bigcode/starcoder2-7b
22327k
1{2 "activation_function": "gelu",3 "architectures": [4 "Starcoder2ForCausalLM"5 ],6 "attention_dropout": 0.1,7 "residual_dropout": 0.1,8 "embedding_dropout": 0.1,9 "attention_softmax_in_fp32": true,10 "bos_token_id": 0,11 "eos_token_id": 0,12 "hidden_act": "gelu_pytorch_tanh",13 "hidden_size": 4608,14 "initializer_range": 0.018042,15 "intermediate_size": 18432,16 "layer_norm_epsilon": 1e-05,17 "max_position_embeddings": 16384,18 "mlp_type": "default",19 "model_type": "starcoder2",20 "norm_epsilon": 1e-05,21 "norm_type": "layer_norm",22 "num_attention_heads": 36,23 "num_hidden_layers": 32,24 "num_key_value_heads": 4,25 "rope_theta": 1000000,26 "scale_attention_softmax_in_fp32": true,27 "scale_attn_weights": true,28 "sliding_window": 4096,29 "torch_dtype": "bfloat16",30 "transformers_version": "4.37.0.dev0",31 "use_bias": true,32 "use_cache": true,33 "vocab_size": 4915234}35 