trillionlabs/Tri-1.9B-Base
1105
1{2 "architectures": [3 "LlamaForCausalLM"4 ],5 "attention_bias": false,6 "attention_dropout": 0.0,7 "bos_token_id": 0,8 "eos_token_id": 128001,9 "head_dim": 128,10 "hidden_act": "silu",11 "hidden_size": 2048,12 "initializer_range": 0.02,13 "intermediate_size": 5632,14 "max_position_embeddings": 4096,15 "mlp_bias": false,16 "model_type": "llama",17 "num_attention_heads": 16,18 "num_hidden_layers": 25,19 "num_key_value_heads": 16,20 "pretraining_tp": 1,21 "rms_norm_eps": 1e-05,22 "rope_scaling": null,23 "rope_theta": 10000.0,24 "tie_word_embeddings": false,25 "torch_dtype": "bfloat16",26 "transformers_version": "4.49.0",27 "use_cache": true,28 "vocab_size": 12812829}30 