{"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-llama","entry":"get_llama","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":21,"n_papers_ran":14,"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":13,"n_samples_ran":5,"n_samples_fingerprinted":0,"n_places":22,"n_places_pointer_only":10,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":4,"ran_fixture":0,"ran":1,"unverified":8},"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":"2505.23049","paper":"/paper/denoiserotator-enhance-pruning-robustness-for","title":"DenoiseRotator: Enhance Pruning Robustness for LLMs via Importance Concentration","date":"2025-05-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"axel-gu/denoiserotator","path":"llama_prune.py","file_url":"https://github.com/axel-gu/denoiserotator/blob/HEAD/llama_prune.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OPAQUE_PARAMS","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"708c67f2479aa444","mcp_get_code":{"code_sha256":"708c67f2479aa444"}},{"arxiv_id":"2412.11041","paper":"/paper/separate-the-wheat-from-the-chaff-a-post-hoc","title":"Separate the Wheat from the Chaff: A Post-Hoc Approach to Safety Re-Alignment for Fine-Tuned Language Models","date":"2024-12-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"pikepokenew/IRR","path":"IRR/llama.py","file_url":"https://github.com/pikepokenew/IRR/blob/HEAD/IRR/llama.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"99abb5717e4763c2","mcp_get_code":{"code_sha256":"99abb5717e4763c2"}},{"arxiv_id":"2411.05282","paper":"/paper/microscopiq-accelerating-foundational-models","title":"MicroScopiQ: Accelerating Foundational Models through Outlier-Aware Microscaling Quantization","date":"2024-11-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"georgia-tech-synergy-lab/microscopiq-llm-quantization","path":"llm/llama.py","file_url":"https://github.com/georgia-tech-synergy-lab/microscopiq-llm-quantization/blob/HEAD/llm/llama.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"d1d25542bf6a73b0","mcp_get_code":{"code_sha256":"d1d25542bf6a73b0"}},{"arxiv_id":"2409.18850","paper":"/paper/two-sparse-matrices-are-better-than-one","title":"Two Sparse Matrices are Better than One: Sparsifying Neural Networks with Double Sparse Factorization","date":"2024-09-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"usamec/double_sparse","path":"llama.py","file_url":"https://github.com/usamec/double_sparse/blob/HEAD/llama.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":"bf5b0ce87ee19903","mcp_get_code":{"code_sha256":"bf5b0ce87ee19903"}},{"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":"llama.py","file_url":"https://github.com/LeanModels/LeanQuant/blob/HEAD/llama.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"9c16d58cb9509ae5","mcp_get_code":{"code_sha256":"9c16d58cb9509ae5"}},{"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":"llama_analysis.py","file_url":"https://github.com/gatech-eic/shiftaddllm/blob/HEAD/llama_analysis.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"88d590323ed219c8","mcp_get_code":{"code_sha256":"88d590323ed219c8"}},{"arxiv_id":"2406.00800","paper":"/paper/magr-weight-magnitude-reduction-for-enhancing","title":"MagR: Weight Magnitude Reduction for Enhancing Post-Training Quantization","date":"2024-06-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"aozhongzhang/magr","path":"llama.py","file_url":"https://github.com/aozhongzhang/magr/blob/HEAD/llama.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"88d590323ed219c8","mcp_get_code":{"code_sha256":"88d590323ed219c8"}},{"arxiv_id":"2405.15756","paper":"/paper/sparse-expansion-and-neuronal-disentanglement","title":"Sparse Expansion and Neuronal Disentanglement","date":"2024-05-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"shavit-lab/sparse-expansion","path":"utils/modelutils.py","file_url":"https://github.com/shavit-lab/sparse-expansion/blob/HEAD/utils/modelutils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c6dd03f3342d1724","mcp_get_code":{"code_sha256":"c6dd03f3342d1724"}},{"arxiv_id":"2404.14047","paper":"/paper/how-good-are-low-bit-quantized-llama3-models","title":"An empirical study of LLaMA3 quantization: from LLMs to MLLMs","date":"2024-04-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"macaronlin/llama3-quantization","path":"llama.py","file_url":"https://github.com/macaronlin/llama3-quantization/blob/HEAD/llama.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"2c201f017173954b","mcp_get_code":{"code_sha256":"2c201f017173954b"}},{"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":"llama.py","file_url":"https://github.com/vsingh-group/framequant/blob/HEAD/llama.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"7ca52cb5d1719b2f","mcp_get_code":{"code_sha256":"7ca52cb5d1719b2f"}},{"arxiv_id":"2402.17946","paper":"/paper/gradient-free-adaptive-global-pruning-for-pre","title":"SparseLLM: Towards Global Pruning for Pre-trained Language Models","date":"2024-02-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"BaiTheBest/SparseLLM","path":"model_utils.py","file_url":"https://github.com/BaiTheBest/SparseLLM/blob/HEAD/model_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":"0ac474c6b7daab48","mcp_get_code":{"code_sha256":"0ac474c6b7daab48"}},{"arxiv_id":"2312.05693","paper":"/paper/agile-quant-activation-guided-quantization","title":"Agile-Quant: Activation-Guided Quantization for Faster Inference of LLMs on the Edge","date":"2023-12-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"shawnricecake/agile-quant","path":"gptq_fq_quant_llama.py","file_url":"https://github.com/shawnricecake/agile-quant/blob/HEAD/gptq_fq_quant_llama.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"2c201f017173954b","mcp_get_code":{"code_sha256":"2c201f017173954b"}},{"arxiv_id":"2310.09499","paper":"/paper/one-shot-sensitivity-aware-mixed-sparsity","title":"One-Shot Sensitivity-Aware Mixed Sparsity Pruning for Large Language Models","date":"2023-10-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"talkking/MixGPT","path":"llama.py","file_url":"https://github.com/talkking/MixGPT/blob/HEAD/llama.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"88d590323ed219c8","mcp_get_code":{"code_sha256":"88d590323ed219c8"}},{"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/llama.py","file_url":"https://github.com/VITA-Group/llm-kick/blob/HEAD/GPTQ_experiment/llama.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"2c201f017173954b","mcp_get_code":{"code_sha256":"2c201f017173954b"}},{"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/llama_inference.py","file_url":"https://github.com/VITA-Group/llm-kick/blob/HEAD/GPTQ_experiment/llama_inference.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"ffa71b6ff9b64407","mcp_get_code":{"code_sha256":"ffa71b6ff9b64407"}},{"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/llama.py","file_url":"https://github.com/lianjiatech/belle/blob/HEAD/models/gptq/llama.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"88d590323ed219c8","mcp_get_code":{"code_sha256":"88d590323ed219c8"}},{"arxiv_id":"2307.08072","paper":"/paper/do-emergent-abilities-exist-in-quantized","title":"Do Emergent Abilities Exist in Quantized Large Language Models: An Empirical Study","date":"2023-07-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"rucaibox/quantizedempirical","path":"models/llama.py","file_url":"https://github.com/rucaibox/quantizedempirical/blob/HEAD/models/llama.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"2c201f017173954b","mcp_get_code":{"code_sha256":"2c201f017173954b"}},{"arxiv_id":"2302.13971","paper":"/paper/llama-open-and-efficient-foundation-language-1","title":"LLaMA: Open and Efficient Foundation Language Models","date":"2023-02-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"code_sha256_prefix":"2c201f017173954b","mcp_get_code":{"code_sha256":"2c201f017173954b"}},{"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":"model_utils.py","file_url":"https://github.com/AI2C-Lab/STLA/blob/HEAD/model_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":"00f92653e59d38b4","mcp_get_code":{"code_sha256":"00f92653e59d38b4"}},{"arxiv_id":"2025.findings-emnlp.1054","paper":null,"title":"arXiv:2025.findings-emnlp.1054","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"IST-DASLab/sparsegpt","path":"llama.py","file_url":"https://github.com/IST-DASLab/sparsegpt/blob/HEAD/llama.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"88d590323ed219c8","mcp_get_code":{"code_sha256":"88d590323ed219c8"}},{"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/llama.py","file_url":"https://github.com/LianjiaTech/BELLE/blob/HEAD/models/gptq/llama.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"88d590323ed219c8","mcp_get_code":{"code_sha256":"88d590323ed219c8"}},{"arxiv_id":"2023.emnlp-main.892","paper":null,"title":"arXiv:2023.emnlp-main.892","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"SamsungLabs/Z-Fold","path":"llama.py","file_url":"https://github.com/SamsungLabs/Z-Fold/blob/HEAD/llama.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"6897a8caeb3dedd0","mcp_get_code":{"code_sha256":"6897a8caeb3dedd0"}}]}