37 lines
981 B
JSON
37 lines
981 B
JSON
|
|
{
|
||
|
|
"_name_or_path": "m-a-p/OpenCodeInterpreter-SC2-7B",
|
||
|
|
"activation_function": "gelu",
|
||
|
|
"architectures": [
|
||
|
|
"Starcoder2ForCausalLM"
|
||
|
|
],
|
||
|
|
"attention_dropout": 0.0,
|
||
|
|
"attention_softmax_in_fp32": true,
|
||
|
|
"bos_token_id": 0,
|
||
|
|
"embedding_dropout": 0.0,
|
||
|
|
"eos_token_id": 0,
|
||
|
|
"hidden_act": "gelu_pytorch_tanh",
|
||
|
|
"hidden_size": 4608,
|
||
|
|
"initializer_range": 0.018042,
|
||
|
|
"intermediate_size": 18432,
|
||
|
|
"layer_norm_epsilon": 1e-05,
|
||
|
|
"max_position_embeddings": 16384,
|
||
|
|
"mlp_type": "default",
|
||
|
|
"model_type": "starcoder2",
|
||
|
|
"norm_epsilon": 1e-05,
|
||
|
|
"norm_type": "layer_norm",
|
||
|
|
"num_attention_heads": 36,
|
||
|
|
"num_hidden_layers": 32,
|
||
|
|
"num_key_value_heads": 4,
|
||
|
|
"residual_dropout": 0.0,
|
||
|
|
"rope_theta": 1000000,
|
||
|
|
"scale_attention_softmax_in_fp32": true,
|
||
|
|
"scale_attn_weights": true,
|
||
|
|
"sliding_window": 4096,
|
||
|
|
"tie_word_embeddings": false,
|
||
|
|
"torch_dtype": "bfloat16",
|
||
|
|
"transformers_version": "4.39.0.dev0",
|
||
|
|
"use_bias": true,
|
||
|
|
"use_cache": false,
|
||
|
|
"vocab_size": 49152
|
||
|
|
}
|