MrLvTian/Qwen3-8B-shortgpt-prune-3-layer
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: MrLvTian/Qwen3-8B-shortgpt-prune-3-layer
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-06-10 17:42:52 +08:00
commit 0d1078abfc
16 changed files with 152478 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

65
config.json Normal file
View File

@@ -0,0 +1,65 @@
{
"architectures": [
"Qwen3ForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"head_dim": 128,
"hidden_act": "silu",
"hidden_size": 4096,
"initializer_range": 0.02,
"intermediate_size": 12288,
"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"
],
"max_position_embeddings": 40960,
"max_window_layers": 33,
"model_type": "qwen3",
"num_attention_heads": 32,
"num_hidden_layers": 33,
"num_key_value_heads": 8,
"rms_norm_eps": 1e-06,
"rope_scaling": null,
"rope_theta": 1000000,
"sliding_window": null,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.53.3",
"use_cache": true,
"use_sliding_window": false,
"vocab_size": 151669
}