Upload config.json with huggingface_hub
Browse files- config.json +16 -39
config.json
CHANGED
|
@@ -1,60 +1,37 @@
|
|
| 1 |
{
|
| 2 |
-
"_attn_implementation_autoset": true,
|
| 3 |
"architectures": [
|
| 4 |
-
"
|
| 5 |
],
|
| 6 |
"attention_dropout": 0.0,
|
| 7 |
-
"dtype": "bfloat16",
|
| 8 |
"eos_token_id": 151643,
|
| 9 |
"hidden_act": "silu",
|
| 10 |
"hidden_size": 1536,
|
| 11 |
"initializer_range": 0.02,
|
| 12 |
"intermediate_size": 8960,
|
| 13 |
-
"layer_types": [
|
| 14 |
-
"full_attention",
|
| 15 |
-
"full_attention",
|
| 16 |
-
"full_attention",
|
| 17 |
-
"full_attention",
|
| 18 |
-
"full_attention",
|
| 19 |
-
"full_attention",
|
| 20 |
-
"full_attention",
|
| 21 |
-
"full_attention",
|
| 22 |
-
"full_attention",
|
| 23 |
-
"full_attention",
|
| 24 |
-
"full_attention",
|
| 25 |
-
"full_attention",
|
| 26 |
-
"full_attention",
|
| 27 |
-
"full_attention",
|
| 28 |
-
"full_attention",
|
| 29 |
-
"full_attention",
|
| 30 |
-
"full_attention",
|
| 31 |
-
"full_attention",
|
| 32 |
-
"full_attention",
|
| 33 |
-
"full_attention",
|
| 34 |
-
"full_attention",
|
| 35 |
-
"full_attention",
|
| 36 |
-
"full_attention",
|
| 37 |
-
"full_attention",
|
| 38 |
-
"full_attention",
|
| 39 |
-
"full_attention",
|
| 40 |
-
"full_attention",
|
| 41 |
-
"full_attention"
|
| 42 |
-
],
|
| 43 |
"max_position_embeddings": 131072,
|
| 44 |
"max_window_layers": 21,
|
| 45 |
-
"model_type": "
|
| 46 |
"num_attention_heads": 12,
|
| 47 |
"num_hidden_layers": 28,
|
| 48 |
"num_key_value_heads": 2,
|
| 49 |
-
"pad_token_id": 151643,
|
| 50 |
"rms_norm_eps": 1e-06,
|
| 51 |
-
"rope_scaling": null,
|
| 52 |
"rope_theta": 640000,
|
| 53 |
"sliding_window": null,
|
| 54 |
"tie_word_embeddings": true,
|
| 55 |
"transformers_version": "4.56.1",
|
| 56 |
"use_cache": false,
|
| 57 |
-
"use_mrope": false,
|
| 58 |
"use_sliding_window": false,
|
| 59 |
-
"vocab_size": 151936
|
| 60 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
{
|
|
|
|
| 2 |
"architectures": [
|
| 3 |
+
"Qwen2MoeForCausalLM"
|
| 4 |
],
|
| 5 |
"attention_dropout": 0.0,
|
|
|
|
| 6 |
"eos_token_id": 151643,
|
| 7 |
"hidden_act": "silu",
|
| 8 |
"hidden_size": 1536,
|
| 9 |
"initializer_range": 0.02,
|
| 10 |
"intermediate_size": 8960,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11 |
"max_position_embeddings": 131072,
|
| 12 |
"max_window_layers": 21,
|
| 13 |
+
"model_type": "qwen2_moe",
|
| 14 |
"num_attention_heads": 12,
|
| 15 |
"num_hidden_layers": 28,
|
| 16 |
"num_key_value_heads": 2,
|
|
|
|
| 17 |
"rms_norm_eps": 1e-06,
|
|
|
|
| 18 |
"rope_theta": 640000,
|
| 19 |
"sliding_window": null,
|
| 20 |
"tie_word_embeddings": true,
|
| 21 |
"transformers_version": "4.56.1",
|
| 22 |
"use_cache": false,
|
|
|
|
| 23 |
"use_sliding_window": false,
|
| 24 |
+
"vocab_size": 151936,
|
| 25 |
+
"dtype": "bfloat16",
|
| 26 |
+
"pad_token_id": 151643,
|
| 27 |
+
"rope_scaling": null,
|
| 28 |
+
"use_mrope": false,
|
| 29 |
+
"decoder_sparse_step": 1,
|
| 30 |
+
"moe_intermediate_size": 256,
|
| 31 |
+
"shared_expert_intermediate_size": 8960,
|
| 32 |
+
"num_experts_per_tok": 4,
|
| 33 |
+
"num_experts": 32,
|
| 34 |
+
"norm_topk_prob": false,
|
| 35 |
+
"output_router_logits": false,
|
| 36 |
+
"router_aux_loss_coef": 0.001
|
| 37 |
+
}
|