初始化项目,由ModelHub XC社区提供模型
Model: Yousefbahr/Turjman-Cold-Start Source: Original Platform
This commit is contained in:
31
config.json
Normal file
31
config.json
Normal file
@@ -0,0 +1,31 @@
|
||||
{
|
||||
"architectures": [
|
||||
"CohereForCausalLM"
|
||||
],
|
||||
"attention_bias": false,
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 5,
|
||||
"dtype": "bfloat16",
|
||||
"eos_token_id": 255001,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 4096,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 14336,
|
||||
"layer_norm_eps": 1e-05,
|
||||
"logit_scale": 0.125,
|
||||
"max_position_embeddings": 8192,
|
||||
"model_type": "cohere",
|
||||
"num_attention_heads": 32,
|
||||
"num_hidden_layers": 32,
|
||||
"num_key_value_heads": 8,
|
||||
"pad_token_id": 0,
|
||||
"rope_parameters": {
|
||||
"rope_theta": 10000,
|
||||
"rope_type": "default"
|
||||
},
|
||||
"tie_word_embeddings": true,
|
||||
"transformers_version": "5.2.0",
|
||||
"use_cache": false,
|
||||
"use_qk_norm": false,
|
||||
"vocab_size": 256000
|
||||
}
|
||||
Reference in New Issue
Block a user