DavidAU/Qwen3-MOE-4x0.6B-2.4B-Writing-Thunder-V1.2
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: DavidAU/Qwen3-MOE-4x0.6B-2.4B-Writing-Thunder-V1.2
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-04-25 02:12:42 +08:00
commit 8fd0e8cd54
12 changed files with 152107 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

68
config.json Normal file
View File

@@ -0,0 +1,68 @@
{
"architectures": [
"Qwen3MoeForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 151643,
"decoder_sparse_step": 1,
"eos_token_id": 151645,
"head_dim": 128,
"hidden_act": "silu",
"hidden_size": 1024,
"initializer_range": 0.02,
"intermediate_size": 3072,
"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"
],
"max_position_embeddings": 40960,
"max_window_layers": 28,
"mlp_only_layers": [],
"model_type": "qwen3_moe",
"moe_intermediate_size": 3072,
"norm_topk_prob": true,
"num_attention_heads": 16,
"num_experts": 4,
"num_experts_per_tok": 2,
"num_hidden_layers": 28,
"num_key_value_heads": 8,
"output_router_logits": false,
"rms_norm_eps": 1e-06,
"rope_scaling": null,
"rope_theta": 1000000,
"router_aux_loss_coef": 0.001,
"sliding_window": null,
"tie_word_embeddings": true,
"torch_dtype": "bfloat16",
"transformers_version": "4.55.0",
"use_cache": true,
"use_sliding_window": false,
"vocab_size": 151936
}