初始化项目,由ModelHub XC社区提供模型

Model: yakazimir/simpo-exps_qwen05b
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-05-27 13:20:24 +08:00
commit 9c0b547458
23 changed files with 151912 additions and 0 deletions

29
config.json Normal file
View File

@@ -0,0 +1,29 @@
{
"_name_or_path": "trl-lib/qwen1.5-0.5b-sft",
"architectures": [
"Qwen2ForCausalLM"
],
"attention_dropout": 0.0,
"bos_token_id": 151644,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 1024,
"initializer_range": 0.02,
"intermediate_size": 2816,
"max_position_embeddings": 32768,
"max_window_layers": 21,
"model_type": "qwen2",
"num_attention_heads": 16,
"num_hidden_layers": 24,
"num_key_value_heads": 16,
"pad_token_id": 151645,
"rms_norm_eps": 1e-06,
"rope_theta": 1000000.0,
"sliding_window": null,
"tie_word_embeddings": true,
"torch_dtype": "bfloat16",
"transformers_version": "4.44.2",
"use_cache": true,
"use_sliding_window": false,
"vocab_size": 151648
}