初始化项目,由ModelHub XC社区提供模型
Model: cognitivecomputations/dolphincoder-starcoder2-15b Source: Original Platform
This commit is contained in:
32
config.json
Normal file
32
config.json
Normal file
@@ -0,0 +1,32 @@
|
||||
{
|
||||
"_name_or_path": "/home/ubuntu/models/starcoder2-15b",
|
||||
"architectures": [
|
||||
"Starcoder2ForCausalLM"
|
||||
],
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 0,
|
||||
"embedding_dropout": 0.0,
|
||||
"eos_token_id": 0,
|
||||
"hidden_act": "gelu_pytorch_tanh",
|
||||
"hidden_size": 6144,
|
||||
"initializer_range": 0.01275,
|
||||
"intermediate_size": 24576,
|
||||
"max_position_embeddings": 16384,
|
||||
"mlp_type": "default",
|
||||
"model_type": "starcoder2",
|
||||
"norm_epsilon": 1e-05,
|
||||
"norm_type": "layer_norm",
|
||||
"num_attention_heads": 48,
|
||||
"num_hidden_layers": 40,
|
||||
"num_key_value_heads": 4,
|
||||
"residual_dropout": 0.0,
|
||||
"rms_norm_eps": 1e-05,
|
||||
"rope_theta": 100000,
|
||||
"sliding_window": 4096,
|
||||
"tie_word_embeddings": false,
|
||||
"torch_dtype": "bfloat16",
|
||||
"transformers_version": "4.39.0.dev0",
|
||||
"use_bias": true,
|
||||
"use_cache": false,
|
||||
"vocab_size": 49154
|
||||
}
|
||||
Reference in New Issue
Block a user