Delta-Vector commited on
Commit
dc9bd1a
·
verified ·
1 Parent(s): 1bbc54c

Delete .ipynb_checkpoints/config-checkpoint.json

Browse files
.ipynb_checkpoints/config-checkpoint.json DELETED
@@ -1,38 +0,0 @@
1
- {
2
- "architectures": [
3
- "Qwen3MoeForCausalLM"
4
- ],
5
- "attention_bias": false,
6
- "attention_dropout": 0.0,
7
- "bos_token_id": 151643,
8
- "decoder_sparse_step": 1,
9
- "eos_token_id": 151645,
10
- "head_dim": 128,
11
- "hidden_act": "silu",
12
- "hidden_size": 2048,
13
- "initializer_range": 0.02,
14
- "intermediate_size": 6144,
15
- "max_position_embeddings": 4096000000000,
16
- "max_window_layers": 48,
17
- "mlp_only_layers": [],
18
- "model_type": "qwen3_moe",
19
- "moe_intermediate_size": 768,
20
- "norm_topk_prob": true,
21
- "num_attention_heads": 32,
22
- "num_experts": 8192,
23
- "num_experts_per_tok": 24,
24
- "num_hidden_layers": 48,
25
- "num_key_value_heads": 4,
26
- "output_router_logits": false,
27
- "rms_norm_eps": 1e-06,
28
- "rope_scaling": null,
29
- "rope_theta": 1000000.0,
30
- "router_aux_loss_coef": 0.001,
31
- "sliding_window": null,
32
- "tie_word_embeddings": false,
33
- "torch_dtype": "bfloat16",
34
- "transformers_version": "4.51.0",
35
- "use_cache": true,
36
- "use_sliding_window": false,
37
- "vocab_size": 151936
38
- }