Upload config.json with huggingface_hub
Browse files- config.json +70 -0
config.json
ADDED
|
@@ -0,0 +1,70 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"UpcyclingQwen2MoeForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_dropout": 0.0,
|
| 6 |
+
"attn_init_change": false,
|
| 7 |
+
"auto_map": {
|
| 8 |
+
"AutoConfig": "configuration_upcycling_qwen2_moe.UpcyclingQwen2MoeConfig",
|
| 9 |
+
"AutoModelForCausalLM": "modeling_upcycling_qwen2_moe.UpcyclingQwen2MoeForCausalLM"
|
| 10 |
+
},
|
| 11 |
+
"bos_token_id": 151643,
|
| 12 |
+
"decoder_sparse_step": 1,
|
| 13 |
+
"eos_token_id": 151643,
|
| 14 |
+
"hidden_act": "silu",
|
| 15 |
+
"hidden_size": 1536,
|
| 16 |
+
"initializer_range": 0.02,
|
| 17 |
+
"intermediate_size": 8960,
|
| 18 |
+
"language_gate": true,
|
| 19 |
+
"max_position_embeddings": 131072,
|
| 20 |
+
"max_window_layers": 28,
|
| 21 |
+
"mlp_only_layers": [
|
| 22 |
+
0,
|
| 23 |
+
1,
|
| 24 |
+
2,
|
| 25 |
+
3,
|
| 26 |
+
4,
|
| 27 |
+
5,
|
| 28 |
+
6,
|
| 29 |
+
7,
|
| 30 |
+
8,
|
| 31 |
+
9,
|
| 32 |
+
10,
|
| 33 |
+
11,
|
| 34 |
+
12,
|
| 35 |
+
13,
|
| 36 |
+
14,
|
| 37 |
+
15,
|
| 38 |
+
16,
|
| 39 |
+
17,
|
| 40 |
+
18,
|
| 41 |
+
19,
|
| 42 |
+
20,
|
| 43 |
+
21,
|
| 44 |
+
22,
|
| 45 |
+
23,
|
| 46 |
+
24,
|
| 47 |
+
25
|
| 48 |
+
],
|
| 49 |
+
"model_type": "upcycling-qwen2-moe",
|
| 50 |
+
"moe_intermediate_size": 8960,
|
| 51 |
+
"norm_topk_prob": false,
|
| 52 |
+
"num_attention_heads": 12,
|
| 53 |
+
"num_experts": 7,
|
| 54 |
+
"num_experts_per_tok": 2,
|
| 55 |
+
"num_hidden_layers": 28,
|
| 56 |
+
"num_key_value_heads": 2,
|
| 57 |
+
"output_router_logits": false,
|
| 58 |
+
"rms_norm_eps": 1e-06,
|
| 59 |
+
"rope_theta": 1000000.0,
|
| 60 |
+
"router_aux_loss_coef": 0.0,
|
| 61 |
+
"share_flag": false,
|
| 62 |
+
"shared_expert_intermediate_size": 8960,
|
| 63 |
+
"sliding_window": 131072,
|
| 64 |
+
"tie_word_embeddings": true,
|
| 65 |
+
"torch_dtype": "bfloat16",
|
| 66 |
+
"transformers_version": "4.44.2",
|
| 67 |
+
"use_cache": true,
|
| 68 |
+
"use_sliding_window": false,
|
| 69 |
+
"vocab_size": 151936
|
| 70 |
+
}
|