Team Ai
Modelpublic

flexitok/parity_aware_bpe_devset

sourceHugging Faceupdated 1mo agoView on Hugging Face
0likes19downloads
config.json26 linesDownload Raw Back to root
1{2  "attention_bias": false,3  "attention_dropout": 0.0,4  "bos_token_id": 128000,5  "eos_token_id": 128001,6  "head_dim": 128,7  "hidden_act": "silu",8  "hidden_size": 2048,9  "initializer_range": 0.02,10  "intermediate_size": 5632,11  "max_position_embeddings": 8192,12  "mlp_bias": false,13  "model_type": "llama",14  "num_attention_heads": 16,15  "num_hidden_layers": 25,16  "num_key_value_heads": 16,17  "pretraining_tp": 1,18  "rms_norm_eps": 1e-05,19  "rope_scaling": null,20  "rope_theta": 10000.0,21  "tie_word_embeddings": false,22  "transformers_version": "4.57.3",23  "use_cache": true,24  "vocab_size": 12825825}26