GLM-5.3-224E-FP8-MAN / prune-report.json
destr8803's picture
Add MAN model card and qualification report
863bc70 verified
Raw History Blame Contribute Delete
4.35 kB
{
"base_model": "zai-org/GLM-5.3",
"calibration": {
"axes": {
"agentic": {
"samples": 648,
"tokens": 497302
},
"code": {
"samples": 912,
"tokens": 500387
},
"general": {
"samples": 1128,
"tokens": 495244
},
"reasoning": {
"samples": 160,
"tokens": 490789
}
},
"corpus_sha256": "27bdf438f05019d65655c2f0db7ef0b7f994d3c2b250abe66244f30af986a372",
"packing": false,
"samples": 2848,
"seed": 42,
"source_datasets": [
"allenai/c4[en]",
"theblackcat102/evol-codealpaca-v1",
"open-r1/Mixture-of-Thoughts[code,math,science]",
"glaiveai/glaive-function-calling-v2",
"SWE-bench/SWE-smith-trajectories[tool]"
],
"tokens": 1983722,
"truncation": false,
"world_size": 8
},
"checkpoint": {
"config_sha256": "546c69d5e6b79f848598f0cc5ad7689bf5033cd3995e34341918ae7224158c7e",
"index_sha256": "a8193674cab604ca7b8af9bfc5ff1db10a058a832282017c8aa345a77c3c99c6",
"payload_bytes": 663759907008,
"precision": "FP8 weights; BF16 KV cache runtime-qualified",
"shards": 141,
"tensors": 104037
},
"evaluation": {
"behavior": {
"passed": 12,
"reasoning_efforts": [
"low",
"high",
"max"
],
"total": 12
},
"comparison_report_sha256": "e2acf585eed9108fe502d8573eca46a700c534134721ae997bc46baec2e8e297",
"functional": {
"passed": 4,
"total": 4
},
"gpqa_diamond": {
"accuracy_percent": 97.5,
"bootstrap_95_clustered_by_question": [
92.5,
100.0
],
"completed_requests": 40,
"correct": 39,
"dataset_sha256": "41d1213cd7a4998605a26c2798500652572007161b3a92817ba46b35befcd305",
"dataset_url": "https://openaipublic.blob.core.windows.net/simple-evals/gpqa_diamond.csv",
"failed_requests": 0,
"malformed_answers": 0,
"max_tokens": 120000,
"prompt_sha256": "d4d85337bbd54659d12c8da7edc8b854d151b7327cf7574dc1062d753b03c8a6",
"question_count": 40,
"question_set_sha256": "c5c24ae147b5f771e3b5ca5552119fa1340e479073c23adad46b22f21ebc3476",
"reasoning_effort": "max (server default)",
"run_fingerprint": "a8a8737cfeae2bd96a87df27b1620ad523dcac5a1dc341b108a1d524f943ca4e",
"seed": 0,
"temperature": 1.0,
"top_p": 0.95
},
"runtime": {
"accelerators": "8x Intel Gaudi2",
"aggregate_16x1024_tokens_per_second": 237.03,
"expert_parallel_size": 8,
"kv_cache_dtype": "BF16",
"max_model_len": 131072,
"single_stream_tokens_per_second": 19.716830071821388,
"tensor_parallel_size": 8
}
},
"format_version": 3,
"license": "glm-5.3; see LICENSE",
"limitations": [
"The checkpoint is a 12.5% expert-pruned derivative without retraining.",
"Calibration was English-heavy and did not include an explicit Spanish axis.",
"GPQA validation covered a deterministic 40-question subset, not the full benchmark.",
"Gaudi2 TP8/EP8 was qualified; other accelerator backends were not qualified."
],
"pruning": {
"activation_outlier_protection": {
"candidate_count": 7,
"candidate_layers": [
77
],
"enabled": true,
"threshold": "max_abs > max(global_p99.5, global_max/10)"
},
"criterion": "S(1,0,1)=mean(l2(unweighted_expert_output)) over routed tokens",
"criterion_id": "s101_man",
"keep_map_sha256": "f5abe51855b4d7975773bf640128c3077fcf8f7aaa3c54f1c892b55304e2444b",
"method": "MAN",
"mtp_policy": "reuse_layer_77_keep_ids_for_base_first_delivery",
"reduction_percent": 12.5,
"retraining": false,
"source_experts_per_sparse_layer": 256,
"target_experts_per_sparse_layer": 224,
"top_k": 8
},
"repository": "destr8803/GLM-5.3-224E-FP8-MAN",
"source": {
"config_sha256": "3ac72612095574542f7fff847ada8e59d9199dd8af44bdf625d7e02615572e69",
"index_sha256": "e0fe7f28c1f853d4824e4d796374e3dacf1fe470988773952c79b063768134bf",
"routed_experts_per_sparse_layer": 256
},
"status": "runtime-qualified",
"validation": {
"checked_tensors": 104037,
"errors": 0,
"report_sha256": "0d547367304885ae4d7c66b44e7c446e0dcd7685ff0a085992604e865d23a391",
"shards": 141,
"status": "pass"
}
}