datapaf/ve_focus_starcoder2_elixir
013
1{2 "architectures": [3 "Starcoder2ForCausalLM"4 ],5 "attention_dropout": 0.1,6 "bos_token_id": 0,7 "embedding_dropout": 0.1,8 "eos_token_id": 0,9 "hidden_act": "gelu_pytorch_tanh",10 "hidden_size": 3072,11 "initializer_range": 0.018042,12 "intermediate_size": 12288,13 "max_position_embeddings": 16384,14 "mlp_type": "default",15 "model_type": "starcoder2",16 "norm_epsilon": 1e-05,17 "norm_type": "layer_norm",18 "num_attention_heads": 24,19 "num_hidden_layers": 30,20 "num_key_value_heads": 2,21 "residual_dropout": 0.1,22 "rope_scaling": null,23 "rope_theta": 999999.4420358813,24 "sliding_window": 4096,25 "torch_dtype": "bfloat16",26 "transformers_version": "4.51.3",27 "use_bias": true,28 "use_cache": true,29 "vocab_size": 5220230}31 