初始化项目,由ModelHub XC社区提供模型

Model: mehuldamani/sft-qwen-hmaze-v1
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-05-06 13:55:54 +08:00
commit 2a6f5dfb66
15 changed files with 152472 additions and 0 deletions

72
config.json Normal file
View File

@@ -0,0 +1,72 @@
{
"architectures": [
"Qwen2ForCausalLM"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"dtype": "float32",
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 2048,
"id2label": {
"0": "LABEL_0"
},
"initializer_range": 0.02,
"intermediate_size": 11008,
"label2id": {
"LABEL_0": 0
},
"layer_types": [
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention"
],
"max_position_embeddings": 32768,
"max_window_layers": 70,
"model_type": "qwen2",
"num_attention_heads": 16,
"num_hidden_layers": 36,
"num_key_value_heads": 2,
"rms_norm_eps": 1e-06,
"rope_scaling": null,
"rope_theta": 1000000.0,
"sliding_window": null,
"tie_word_embeddings": true,
"transformers_version": "4.57.1",
"use_cache": true,
"use_sliding_window": false,
"vocab_size": 151936
}