初始化项目,由ModelHub XC社区提供模型

Model: Tanveer539mbw8/Aivapro-Model
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-08-04 19:19:17 +08:00
commit c480f67d98
9 changed files with 118 additions and 0 deletions

25
config.json Normal file
View File

@@ -0,0 +1,25 @@
{
"architectures": [
"Qwen2ForCausalLM"
],
"attention_dropout": 0.0,
"bos_token_id": 151646,
"torch_dtype": "float16",
"eos_token_id": 151643,
"hidden_act": "silu",
"hidden_size": 1536,
"initializer_range": 0.02,
"intermediate_size": 8960,
"max_position_embeddings": 32768,
"model_type": "qwen2",
"num_attention_heads": 12,
"num_hidden_layers": 28,
"num_key_value_heads": 2,
"pad_token_id": 151643,
"rms_norm_eps": 1e-06,
"rope_theta": 1000000.0,
"sliding_window": null,
"tie_word_embeddings": false,
"use_cache": true,
"vocab_size": 151936
}