Update Apollo-34B/config.json
Browse files- Apollo-34B/config.json +6 -10
Apollo-34B/config.json
CHANGED
|
@@ -1,13 +1,7 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "/sds_wangby/models/Yi-34B",
|
| 3 |
"architectures": [
|
| 4 |
-
"
|
| 5 |
],
|
| 6 |
-
"auto_map": {
|
| 7 |
-
"AutoConfig": "configuration_yi.YiConfig",
|
| 8 |
-
"AutoModel": "modeling_yi.YiModel",
|
| 9 |
-
"AutoModelForCausalLM": "modeling_yi.YiForCausalLM"
|
| 10 |
-
},
|
| 11 |
"bos_token_id": 1,
|
| 12 |
"eos_token_id": 2,
|
| 13 |
"hidden_act": "silu",
|
|
@@ -15,16 +9,18 @@
|
|
| 15 |
"initializer_range": 0.02,
|
| 16 |
"intermediate_size": 20480,
|
| 17 |
"max_position_embeddings": 4096,
|
| 18 |
-
"model_type": "
|
| 19 |
"num_attention_heads": 56,
|
| 20 |
"num_hidden_layers": 60,
|
| 21 |
"num_key_value_heads": 8,
|
| 22 |
"pad_token_id": 0,
|
|
|
|
| 23 |
"rms_norm_eps": 1e-05,
|
|
|
|
| 24 |
"rope_theta": 5000000.0,
|
| 25 |
"tie_word_embeddings": false,
|
| 26 |
"torch_dtype": "bfloat16",
|
| 27 |
-
"transformers_version": "4.
|
| 28 |
"use_cache": true,
|
| 29 |
"vocab_size": 64000
|
| 30 |
-
}
|
|
|
|
| 1 |
{
|
|
|
|
| 2 |
"architectures": [
|
| 3 |
+
"LlamaForCausalLM"
|
| 4 |
],
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
"bos_token_id": 1,
|
| 6 |
"eos_token_id": 2,
|
| 7 |
"hidden_act": "silu",
|
|
|
|
| 9 |
"initializer_range": 0.02,
|
| 10 |
"intermediate_size": 20480,
|
| 11 |
"max_position_embeddings": 4096,
|
| 12 |
+
"model_type": "llama",
|
| 13 |
"num_attention_heads": 56,
|
| 14 |
"num_hidden_layers": 60,
|
| 15 |
"num_key_value_heads": 8,
|
| 16 |
"pad_token_id": 0,
|
| 17 |
+
"pretraining_tp": 1,
|
| 18 |
"rms_norm_eps": 1e-05,
|
| 19 |
+
"rope_scaling": null,
|
| 20 |
"rope_theta": 5000000.0,
|
| 21 |
"tie_word_embeddings": false,
|
| 22 |
"torch_dtype": "bfloat16",
|
| 23 |
+
"transformers_version": "4.34.0",
|
| 24 |
"use_cache": true,
|
| 25 |
"vocab_size": 64000
|
| 26 |
+
}
|