{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/code/get-c4","entry":"get_c4","source":"Syntology graph, per-sample; not an archive number","read_at":"2026-09-24T18:15:14+00:00","claim":"Names are grouped by exact entry-name string. Same-named routines are NOT asserted to be equivalent; 'ran' means executed on a synthesized fixture, not correctness. n_samples_ran = sum of by_status over every status except 'unverified' (ran_draft_wrong and ran_fixture are failures of Syntology's instrument, not of the code); n_papers_ran = papers with at least one such sample.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"n_papers":41,"n_papers_ran":3,"units":"n_samples, n_samples_ran, n_samples_fingerprinted and by_status count distinct code bodies (code_sha256); n_places and n_places_pointer_only count places, one per (paper, code body) pair, which is also the unit of the samples list","n_samples":34,"n_samples_ran":2,"n_samples_fingerprinted":0,"n_places":46,"n_places_pointer_only":16,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":2,"unverified":32},"syntology":{"atlas_url":null,"mcp":null,"mcp_per_sample":{"tool":"get_code","arguments_in":"samples[].mcp_get_code"},"developers":"https://syntology.ai/developers"},"samples":[{"arxiv_id":"2601.06787","paper":"/paper/arxiv-2601-06787","title":"Garbage Attention in Large Language Models: <BOS> Sink Heads and Sink-aware Pruning","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"CASIA-LMC-Lab/FLAP","path":"lib/prune.py","file_url":"https://github.com/CASIA-LMC-Lab/FLAP/blob/HEAD/lib/prune.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"6ccf0fe3fd4574d5","mcp_get_code":{"code_sha256":"6ccf0fe3fd4574d5"}},{"arxiv_id":"2511.04805","paper":"/paper/arxiv-2511-04805","title":"PuzzleMoE: Efficient Compression of Large Mixture-of-Experts Models via Fine-Grained Expert Merging and Bit-packed Inference","date":null,"month_inferred_from_arxiv_id":"2025-11","title_source":"syntology","repo":"Supercomputing-System-AI-Lab/PuzzleMoE","path":"puzzlemoe/utils/merge_experts_function.py","file_url":"https://github.com/Supercomputing-System-AI-Lab/PuzzleMoE/blob/HEAD/puzzlemoe/utils/merge_experts_function.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"60d24b07d3b90b7c","mcp_get_code":{"code_sha256":"60d24b07d3b90b7c"}},{"arxiv_id":"2507.23279","paper":null,"title":"arXiv:2507.23279","date":null,"month_inferred_from_arxiv_id":"2025-07","title_source":null,"repo":"ZunhaiSu/Super-Experts-Profilling","path":"data_utils.py","file_url":"https://github.com/ZunhaiSu/Super-Experts-Profilling/blob/HEAD/data_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"709a6f261dbed787","mcp_get_code":{"code_sha256":"709a6f261dbed787"}},{"arxiv_id":"2506.09351","paper":null,"title":"arXiv:2506.09351","date":null,"month_inferred_from_arxiv_id":"2025-06","title_source":null,"repo":"yuchenblah/DIVE","path":"prune/lib/calidata_random.py","file_url":"https://github.com/yuchenblah/DIVE/blob/HEAD/prune/lib/calidata_random.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"92ee6796edcd33e1","mcp_get_code":{"code_sha256":"92ee6796edcd33e1"}},{"arxiv_id":"2506.09351","paper":null,"title":"arXiv:2506.09351","date":null,"month_inferred_from_arxiv_id":"2025-06","title_source":null,"repo":"yuchenblah/DIVE","path":"prune/lib/calidata_select_8.py","file_url":"https://github.com/yuchenblah/DIVE/blob/HEAD/prune/lib/calidata_select_8.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"fe56cd1859314741","mcp_get_code":{"code_sha256":"fe56cd1859314741"}},{"arxiv_id":"2506.06866","paper":"/paper/safe-finding-sparse-and-flat-minima-to","title":"SAFE: Finding Sparse and Flat Minima to Improve Pruning","date":"2025-06-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"LOG-postech/safe-torch","path":"language/lib/prune.py","file_url":"https://github.com/LOG-postech/safe-torch/blob/HEAD/language/lib/prune.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"d53a6dae4f8104ea","mcp_get_code":{"code_sha256":"d53a6dae4f8104ea"}},{"arxiv_id":"2505.23807","paper":"/paper/dlp-dynamic-layerwise-pruning-in-large","title":"DLP: Dynamic Layerwise Pruning in Large Language Models","date":"2025-05-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ironartisan/dlp","path":"lib/prune.py","file_url":"https://github.com/ironartisan/dlp/blob/HEAD/lib/prune.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"c668683d68ff5099","mcp_get_code":{"code_sha256":"c668683d68ff5099"}},{"arxiv_id":"2411.10606","paper":"/paper/amoeballm-constructing-any-shape-large","title":"AmoebaLLM: Constructing Any-Shape Large Language Models for Efficient and Instant Deployment","date":"2024-11-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"GATECH-EIC/AmoebaLLM","path":"width_shrink/data.py","file_url":"https://github.com/GATECH-EIC/AmoebaLLM/blob/HEAD/width_shrink/data.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"7630a157a3b32ab9","mcp_get_code":{"code_sha256":"7630a157a3b32ab9"}},{"arxiv_id":"2410.17509","paper":"/paper/wagle-strategic-weight-attribution-for","title":"WAGLE: Strategic Weight Attribution for Effective and Modular Unlearning in Large Language Models","date":"2024-10-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"OPTML-Group/WAGLE","path":"src/dataset/dataset.py","file_url":"https://github.com/OPTML-Group/WAGLE/blob/HEAD/src/dataset/dataset.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"7630a157a3b32ab9","mcp_get_code":{"code_sha256":"7630a157a3b32ab9"}},{"arxiv_id":"2410.13229","paper":"/paper/quamba-a-post-training-quantization-recipe","title":"Quamba: A Post-Training Quantization Recipe for Selective State Space Models","date":"2024-10-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"enyac-group/quamba","path":"quamba/data_loaders.py","file_url":"https://github.com/enyac-group/quamba/blob/HEAD/quamba/data_loaders.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"eb9d2957b3161128","mcp_get_code":{"code_sha256":"eb9d2957b3161128"}},{"arxiv_id":"2410.09615","paper":"/paper/slim-one-shot-quantized-sparse-plus-low-rank","title":"SLiM: One-shot Quantization and Sparsity with Low-rank Approximation for LLM Weight Compression","date":"2024-10-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mohammad-mozaffari/slim","path":"slim/data.py","file_url":"https://github.com/mohammad-mozaffari/slim/blob/HEAD/slim/data.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ddc3bcb5e5b4ab8d","mcp_get_code":{"code_sha256":"ddc3bcb5e5b4ab8d"}},{"arxiv_id":"2409.17481","paper":"/paper/maskllm-learnable-semi-structured-sparsity","title":"MaskLLM: Learnable Semi-Structured Sparsity for Large Language Models","date":"2024-09-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"NVlabs/MaskLLM","path":"eval_llama_ppl.py","file_url":"https://github.com/NVlabs/MaskLLM/blob/HEAD/eval_llama_ppl.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"7630a157a3b32ab9","mcp_get_code":{"code_sha256":"7630a157a3b32ab9"}},{"arxiv_id":"2407.11062","paper":"/paper/efficientqat-efficient-quantization-aware","title":"EfficientQAT: Efficient Quantization-Aware Training for Large Language Models","date":"2024-07-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"opengvlab/efficientqat","path":"datautils_block.py","file_url":"https://github.com/opengvlab/efficientqat/blob/HEAD/datautils_block.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"2d9448699cce6e63","mcp_get_code":{"code_sha256":"2d9448699cce6e63"}},{"arxiv_id":"2407.10032","paper":"/paper/leanquant-accurate-large-language-model","title":"LeanQuant: Accurate Large Language Model Quantization with Loss-Error-Aware Grid","date":"2024-07-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"LeanModels/LeanQuant","path":"datautils.py","file_url":"https://github.com/LeanModels/LeanQuant/blob/HEAD/datautils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"86ac8f1de9c0550b","mcp_get_code":{"code_sha256":"86ac8f1de9c0550b"}},{"arxiv_id":"2407.06483","paper":"/paper/composable-interventions-for-language-models","title":"Composable Interventions for Language Models","date":"2024-07-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hartvigsen-group/composable-interventions","path":"sparsellm/lib/data.py","file_url":"https://github.com/hartvigsen-group/composable-interventions/blob/HEAD/sparsellm/lib/data.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"823f33725cd8f75d","mcp_get_code":{"code_sha256":"823f33725cd8f75d"}},{"arxiv_id":"2407.06483","paper":"/paper/composable-interventions-for-language-models","title":"Composable Interventions for Language Models","date":"2024-07-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hartvigsen-group/composable-interventions","path":"sparsellm/lib/datautils.py","file_url":"https://github.com/hartvigsen-group/composable-interventions/blob/HEAD/sparsellm/lib/datautils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"1ebe223f71f863bc","mcp_get_code":{"code_sha256":"1ebe223f71f863bc"}},{"arxiv_id":"2407.05563","paper":"/paper/llmbox-a-comprehensive-library-for-large","title":"LLMBox: A Comprehensive Library for Large Language Models","date":"2024-07-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"RUCAIBox/LLMBox","path":"training/gptq.py","file_url":"https://github.com/RUCAIBox/LLMBox/blob/HEAD/training/gptq.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3a8ad8ccd4b56839","mcp_get_code":{"code_sha256":"3a8ad8ccd4b56839"}},{"arxiv_id":"2406.15524","paper":"/paper/rethinking-pruning-large-language-models","title":"Rethinking Pruning Large Language Models: Benefits and Pitfalls of Reconstruction Error Minimization","date":"2024-06-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"log-postech/rethinking-llm-pruning","path":"lib/data.py","file_url":"https://github.com/log-postech/rethinking-llm-pruning/blob/HEAD/lib/data.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"112fa6e5a362cc14","mcp_get_code":{"code_sha256":"112fa6e5a362cc14"}},{"arxiv_id":"2406.12928","paper":"/paper/evaluating-the-generalization-ability-of-1","title":"Evaluating the Generalization Ability of Quantized LLMs: Benchmark, Analysis, and Toolbox","date":"2024-06-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tsingmaoai/mi-optimize","path":"mi_optimize/datasets/data_loader.py","file_url":"https://github.com/tsingmaoai/mi-optimize/blob/HEAD/mi_optimize/datasets/data_loader.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"0f169d61e5b5e02a","mcp_get_code":{"code_sha256":"0f169d61e5b5e02a"}},{"arxiv_id":"2406.05981","paper":"/paper/shiftaddllm-accelerating-pretrained-llms-via","title":"ShiftAddLLM: Accelerating Pretrained LLMs via Post-Training Multiplication-Less Reparameterization","date":"2024-06-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"gatech-eic/shiftaddllm","path":"datautils.py","file_url":"https://github.com/gatech-eic/shiftaddllm/blob/HEAD/datautils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"3b7f82daf1a2f6d5","mcp_get_code":{"code_sha256":"3b7f82daf1a2f6d5"}},{"arxiv_id":"2406.02924","paper":"/paper/pruner-zero-evolving-symbolic-pruning-metric","title":"Pruner-Zero: Evolving Symbolic Pruning Metric from scratch for Large Language Models","date":"2024-06-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"pprp/pruner-zero","path":"lib/data.py","file_url":"https://github.com/pprp/pruner-zero/blob/HEAD/lib/data.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a271ec700d8df453","mcp_get_code":{"code_sha256":"a271ec700d8df453"}},{"arxiv_id":"2404.18239","paper":"/paper/soul-unlocking-the-power-of-second-order","title":"SOUL: Unlocking the Power of Second-Order Optimization for LLM Unlearning","date":"2024-04-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"optml-group/soul","path":"src/dataset/dataset.py","file_url":"https://github.com/optml-group/soul/blob/HEAD/src/dataset/dataset.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"7630a157a3b32ab9","mcp_get_code":{"code_sha256":"7630a157a3b32ab9"}},{"arxiv_id":"2403.06082","paper":"/paper/framequant-flexible-low-bit-quantization-for","title":"FrameQuant: Flexible Low-Bit Quantization for Transformers","date":"2024-03-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"vsingh-group/framequant","path":"datautils.py","file_url":"https://github.com/vsingh-group/framequant/blob/HEAD/datautils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"4d29e98e5f0e4149","mcp_get_code":{"code_sha256":"4d29e98e5f0e4149"}},{"arxiv_id":"2402.16880","paper":"/paper/besa-pruning-large-language-models-with","title":"BESA: Pruning Large Language Models with Blockwise Parameter-Efficient Sparsity Allocation","date":"2024-02-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"linkanonymous/besa","path":"utils/data.py","file_url":"https://github.com/linkanonymous/besa/blob/HEAD/utils/data.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"51a53fa33d2d9a6f","mcp_get_code":{"code_sha256":"51a53fa33d2d9a6f"}},{"arxiv_id":"2402.09398","paper":"/paper/get-more-with-less-synthesizing-recurrence","title":"Get More with LESS: Synthesizing Recurrence with KV Cache Compression for Efficient LLM Inference","date":"2024-02-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hdong920/less","path":"src/data_processing.py","file_url":"https://github.com/hdong920/less/blob/HEAD/src/data_processing.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e17b6c1ff661e9bd","mcp_get_code":{"code_sha256":"e17b6c1ff661e9bd"}},{"arxiv_id":"2401.02938","paper":"/paper/fast-and-optimal-weight-update-for-pruned","title":"Fast and Effective Weight Update for Pruned Large Language Models","date":"2024-01-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"fmfi-compbio/admm-pruning","path":"lib/data.py","file_url":"https://github.com/fmfi-compbio/admm-pruning/blob/HEAD/lib/data.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"112fa6e5a362cc14","mcp_get_code":{"code_sha256":"112fa6e5a362cc14"}},{"arxiv_id":"2312.17244","paper":"/paper/the-llm-surgeon","title":"The LLM Surgeon","date":"2023-12-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"qualcomm-ai-research/llm-surgeon","path":"datautils.py","file_url":"https://github.com/qualcomm-ai-research/llm-surgeon/blob/HEAD/datautils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause-Clear","inline_ok":false,"code_sha256_prefix":"4b6dab2040cdb423","mcp_get_code":{"code_sha256":"4b6dab2040cdb423"}},{"arxiv_id":"2312.11983","paper":"/paper/fluctuation-based-adaptive-structured-pruning","title":"Fluctuation-based Adaptive Structured Pruning for Large Language Models","date":"2023-12-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"casia-iva-lab/flap","path":"lib/data.py","file_url":"https://github.com/casia-iva-lab/flap/blob/HEAD/lib/data.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"6ccf0fe3fd4574d5","mcp_get_code":{"code_sha256":"6ccf0fe3fd4574d5"}},{"arxiv_id":"2311.04902","paper":"/paper/beyond-size-how-gradients-shape-pruning","title":"Beyond Size: How Gradients Shape Pruning Decisions in Large Language Models","date":"2023-11-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"rocktimjyotidas/gblm-pruner","path":"gradient_computation.py","file_url":"https://github.com/rocktimjyotidas/gblm-pruner/blob/HEAD/gradient_computation.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"362bd8bd1eddbfc5","mcp_get_code":{"code_sha256":"362bd8bd1eddbfc5"}},{"arxiv_id":"2311.04902","paper":"/paper/beyond-size-how-gradients-shape-pruning","title":"Beyond Size: How Gradients Shape Pruning Decisions in Large Language Models","date":"2023-11-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"rocktimjyotidas/gblm-pruner","path":"lib/data.py","file_url":"https://github.com/rocktimjyotidas/gblm-pruner/blob/HEAD/lib/data.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"5cbbb830025b49e7","mcp_get_code":{"code_sha256":"5cbbb830025b49e7"}},{"arxiv_id":"2310.19102","paper":"/paper/atom-low-bit-quantization-for-efficient-and","title":"Atom: Low-bit Quantization for Efficient and Accurate LLM Serving","date":"2023-10-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"efeslab/atom","path":"model/datautils.py","file_url":"https://github.com/efeslab/atom/blob/HEAD/model/datautils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"eb9d2957b3161128","mcp_get_code":{"code_sha256":"eb9d2957b3161128"}},{"arxiv_id":"2310.09259","paper":"/paper/towards-end-to-end-4-bit-inference-on","title":"QUIK: Towards End-to-End 4-Bit Inference on Generative Large Language Models","date":"2023-10-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ist-daslab/quik","path":"experiments/datautils.py","file_url":"https://github.com/ist-daslab/quik/blob/HEAD/experiments/datautils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"980b7a8e42ae4a52","mcp_get_code":{"code_sha256":"980b7a8e42ae4a52"}},{"arxiv_id":"2310.08915","paper":"/paper/dynamic-sparse-no-training-training-free-fine","title":"Dynamic Sparse No Training: Training-Free Fine-tuning for Sparse LLMs","date":"2023-10-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zyxxmu/dsnot","path":"lib/prune.py","file_url":"https://github.com/zyxxmu/dsnot/blob/HEAD/lib/prune.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"7630a157a3b32ab9","mcp_get_code":{"code_sha256":"7630a157a3b32ab9"}},{"arxiv_id":"2310.01382","paper":"/paper/compressing-llms-the-truth-is-rarely-pure-and","title":"Compressing LLMs: The Truth is Rarely Pure and Never Simple","date":"2023-10-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"VITA-Group/llm-kick","path":"GPTQ_experiment/lib/data.py","file_url":"https://github.com/VITA-Group/llm-kick/blob/HEAD/GPTQ_experiment/lib/data.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"c00c627524c6a86f","mcp_get_code":{"code_sha256":"c00c627524c6a86f"}},{"arxiv_id":"2307.15290","paper":"/paper/chathome-development-and-evaluation-of-a","title":"ChatHome: Development and Evaluation of a Domain-Specific Language Model for Home Renovation","date":"2023-07-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lianjiatech/belle","path":"models/gptq/datautils.py","file_url":"https://github.com/lianjiatech/belle/blob/HEAD/models/gptq/datautils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"91dba77fa391e15e","mcp_get_code":{"code_sha256":"91dba77fa391e15e"}},{"arxiv_id":"2307.09288","paper":"/paper/llama-2-open-foundation-and-fine-tuned-chat","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","date":"2023-07-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"squeezeailab/squeezellm","path":"squeezellm/datautils.py","file_url":"https://github.com/squeezeailab/squeezellm/blob/HEAD/squeezellm/datautils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"92dc709e4e73e133","mcp_get_code":{"code_sha256":"92dc709e4e73e133"}},{"arxiv_id":"2306.11695","paper":"/paper/a-simple-and-effective-pruning-approach-for","title":"A Simple and Effective Pruning Approach for Large Language Models","date":"2023-06-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"crystaleye42/eval-safety","path":"lib/prune.py","file_url":"https://github.com/crystaleye42/eval-safety/blob/HEAD/lib/prune.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9660cb0c932e836e","mcp_get_code":{"code_sha256":"9660cb0c932e836e"}},{"arxiv_id":"2306.11695","paper":"/paper/a-simple-and-effective-pruning-approach-for","title":"A Simple and Effective Pruning Approach for Large Language Models","date":"2023-06-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"qiaoxiao7282/seft","path":"lib/prune_all.py","file_url":"https://github.com/qiaoxiao7282/seft/blob/HEAD/lib/prune_all.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"112fa6e5a362cc14","mcp_get_code":{"code_sha256":"112fa6e5a362cc14"}},{"arxiv_id":"2306.11695","paper":"/paper/a-simple-and-effective-pruning-approach-for","title":"A Simple and Effective Pruning Approach for Large Language Models","date":"2023-06-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"locuslab/wanda","path":"lib/prune.py","file_url":"https://github.com/locuslab/wanda/blob/HEAD/lib/prune.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"5a7a61a0235b3907","mcp_get_code":{"code_sha256":"5a7a61a0235b3907"}},{"arxiv_id":"2304.01089","paper":"/paper/rptq-reorder-based-post-training-quantization","title":"RPTQ: Reorder-based Post-training Quantization for Large Language Models","date":"2023-04-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hahnyuan/rptq4llm","path":"datautils.py","file_url":"https://github.com/hahnyuan/rptq4llm/blob/HEAD/datautils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a7b3cccc9ad0d188","mcp_get_code":{"code_sha256":"a7b3cccc9ad0d188"}},{"arxiv_id":"openreview_d3RFDLBw01","paper":null,"title":"arXiv:openreview_d3RFDLBw01","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"AI2C-Lab/STLA","path":"data_utils.py","file_url":"https://github.com/AI2C-Lab/STLA/blob/HEAD/data_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"3e8381ec040b34cc","mcp_get_code":{"code_sha256":"3e8381ec040b34cc"}},{"arxiv_id":"openreview_4iupzej9nT","paper":null,"title":"arXiv:openreview_4iupzej9nT","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"hikvision-research/STEP","path":"step/lib/data.py","file_url":"https://github.com/hikvision-research/STEP/blob/HEAD/step/lib/data.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"49637fd9dbf67223","mcp_get_code":{"code_sha256":"49637fd9dbf67223"}},{"arxiv_id":"aaai_28960","paper":null,"title":"arXiv:aaai_28960","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"CASIA-IVA-Lab/FLAP","path":"lib/data.py","file_url":"https://github.com/CASIA-IVA-Lab/FLAP/blob/HEAD/lib/data.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"6ccf0fe3fd4574d5","mcp_get_code":{"code_sha256":"6ccf0fe3fd4574d5"}},{"arxiv_id":"2025.acl-long.498","paper":null,"title":"arXiv:2025.acl-long.498","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"OpenGVLab/EfficientQAT","path":"datautils_block.py","file_url":"https://github.com/OpenGVLab/EfficientQAT/blob/HEAD/datautils_block.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"2d9448699cce6e63","mcp_get_code":{"code_sha256":"2d9448699cce6e63"}},{"arxiv_id":"2024.findings-naacl.145","paper":null,"title":"arXiv:2024.findings-naacl.145","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"LianjiaTech/BELLE","path":"models/gptq/datautils.py","file_url":"https://github.com/LianjiaTech/BELLE/blob/HEAD/models/gptq/datautils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"91dba77fa391e15e","mcp_get_code":{"code_sha256":"91dba77fa391e15e"}},{"arxiv_id":"2024.findings-emnlp.579","paper":null,"title":"arXiv:2024.findings-emnlp.579","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"RazvanDu/DynamicSlicing","path":"src/slicegpt/data.lib.py","file_url":"https://github.com/RazvanDu/DynamicSlicing/blob/HEAD/src/slicegpt/data.lib.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"7630a157a3b32ab9","mcp_get_code":{"code_sha256":"7630a157a3b32ab9"}}]}