初始化项目,由ModelHub XC社区提供模型
Model: ChuGyouk/F_R8_1_T1 Source: Original Platform
This commit is contained in:
34
config.json
Normal file
34
config.json
Normal file
@@ -0,0 +1,34 @@
|
||||
{
|
||||
"architectures": [
|
||||
"LlamaForCausalLM"
|
||||
],
|
||||
"attention_bias": false,
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 128000,
|
||||
"dtype": "bfloat16",
|
||||
"eos_token_id": 128009,
|
||||
"head_dim": 128,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 4096,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 14336,
|
||||
"max_position_embeddings": 131072,
|
||||
"mlp_bias": false,
|
||||
"model_name": "ChuGyouk/F_R8_1",
|
||||
"model_type": "llama",
|
||||
"num_attention_heads": 32,
|
||||
"num_hidden_layers": 32,
|
||||
"num_key_value_heads": 8,
|
||||
"pad_token_id": 128004,
|
||||
"pretraining_tp": 1,
|
||||
"rms_norm_eps": 1e-05,
|
||||
"rope_parameters": {
|
||||
"rope_theta": 500000.0,
|
||||
"rope_type": "default"
|
||||
},
|
||||
"tie_word_embeddings": false,
|
||||
"transformers_version": "5.2.0",
|
||||
"unsloth_version": "2026.3.3",
|
||||
"use_cache": false,
|
||||
"vocab_size": 128256
|
||||
}
|
||||
Reference in New Issue
Block a user