SpectraSuite/TriLM_3.9B_Unpacked
15355
1{2 "architectures": [3 "LlamaForCausalLM"4 ],5 "attention_bias": false,6 "attention_dropout": 0.0,7 "bos_token_id": 0,8 "dims_per_head": 128,9 "eos_token_id": 0,10 "hidden_act": "silu",11 "hidden_size": 3072,12 "initializer_range": 0.02,13 "intermediate_size": 9216,14 "layer_norm_eps": 1e-05,15 "max_position_embeddings": 2048,16 "model_type": "llama",17 "num_attention_heads": 24,18 "num_hidden_layers": 30,19 "num_key_value_heads": 24,20 "pretraining_tp": 1,21 "pretraining_model_parallel": 6,22 "rms_norm_eps": 1e-05,23 "rope_scaling": null,24 "rope_theta": 10000.0,25 "rotary_emb_base": 10000,26 "rotary_pct": 1.0,27 "tie_word_embeddings": false,28 "torch_dtype": "float16",29 "transformers_version": "4.40.1",30 "use_cache": true,31 "use_parallel_residual": false,32 "vocab_size": 5068833}34 