:14:17.745344+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/labs/index.html"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-09-03T02:15:16.915343+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-09-03T02:15:16.915343+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T07:16:08.453454+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "fb75f77e7ac14855c0724930ca73071e741eb1a351e319bb0f5c193221197c61", "fetched_at": "2026-09-03T02:15:16.915343+00:00", "kind": "readme", "missing": false, "url": "https://github.com/pjlab-sys4nlp/llama-moe"}, {"content_hash": "ff7adda366dcb156cea28b7520d164896610aaf00fe63055f565907516bf9168", "fetched_at": "2026-08-29T13:14:17.741131+00:00", "kind": "homepage", "missing": false, "url": "https://arxiv.org/abs/2406.16554"}, {"content_hash": "cca9c3a11c56b1212864e03fb8a5511a3bdb6df53398ba4dd2ed778f931607dd", "fetched_at": "2026-08-29T13:14:17.743698+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/donate.html"}, {"content_hash": "47cbc55ff1deaca3f36b463373de863a7053d91cacf9f95725618e11610209ae", "fetched_at": "2026-08-29T13:14:17.746896+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/ourmembers.html"}, {"content_hash": "a1f16f915a9ad89ee57c3e929a1b6577d481f52c05f8015fc720b16ee8014f19", "fetched_at": "2026-08-29T13:14:17.748685+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about"}, {"content_hash": "b14a8d05a0ec337409ab63bffd91306b5317b16fac358aa6d1fe6afbaf3c8628", "fetched_at": "2026-08-29T13:14:17.745344+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/labs/index.html"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-09-03T02:15:16.915343+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-09-03T02:15:16.915343+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-09-03T02:15:16.915343+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T07:16:08.453454+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "fb75f77e7ac14855c0724930ca73071e741eb1a351e319bb0f5c193221197c61", "fetched_at": "2026-09-03T02:15:16.915343+00:00", "kind": "readme", "missing": false, "url": "https://github.com/pjlab-sys4nlp/llama-moe"}, {"content_hash": "ff7adda366dcb156cea28b7520d164896610aaf00fe63055f565907516bf9168", "fetched_at": "2026-08-29T13:14:17.741131+00:00", "kind": "homepage", "missing": false, "url": "https://arxiv.org/abs/2406.16554"}, {"content_hash": "cca9c3a11c56b1212864e03fb8a5511a3bdb6df53398ba4dd2ed778f931607dd", "fetched_at": "2026-08-29T13:14:17.743698+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/donate.html"}, {"content_hash": "47cbc55ff1deaca3f36b463373de863a7053d91cacf9f95725618e11610209ae", "fetched_at": "2026-08-29T13:14:17.746896+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/ourmembers.html"}, {"content_hash": "a1f16f915a9ad89ee57c3e929a1b6577d481f52c05f8015fc720b16ee8014f19", "fetched_at": "2026-08-29T13:14:17.748685+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about"}, {"content_hash": "b14a8d05a0ec337409ab63bffd91306b5317b16fac358aa6d1fe6afbaf3c8628", "fetched_at": "2026-08-29T13:14:17.745344+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/labs/index.html"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-09-03T02:15:16.915343+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-09-03T02:15:16.915343+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T07:16:08.453454+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "fb75f77e7ac14855c0724930ca73071e741eb1a351e319bb0f5c193221197c61", "fetched_at": "2026-09-03T02:15:16.915343+00:00", "kind": "readme", "missing": false, "url": "https://github.com/pjlab-sys4nlp/llama-moe"}, {"content_hash": "ff7adda366dcb156cea28b7520d164896610aaf00fe63055f565907516bf9168", "fetched_at": "2026-08-29T13:14:17.741131+00:00", "kind": "homepage", "missing": false, "url": "https://arxiv.org/abs/2406.16554"}, {"content_hash": "cca9c3a11c56b1212864e03fb8a5511a3bdb6df53398ba4dd2ed778f931607dd", "fetched_at": "2026-08-29T13:14:17.743698+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/donate.html"}, {"content_hash": "47cbc55ff1deaca3f36b463373de863a7053d91cacf9f95725618e11610209ae", "fetched_at": "2026-08-29T13:14:17.746896+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/ourmembers.html"}, {"content_hash": "a1f16f915a9ad89ee57c3e929a1b6577d481f52c05f8015fc720b16ee8014f19", "fetched_at": "2026-08-29T13:14:17.748685+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about"}, {"content_hash": "b14a8d05a0ec337409ab63bffd91306b5317b16fac358aa6d1fe6afbaf3c8628", "fetched_at": "2026-08-29T13:14:17.745344+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/labs/index.html"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T07:16:08.453454+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "fb75f77e7ac14855c0724930ca73071e741eb1a351e319bb0f5c193221197c61", "fetched_at": "2026-09-03T02:15:16.915343+00:00", "kind": "readme", "missing": false, "url": "https://github.com/pjlab-sys4nlp/llama-moe"}, {"content_hash": "ff7adda366dcb156cea28b7520d164896610aaf00fe63055f565907516bf9168", "fetched_at": "2026-08-29T13:14:17.741131+00:00", "kind": "homepage", "missing": false, "url": "https://arxiv.org/abs/2406.16554"}, {"content_hash": "cca9c3a11c56b1212864e03fb8a5511a3bdb6df53398ba4dd2ed778f931607dd", "fetched_at": "2026-08-29T13:14:17.743698+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/donate.html"}, {"content_hash": "47cbc55ff1deaca3f36b463373de863a7053d91cacf9f95725618e11610209ae", "fetched_at": "2026-08-29T13:14:17.746896+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/ourmembers.html"}, {"content_hash": "a1f16f915a9ad89ee57c3e929a1b6577d481f52c05f8015fc720b16ee8014f19", "fetched_at": "2026-08-29T13:14:17.748685+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about"}, {"content_hash": "b14a8d05a0ec337409ab63bffd91306b5317b16fac358aa6d1fe6afbaf3c8628", "fetched_at": "2026-08-29T13:14:17.745344+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/labs/index.html"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T07:16:08.453454+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "fb75f77e7ac14855c0724930ca73071e741eb1a351e319bb0f5c193221197c61", "fetched_at": "2026-09-03T02:15:16.915343+00:00", "kind": "readme", "missing": false, "url": "https://github.com/pjlab-sys4nlp/llama-moe"}, {"content_hash": "ff7adda366dcb156cea28b7520d164896610aaf00fe63055f565907516bf9168", "fetched_at": "2026-08-29T13:14:17.741131+00:00", "kind": "homepage", "missing": false, "url": "https://arxiv.org/abs/2406.16554"}, {"content_hash": "cca9c3a11c56b1212864e03fb8a5511a3bdb6df53398ba4dd2ed778f931607dd", "fetched_at": "2026-08-29T13:14:17.743698+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/donate.html"}, {"content_hash": "47cbc55ff1deaca3f36b463373de863a7053d91cacf9f95725618e11610209ae", "fetched_at": "2026-08-29T13:14:17.746896+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/ourmembers.html"}, {"content_hash": "a1f16f915a9ad89ee57c3e929a1b6577d481f52c05f8015fc720b16ee8014f19", "fetched_at": "2026-08-29T13:14:17.748685+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about"}, {"content_hash": "b14a8d05a0ec337409ab63bffd91306b5317b16fac358aa6d1fe6afbaf3c8628", "fetched_at": "2026-08-29T13:14:17.745344+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/labs/index.html"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T07:16:08.453454+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "fb75f77e7ac14855c0724930ca73071e741eb1a351e319bb0f5c193221197c61", "fetched_at": "2026-09-03T02:15:16.915343+00:00", "kind": "readme", "missing": false, "url": "https://github.com/pjlab-sys4nlp/llama-moe"}, {"content_hash": "ff7adda366dcb156cea28b7520d164896610aaf00fe63055f565907516bf9168", "fetched_at": "2026-08-29T13:14:17.741131+00:00", "kind": "homepage", "missing": false, "url": "https://arxiv.org/abs/2406.16554"}, {"content_hash": "cca9c3a11c56b1212864e03fb8a5511a3bdb6df53398ba4dd2ed778f931607dd", "fetched_at": "2026-08-29T13:14:17.743698+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/donate.html"}, {"content_hash": "47cbc55ff1deaca3f36b463373de863a7053d91cacf9f95725618e11610209ae", "fetched_at": "2026-08-29T13:14:17.746896+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/ourmembers.html"}, {"content_hash": "a1f16f915a9ad89ee57c3e929a1b6577d481f52c05f8015fc720b16ee8014f19", "fetched_at": "2026-08-29T13:14:17.748685+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about"}, {"content_hash": "b14a8d05a0ec337409ab63bffd91306b5317b16fac358aa6d1fe6afbaf3c8628", "fetched_at": "2026-08-29T13:14:17.745344+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/labs/index.html"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 0, "longevity": 81, "rhythm": 8}, "computed_at": "2026-09-02T17:46:02.011165+00:00", "flags": [], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 1136, "days_push": 635, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 19, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 3, "stale_scrape": false}}