初始化项目,由ModelHub XC社区提供模型

Model: MusaKlair/pythia410m-dpo-beta0.1
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-07-21 15:46:11 +08:00
commit 2bf264173e
42 changed files with 1004917 additions and 0 deletions

33
config.json Normal file
View File

@@ -0,0 +1,33 @@
{
"architectures": [
"GPTNeoXForCausalLM"
],
"attention_bias": true,
"attention_dropout": 0.0,
"bos_token_id": 0,
"classifier_dropout": 0.1,
"dtype": "float32",
"eos_token_id": 0,
"hidden_act": "gelu",
"hidden_dropout": 0.0,
"hidden_size": 1024,
"initializer_range": 0.02,
"intermediate_size": 4096,
"is_decoder": false,
"layer_norm_eps": 1e-05,
"max_position_embeddings": 2048,
"model_type": "gpt_neox",
"num_attention_heads": 16,
"num_hidden_layers": 24,
"pad_token_id": 1,
"rope_parameters": {
"partial_rotary_factor": 0.25,
"rope_theta": 10000,
"rope_type": "default"
},
"tie_word_embeddings": false,
"transformers_version": "5.13.0",
"use_cache": false,
"use_parallel_residual": true,
"vocab_size": 50304
}