Upload config.json
Browse files- config.json +43 -0
config.json
ADDED
|
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "/storage4/work/yamaguchi/model/JINIAC-5B-culturex-code0-9-lr-5e-5-aozora-wiki-kokkai-law-hanrei-5e-5",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"DeepseekForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_bias": false,
|
| 7 |
+
"attention_dropout": 0.0,
|
| 8 |
+
"auto_map": {
|
| 9 |
+
"AutoConfig": "configuration_deepseek.DeepseekConfig",
|
| 10 |
+
"AutoModel": "JINIAC/JINIAC-5B-culturex--modeling_deepseek.DeepseekModel",
|
| 11 |
+
"AutoModelForCausalLM": "modeling_deepseek.DeepseekForCausalLM"
|
| 12 |
+
},
|
| 13 |
+
"aux_loss_alpha": 0.001,
|
| 14 |
+
"bos_token_id": 1,
|
| 15 |
+
"eos_token_id": 2,
|
| 16 |
+
"first_k_dense_replace": 1,
|
| 17 |
+
"hidden_act": "silu",
|
| 18 |
+
"hidden_size": 2048,
|
| 19 |
+
"initializer_range": 0.02,
|
| 20 |
+
"intermediate_size": 10944,
|
| 21 |
+
"max_position_embeddings": 16384,
|
| 22 |
+
"model_type": "deepseek",
|
| 23 |
+
"moe_intermediate_size": 1408,
|
| 24 |
+
"moe_layer_freq": 1,
|
| 25 |
+
"n_routed_experts": 64,
|
| 26 |
+
"n_shared_experts": 2,
|
| 27 |
+
"norm_topk_prob": false,
|
| 28 |
+
"num_attention_heads": 16,
|
| 29 |
+
"num_experts_per_tok": 4,
|
| 30 |
+
"num_hidden_layers": 9,
|
| 31 |
+
"num_key_value_heads": 16,
|
| 32 |
+
"pretraining_tp": 1,
|
| 33 |
+
"rms_norm_eps": 1e-06,
|
| 34 |
+
"rope_scaling": null,
|
| 35 |
+
"rope_theta": 10000,
|
| 36 |
+
"scoring_func": "softmax",
|
| 37 |
+
"seq_aux": true,
|
| 38 |
+
"tie_word_embeddings": false,
|
| 39 |
+
"torch_dtype": "bfloat16",
|
| 40 |
+
"transformers_version": "4.40.2",
|
| 41 |
+
"use_cache": true,
|
| 42 |
+
"vocab_size": 59529
|
| 43 |
+
}
|