Citaman/command-r-12-layer
066
1{2 "_name_or_path": "Citaman/command-r-13-layer",3 "architectures": [4 "CohereForCausalLM"5 ],6 "attention_bias": false,7 "attention_dropout": 0.0,8 "bos_token_id": 5,9 "eos_token_id": 255001,10 "hidden_act": "silu",11 "hidden_size": 8192,12 "initializer_range": 0.02,13 "intermediate_size": 22528,14 "layer_norm_eps": 1e-05,15 "logit_scale": 0.0625,16 "max_position_embeddings": 8192,17 "model_max_length": 131072,18 "model_type": "cohere",19 "num_attention_heads": 64,20 "num_hidden_layers": 12,21 "num_key_value_heads": 64,22 "pad_token_id": 0,23 "pretraining_tp": 1,24 "rope_theta": 8000000.0,25 "torch_dtype": "bfloat16",26 "transformers_version": "4.39.3",27 "use_cache": true,28 "vocab_size": 25600029}30 