Update config.json
Browse files- config.json +5 -7
config.json
CHANGED
|
@@ -1,11 +1,11 @@
|
|
| 1 |
{
|
| 2 |
"architectures": [
|
| 3 |
-
"
|
| 4 |
],
|
| 5 |
"auto_map": {
|
| 6 |
-
"AutoConfig": "
|
| 7 |
-
"AutoModel": "
|
| 8 |
-
"AutoModelForCausalLM": "
|
| 9 |
},
|
| 10 |
"attention_bias": false,
|
| 11 |
"attention_dropout": 0.0,
|
|
@@ -17,7 +17,7 @@
|
|
| 17 |
"intermediate_size": 8192,
|
| 18 |
"kv_lora_rank": 512,
|
| 19 |
"max_position_embeddings": 4096,
|
| 20 |
-
"model_type": "
|
| 21 |
"num_attention_heads": 16,
|
| 22 |
"num_key_value_heads": 16,
|
| 23 |
"num_hidden_layers": 32,
|
|
@@ -28,12 +28,10 @@
|
|
| 28 |
"rope_scaling": null,
|
| 29 |
"pretraining_tp": 1,
|
| 30 |
"rope_theta": 100000.0,
|
| 31 |
-
"sliding_window": 4096,
|
| 32 |
"tie_word_embeddings": true,
|
| 33 |
"torch_dtype": "bfloat16",
|
| 34 |
"transformers_version": "4.40.1",
|
| 35 |
"use_cache": true,
|
| 36 |
-
"use_sliding_window": false,
|
| 37 |
"v_head_dim": 128,
|
| 38 |
"vocab_size": 151936
|
| 39 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"architectures": [
|
| 3 |
+
"PLMForCausalLM"
|
| 4 |
],
|
| 5 |
"auto_map": {
|
| 6 |
+
"AutoConfig": "configuration_plm.PLMConfig",
|
| 7 |
+
"AutoModel": "modeling_plm.PLMModel",
|
| 8 |
+
"AutoModelForCausalLM": "modeling_plm.PLMForCausalLM"
|
| 9 |
},
|
| 10 |
"attention_bias": false,
|
| 11 |
"attention_dropout": 0.0,
|
|
|
|
| 17 |
"intermediate_size": 8192,
|
| 18 |
"kv_lora_rank": 512,
|
| 19 |
"max_position_embeddings": 4096,
|
| 20 |
+
"model_type": "plm",
|
| 21 |
"num_attention_heads": 16,
|
| 22 |
"num_key_value_heads": 16,
|
| 23 |
"num_hidden_layers": 32,
|
|
|
|
| 28 |
"rope_scaling": null,
|
| 29 |
"pretraining_tp": 1,
|
| 30 |
"rope_theta": 100000.0,
|
|
|
|
| 31 |
"tie_word_embeddings": true,
|
| 32 |
"torch_dtype": "bfloat16",
|
| 33 |
"transformers_version": "4.40.1",
|
| 34 |
"use_cache": true,
|
|
|
|
| 35 |
"v_head_dim": 128,
|
| 36 |
"vocab_size": 151936
|
| 37 |
}
|