初始化项目,由ModelHub XC社区提供模型

Model: DavidAU/Qwen3-4B-Thinking-2507-Claude-4.5-Opus-High-Reasoning-Distill-Heretic-Abliterated
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-06-03 11:58:19 +08:00
commit 713d2036e6
14 changed files with 152442 additions and 0 deletions

73
config.json Normal file
View File

@@ -0,0 +1,73 @@
{
"architectures": [
"Qwen3ForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"dtype": "bfloat16",
"eos_token_id": 151645,
"head_dim": 128,
"hidden_act": "silu",
"hidden_size": 2560,
"initializer_range": 0.02,
"intermediate_size": 9728,
"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": 262144,
"max_window_layers": 36,
"model_type": "qwen3",
"num_attention_heads": 32,
"num_hidden_layers": 36,
"num_key_value_heads": 8,
"pad_token_id": 151654,
"rms_norm_eps": 1e-06,
"rope_parameters": {
"rope_theta": 5000000,
"rope_type": "default"
},
"rope_theta": 5000000,
"sliding_window": null,
"tie_word_embeddings": true,
"transformers_version": "5.0.0.dev0",
"unsloth_fixed": true,
"unsloth_version": "2025.11.3",
"use_cache": true,
"use_sliding_window": false,
"vocab_size": 151936
}