28 lines
643 B
JSON
28 lines
643 B
JSON
{
|
|
"architectures": [
|
|
"ArceeForCausalLM"
|
|
],
|
|
"attention_bias": false,
|
|
"attention_dropout": 0.0,
|
|
"bos_token_id": 128000,
|
|
"eos_token_id": 128001,
|
|
"head_dim": 128,
|
|
"hidden_act": "relu2",
|
|
"hidden_size": 2560,
|
|
"initializer_range": 0.02,
|
|
"intermediate_size": 18432,
|
|
"max_position_embeddings": 4096,
|
|
"mlp_bias": false,
|
|
"model_type": "arcee",
|
|
"num_attention_heads": 20,
|
|
"num_hidden_layers": 36,
|
|
"num_key_value_heads": 4,
|
|
"rms_norm_eps": 1e-05,
|
|
"rope_theta": 10000.0,
|
|
"tie_word_embeddings": false,
|
|
"torch_dtype": "bfloat16",
|
|
"transformers_version": "4.53.2",
|
|
"use_cache": false,
|
|
"vocab_size": 128256
|
|
}
|