Commit
•
5fbf3f6
1
Parent(s):
cb0b61c
Upload config
Browse files- config.json +2 -11
config.json
CHANGED
|
@@ -1,38 +1,29 @@
|
|
| 1 |
{
|
| 2 |
-
"activation_function": "silu",
|
| 3 |
"architectures": [
|
| 4 |
"LlamaForCausalLM"
|
| 5 |
],
|
| 6 |
"attention_bias": false,
|
| 7 |
"attention_dropout": 0.0,
|
| 8 |
-
"auto_map": {
|
| 9 |
-
"AutoConfig": "configuration_exaone.ExaoneConfig",
|
| 10 |
-
"AutoModelForCausalLM": "modeling_exaone.ExaoneForCausalLM",
|
| 11 |
-
"AutoModelForSequenceClassification": "modeling_exaone.ExaoneForSequenceClassification"
|
| 12 |
-
},
|
| 13 |
"bos_token_id": 1,
|
| 14 |
-
"embed_dropout": 0.0,
|
| 15 |
"eos_token_id": 361,
|
| 16 |
"hidden_act": "silu",
|
| 17 |
"hidden_size": 4096,
|
| 18 |
"initializer_range": 0.02,
|
| 19 |
"intermediate_size": 14336,
|
| 20 |
-
"layer_norm_epsilon": 1e-05,
|
| 21 |
"max_position_embeddings": 4096,
|
| 22 |
"mlp_bias": false,
|
| 23 |
"model_type": "llama",
|
| 24 |
"num_attention_heads": 32,
|
| 25 |
"num_hidden_layers": 32,
|
| 26 |
"num_key_value_heads": 8,
|
| 27 |
-
"num_layers": 32,
|
| 28 |
"pad_token_id": 0,
|
| 29 |
"pretraining_tp": 1,
|
| 30 |
-
"rms_norm_eps": 1e-
|
| 31 |
"rope_scaling": null,
|
| 32 |
"rope_theta": 500000.0,
|
| 33 |
"tie_word_embeddings": false,
|
| 34 |
"torch_dtype": "float32",
|
| 35 |
-
"transformers_version": "4.
|
| 36 |
"use_cache": true,
|
| 37 |
"vocab_size": 102400
|
| 38 |
}
|
|
|
|
| 1 |
{
|
|
|
|
| 2 |
"architectures": [
|
| 3 |
"LlamaForCausalLM"
|
| 4 |
],
|
| 5 |
"attention_bias": false,
|
| 6 |
"attention_dropout": 0.0,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7 |
"bos_token_id": 1,
|
|
|
|
| 8 |
"eos_token_id": 361,
|
| 9 |
"hidden_act": "silu",
|
| 10 |
"hidden_size": 4096,
|
| 11 |
"initializer_range": 0.02,
|
| 12 |
"intermediate_size": 14336,
|
|
|
|
| 13 |
"max_position_embeddings": 4096,
|
| 14 |
"mlp_bias": false,
|
| 15 |
"model_type": "llama",
|
| 16 |
"num_attention_heads": 32,
|
| 17 |
"num_hidden_layers": 32,
|
| 18 |
"num_key_value_heads": 8,
|
|
|
|
| 19 |
"pad_token_id": 0,
|
| 20 |
"pretraining_tp": 1,
|
| 21 |
+
"rms_norm_eps": 1e-05,
|
| 22 |
"rope_scaling": null,
|
| 23 |
"rope_theta": 500000.0,
|
| 24 |
"tie_word_embeddings": false,
|
| 25 |
"torch_dtype": "float32",
|
| 26 |
+
"transformers_version": "4.44.2",
|
| 27 |
"use_cache": true,
|
| 28 |
"vocab_size": 102400
|
| 29 |
}
|