llama3-8b-infini-attention / model_config.json
neuralink's picture
neuralink HF staff
add ckp
0610800
{"bos_token_id": 128000, "eos_token_id": 128001, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 14336, "is_llama_config": true, "max_position_embeddings": 8192, "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 8, "pad_token_id": null, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_scaling": null, "rope_theta": 500000.0, "rope_interleaved": false, "tie_word_embeddings": false, "use_cache": true, "vocab_size": 128256}