{ "architectures": [ "tnl1-385m-10b-token_no-act" ], "auto_map": { "AutoConfig": "configuration_transnormer.TransnormerConfig", "AutoModelForCausalLM": "modeling_transnormer.TransnormerForCausalLM" }, "bos_token_id": 50260, "eos_token_id": 50260, "vocab_size": 50272, "use_cache": true, "init_std": 0.02, "decoder_embed_dim": 1024, "decoder_layers": 24, "decoder_attention_heads": 8, "no_scale_embedding": false, "add_bos_token": false, "norm_type": "simplermsnorm", "linear_use_lrpe_list": [ 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 ], "hidden_dim": 1024, "linear_act_fun": "none", "glu_dim": 2816, "bias": false, "torch_dtype": "bfloat16", "transformers_version": "4.38.2" }