Update config.json
Browse files- config.json +23 -26
config.json
CHANGED
@@ -1,28 +1,25 @@
|
|
1 |
{
|
2 |
-
"
|
3 |
-
|
4 |
-
"base_model_name_or_path": "line-corporation/japanese-large-lm-3.6b",
|
5 |
-
"bias": "none",
|
6 |
-
"fan_in_fan_out": false,
|
7 |
-
"inference_mode": true,
|
8 |
-
"init_lora_weights": true,
|
9 |
-
"layer_replication": null,
|
10 |
-
"layers_pattern": null,
|
11 |
-
"layers_to_transform": null,
|
12 |
-
"loftq_config": {},
|
13 |
-
"lora_alpha": 8,
|
14 |
-
"lora_dropout": 0.05,
|
15 |
-
"megatron_config": null,
|
16 |
-
"megatron_core": "megatron.core",
|
17 |
-
"modules_to_save": null,
|
18 |
-
"peft_type": "LORA",
|
19 |
-
"r": 4,
|
20 |
-
"rank_pattern": {},
|
21 |
-
"revision": null,
|
22 |
-
"target_modules": [
|
23 |
-
"query_key_value"
|
24 |
],
|
25 |
-
"
|
26 |
-
"
|
27 |
-
"
|
28 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
{
|
2 |
+
"architectures": [
|
3 |
+
"GPTNeoXForCausalLM"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
4 |
],
|
5 |
+
"bos_token_id": 2,
|
6 |
+
"classifier_dropout": 0.1,
|
7 |
+
"eos_token_id": 2,
|
8 |
+
"hidden_act": "gelu",
|
9 |
+
"hidden_size": 3072,
|
10 |
+
"initializer_range": 0.02,
|
11 |
+
"intermediate_size": 12288,
|
12 |
+
"layer_norm_eps": 1e-05,
|
13 |
+
"max_position_embeddings": 2048,
|
14 |
+
"model_type": "gpt_neox",
|
15 |
+
"num_attention_heads": 32,
|
16 |
+
"num_hidden_layers": 30,
|
17 |
+
"rotary_emb_base": 10000,
|
18 |
+
"rotary_pct": 1.0,
|
19 |
+
"tie_word_embeddings": true,
|
20 |
+
"torch_dtype": "float16",
|
21 |
+
"transformers_version": "4.29.2",
|
22 |
+
"use_cache": true,
|
23 |
+
"use_parallel_residual": false,
|
24 |
+
"vocab_size": 51200
|
25 |
+
}
|