pancode / config.json
tiagozip's picture
release pancode
3b06c7c verified
Raw History Blame Contribute Delete
3.78 kB
{
"_name_or_path": "pancode",
"architectures": [
"ModernBertForSequenceClassification"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 50281,
"classifier_activation": "gelu",
"classifier_bias": false,
"classifier_dropout": 0.0,
"classifier_pooling": "mean",
"cls_token_id": 50281,
"decoder_bias": true,
"deterministic_flash_attn": false,
"embedding_dropout": 0.0,
"eos_token_id": 50282,
"global_attn_every_n_layers": 3,
"global_rope_theta": 160000.0,
"gradient_checkpointing": false,
"hidden_activation": "gelu",
"hidden_size": 1024,
"id2label": {
"0": "LABEL_0",
"1": "LABEL_1",
"10": "LABEL_10",
"11": "LABEL_11",
"12": "LABEL_12",
"13": "LABEL_13",
"14": "LABEL_14",
"15": "LABEL_15",
"16": "LABEL_16",
"17": "LABEL_17",
"18": "LABEL_18",
"19": "LABEL_19",
"2": "LABEL_2",
"20": "LABEL_20",
"21": "LABEL_21",
"22": "LABEL_22",
"23": "LABEL_23",
"24": "LABEL_24",
"25": "LABEL_25",
"3": "LABEL_3",
"4": "LABEL_4",
"5": "LABEL_5",
"6": "LABEL_6",
"7": "LABEL_7",
"8": "LABEL_8",
"9": "LABEL_9"
},
"initializer_cutoff_factor": 2.0,
"initializer_range": 0.02,
"intermediate_size": 2624,
"label2id": {
"LABEL_0": 0,
"LABEL_1": 1,
"LABEL_10": 10,
"LABEL_11": 11,
"LABEL_12": 12,
"LABEL_13": 13,
"LABEL_14": 14,
"LABEL_15": 15,
"LABEL_16": 16,
"LABEL_17": 17,
"LABEL_18": 18,
"LABEL_19": 19,
"LABEL_2": 2,
"LABEL_20": 20,
"LABEL_21": 21,
"LABEL_22": 22,
"LABEL_23": 23,
"LABEL_24": 24,
"LABEL_25": 25,
"LABEL_3": 3,
"LABEL_4": 4,
"LABEL_5": 5,
"LABEL_6": 6,
"LABEL_7": 7,
"LABEL_8": 8,
"LABEL_9": 9
},
"layer_norm_eps": 1e-05,
"local_attention": 128,
"local_rope_theta": 10000.0,
"max_position_embeddings": 8192,
"mlp_bias": false,
"mlp_dropout": 0.0,
"model_type": "modernbert",
"norm_bias": false,
"norm_eps": 1e-05,
"num_attention_heads": 16,
"num_hidden_layers": 28,
"pad_token_id": 50283,
"pancode_eval": {
"auc": 0.9842,
"codeberg_fp_1pct": 0.15,
"codeberg_fp_5pct": 0.2787,
"model_top1": 0.3773,
"model_top3": 0.6649,
"recall_1pct": 0.8253,
"recall_5pct": 0.9517,
"vendor_acc": 0.8052
},
"pancode_heads": {
"models": [
"claude fable 5",
"claude fable 5.1",
"claude haiku 4.5",
"claude haiku 5.5",
"claude opus 4.5",
"claude opus 4.6",
"claude opus 4.7",
"claude opus 4.8",
"claude opus 5",
"claude opus 5.5",
"claude other",
"claude sonnet 4.5",
"claude sonnet 4.6",
"claude sonnet 5",
"claude sonnet 5.5",
"deepseek",
"glm",
"gpt-5.6 sol",
"gpt-6",
"gpt-6.1 sol",
"grok",
"kimi",
"openai other",
"qwen"
],
"vendors": [
"claude",
"claude",
"claude",
"claude",
"claude",
"claude",
"claude",
"claude",
"claude",
"claude",
"claude",
"claude",
"claude",
"claude",
"claude",
"deepseek",
"glm",
"openai",
"openai",
"openai",
"grok",
"kimi",
"openai",
"qwen"
],
"version": 3
},
"pancode_thresholds": {
"max_len": 2048,
"source": "val neg_old quantiles",
"step": 12000,
"thr_1pct": 0.7111,
"thr_5pct": 0.1765
},
"position_embedding_type": "absolute",
"reference_compile": false,
"repad_logits_with_grad": false,
"sep_token_id": 50282,
"sparse_pred_ignore_index": -100,
"sparse_prediction": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.48.3",
"vocab_size": 50368
}