{"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/llama-eval","entry":"llama_eval","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":6,"n_papers_ran":4,"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":5,"n_samples_ran":3,"n_samples_fingerprinted":0,"n_places":6,"n_places_pointer_only":4,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":3,"unverified":2},"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":"2606.04980","paper":"/paper/arxiv-2606-04980","title":"AlphaQ: Calibration-Free Bit Allocation for Mixture-of-Experts Quantization","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"Superone77/AlphaQ","path":"eval_ppl_utils.py","file_url":"https://github.com/Superone77/AlphaQ/blob/HEAD/eval_ppl_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"834211043551ca7f","mcp_get_code":{"code_sha256":"834211043551ca7f"}},{"arxiv_id":"2605.15491","paper":"/paper/arxiv-2605-15491","title":"Ghosted Layers: Unconstrained Activation Alignment for Recovering Layer-Pruned LLMs","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"Nota-NetsPresso/shortened-llm","path":"src/eval_ppl.py","file_url":"https://github.com/Nota-NetsPresso/shortened-llm/blob/HEAD/src/eval_ppl.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"9012ddbbaf4ee64f","mcp_get_code":{"code_sha256":"9012ddbbaf4ee64f"}},{"arxiv_id":"2510.03267","paper":"/paper/arxiv-2510-03267","title":"PT$^2$-LLM: Post-Training Ternarization for Large Language Models","date":null,"month_inferred_from_arxiv_id":"2025-10","title_source":"syntology","repo":"XIANGLONGYAN/PT2-LLM","path":"pt2_llm/eval_ppl.py","file_url":"https://github.com/XIANGLONGYAN/PT2-LLM/blob/HEAD/pt2_llm/eval_ppl.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":"7823347a3a40550c","mcp_get_code":{"code_sha256":"7823347a3a40550c"}},{"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":"utils/eval_utils.py","file_url":"https://github.com/vsingh-group/framequant/blob/HEAD/utils/eval_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"0f5810ef333bc3dc","mcp_get_code":{"code_sha256":"0f5810ef333bc3dc"}},{"arxiv_id":"2402.02834","paper":"/paper/shortened-llama-a-simple-depth-pruning-for","title":"Shortened LLaMA: Depth Pruning for Large Language Models with Comparison of Retraining Methods","date":"2024-02-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"nota-netspresso/shortened-llm","path":"src/eval_ppl.py","file_url":"https://github.com/nota-netspresso/shortened-llm/blob/HEAD/src/eval_ppl.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"9012ddbbaf4ee64f","mcp_get_code":{"code_sha256":"9012ddbbaf4ee64f"}},{"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/llama.py","file_url":"https://github.com/ist-daslab/quik/blob/HEAD/experiments/llama.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":"340f10d2f7201ee7","mcp_get_code":{"code_sha256":"340f10d2f7201ee7"}}]}