初始化项目,由ModelHub XC社区提供模型

Model: HuggingFaceFW/ablation-exp-dedup-ind_mh-global_3line-350BT
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-05-07 20:23:06 +08:00
commit 4a4d4a9b43
11 changed files with 50314 additions and 0 deletions

27
config.json Normal file
View File

@@ -0,0 +1,27 @@
{
"architectures": [
"LlamaForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 1,
"eos_token_id": 2,
"hidden_act": "silu",
"hidden_size": 2048,
"initializer_range": 0.02,
"intermediate_size": 8192,
"max_position_embeddings": 2048,
"model_type": "llama",
"num_attention_heads": 32,
"num_hidden_layers": 24,
"num_key_value_heads": 32,
"pretraining_tp": 1,
"rms_norm_eps": 1e-05,
"rope_scaling": null,
"rope_theta": 10000.0,
"tie_word_embeddings": true,
"torch_dtype": "bfloat16",
"transformers_version": "4.38.2",
"use_cache": true,
"vocab_size": 50272
}