|
{ |
|
"_name_or_path": "bigcode/starcoder2-3b", |
|
"architectures": [ |
|
"Starcoder2ForCausalLM" |
|
], |
|
"attention_dropout": 0.1, |
|
"bos_token_id": 0, |
|
"embedding_dropout": 0.1, |
|
"eos_token_id": 0, |
|
"hidden_act": "gelu_pytorch_tanh", |
|
"hidden_size": 3072, |
|
"initializer_range": 0.018042, |
|
"intermediate_size": 12288, |
|
"max_position_embeddings": 16384, |
|
"mlp_type": "default", |
|
"model_type": "starcoder2", |
|
"norm_epsilon": 1e-05, |
|
"norm_type": "layer_norm", |
|
"num_attention_heads": 24, |
|
"num_hidden_layers": 30, |
|
"num_key_value_heads": 2, |
|
"residual_dropout": 0.1, |
|
"rope_scaling": null, |
|
"rope_theta": 999999.4420358813, |
|
"sliding_window": 4096, |
|
"torch_dtype": "float32", |
|
"transformers_version": "4.46.2", |
|
"use_bias": true, |
|
"use_cache": true, |
|
"vocab_size": 49152 |
|
} |
|
|