初始化项目,由ModelHub XC社区提供模型

Model: arcee-ai/Arcee-Spark
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-05-07 07:08:46 +08:00
commit f21e1de245
16 changed files with 455305 additions and 0 deletions

27
config.json Normal file
View File

@@ -0,0 +1,27 @@
{
"_name_or_path": "arcee-train/qwen2-merge4-dpo-v0.1",
"architectures": [
"Qwen2ForCausalLM"
],
"attention_dropout": 0.0,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 3584,
"initializer_range": 0.02,
"intermediate_size": 18944,
"max_position_embeddings": 32768,
"max_window_layers": 28,
"model_type": "qwen2",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"rms_norm_eps": 1e-06,
"rope_theta": 1000000.0,
"sliding_window": 131072,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.41.2",
"use_cache": false,
"use_sliding_window": false,
"vocab_size": 152064
}