初始化项目,由ModelHub XC社区提供模型

Model: AhiskaAI/AhiskaAI-65m-IT-v0.1
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-08-15 13:35:17 +08:00
commit d1c292ef46
7 changed files with 159420 additions and 0 deletions

32
config.json Normal file
View File

@@ -0,0 +1,32 @@
{
"architectures": [
"LlamaForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 5,
"dtype": "float32",
"eos_token_id": 6,
"head_dim": 64,
"hidden_act": "silu",
"hidden_size": 512,
"initializer_range": 0.02,
"intermediate_size": 1376,
"max_position_embeddings": 1024,
"mlp_bias": false,
"model_type": "llama",
"num_attention_heads": 8,
"num_hidden_layers": 12,
"num_key_value_heads": 8,
"pad_token_id": 0,
"pretraining_tp": 1,
"rms_norm_eps": 1e-06,
"rope_parameters": {
"rope_theta": 10000.0,
"rope_type": "default"
},
"tie_word_embeddings": false,
"transformers_version": "5.5.0",
"use_cache": true,
"vocab_size": 32000
}