Upload GPTNeoForCausalLM
Browse files- config.json +5 -25
- model.safetensors +2 -2
config.json
CHANGED
|
@@ -1,23 +1,11 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "/workspace/pretraining/local-models/training/2024-03-
|
| 3 |
"activation_function": "gelu_new",
|
| 4 |
"architectures": [
|
| 5 |
"GPTNeoForCausalLM"
|
| 6 |
],
|
| 7 |
"attention_dropout": 0,
|
| 8 |
"attention_layers": [
|
| 9 |
-
"global",
|
| 10 |
-
"local",
|
| 11 |
-
"global",
|
| 12 |
-
"local",
|
| 13 |
-
"global",
|
| 14 |
-
"local",
|
| 15 |
-
"global",
|
| 16 |
-
"local",
|
| 17 |
-
"global",
|
| 18 |
-
"local",
|
| 19 |
-
"global",
|
| 20 |
-
"local",
|
| 21 |
"global",
|
| 22 |
"local",
|
| 23 |
"global",
|
|
@@ -37,7 +25,7 @@
|
|
| 37 |
"global",
|
| 38 |
"local"
|
| 39 |
],
|
| 40 |
-
|
| 41 |
]
|
| 42 |
],
|
| 43 |
"bos_token_id": 50256,
|
|
@@ -45,28 +33,20 @@
|
|
| 45 |
"embed_dropout": 0,
|
| 46 |
"eos_token_id": 50256,
|
| 47 |
"gradient_checkpointing": false,
|
| 48 |
-
"hidden_size":
|
| 49 |
"initializer_range": 0.02,
|
| 50 |
"intermediate_size": null,
|
| 51 |
"layer_norm_epsilon": 1e-05,
|
| 52 |
"max_position_embeddings": 2048,
|
| 53 |
"model_type": "gpt_neo",
|
| 54 |
-
"num_heads":
|
| 55 |
-
"num_layers":
|
| 56 |
"resid_dropout": 0,
|
| 57 |
"summary_activation": null,
|
| 58 |
"summary_first_dropout": 0.1,
|
| 59 |
"summary_proj_to_labels": true,
|
| 60 |
"summary_type": "cls_index",
|
| 61 |
"summary_use_proj": true,
|
| 62 |
-
"task_specific_params": {
|
| 63 |
-
"text-generation": {
|
| 64 |
-
"do_sample": true,
|
| 65 |
-
"max_length": 50,
|
| 66 |
-
"temperature": 0.9
|
| 67 |
-
}
|
| 68 |
-
},
|
| 69 |
-
"tokenizer_class": "GPT2Tokenizer",
|
| 70 |
"torch_dtype": "float32",
|
| 71 |
"transformers_version": "4.38.0",
|
| 72 |
"use_cache": true,
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "/workspace/pretraining/local-models/training/2024-03-14_01-13-50",
|
| 3 |
"activation_function": "gelu_new",
|
| 4 |
"architectures": [
|
| 5 |
"GPTNeoForCausalLM"
|
| 6 |
],
|
| 7 |
"attention_dropout": 0,
|
| 8 |
"attention_layers": [
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 9 |
"global",
|
| 10 |
"local",
|
| 11 |
"global",
|
|
|
|
| 25 |
"global",
|
| 26 |
"local"
|
| 27 |
],
|
| 28 |
+
6
|
| 29 |
]
|
| 30 |
],
|
| 31 |
"bos_token_id": 50256,
|
|
|
|
| 33 |
"embed_dropout": 0,
|
| 34 |
"eos_token_id": 50256,
|
| 35 |
"gradient_checkpointing": false,
|
| 36 |
+
"hidden_size": 768,
|
| 37 |
"initializer_range": 0.02,
|
| 38 |
"intermediate_size": null,
|
| 39 |
"layer_norm_epsilon": 1e-05,
|
| 40 |
"max_position_embeddings": 2048,
|
| 41 |
"model_type": "gpt_neo",
|
| 42 |
+
"num_heads": 12,
|
| 43 |
+
"num_layers": 12,
|
| 44 |
"resid_dropout": 0,
|
| 45 |
"summary_activation": null,
|
| 46 |
"summary_first_dropout": 0.1,
|
| 47 |
"summary_proj_to_labels": true,
|
| 48 |
"summary_type": "cls_index",
|
| 49 |
"summary_use_proj": true,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 50 |
"torch_dtype": "float32",
|
| 51 |
"transformers_version": "4.38.0",
|
| 52 |
"use_cache": true,
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c202093d2773a3b9816c689add24a9aa5845ba244e47154d29d710982de767ec
|
| 3 |
+
size 500811336
|