snake7gun commited on
Commit
f2c45d0
·
verified ·
1 Parent(s): cd0cdad

Upload folder using huggingface_hub

Browse files
Files changed (2) hide show
  1. config.json +35 -0
  2. model.safetensors +3 -0
config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3MoeModel"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "decoder_sparse_step": 1,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 16,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 6144,
12
+ "max_position_embeddings": 32768,
13
+ "max_window_layers": 28,
14
+ "mlp_only_layers": [],
15
+ "model_type": "qwen3_moe",
16
+ "moe_intermediate_size": 768,
17
+ "norm_topk_prob": false,
18
+ "num_attention_heads": 2,
19
+ "num_experts": 128,
20
+ "num_experts_per_tok": 1,
21
+ "num_hidden_layers": 2,
22
+ "num_key_value_heads": 4,
23
+ "output_router_logits": false,
24
+ "rms_norm_eps": 1e-06,
25
+ "rope_scaling": null,
26
+ "rope_theta": 10000.0,
27
+ "router_aux_loss_coef": 0.001,
28
+ "sliding_window": null,
29
+ "tie_word_embeddings": false,
30
+ "torch_dtype": "float32",
31
+ "transformers_version": "4.52.0.dev0",
32
+ "use_cache": true,
33
+ "use_sliding_window": false,
34
+ "vocab_size": 151936
35
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d6612c734c18f76468abb0cdf78e6475f6de6c4e714c4d61f8ccbd73e820e55b
3
+ size 47588608