Upload GPTNeoForCausalLM
Browse files- config.json +68 -0
- generation_config.json +6 -0
- model.safetensors +3 -0
config.json
ADDED
|
@@ -0,0 +1,68 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "/kaggle/input/gemma-sft/saves_genma/checkpoint-4400",
|
| 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",
|
| 24 |
+
"local",
|
| 25 |
+
"global",
|
| 26 |
+
"local",
|
| 27 |
+
"global",
|
| 28 |
+
"local",
|
| 29 |
+
"global",
|
| 30 |
+
"local",
|
| 31 |
+
"global",
|
| 32 |
+
"local"
|
| 33 |
+
],
|
| 34 |
+
"attention_types": [
|
| 35 |
+
[
|
| 36 |
+
[
|
| 37 |
+
"global",
|
| 38 |
+
"local"
|
| 39 |
+
],
|
| 40 |
+
12
|
| 41 |
+
]
|
| 42 |
+
],
|
| 43 |
+
"bos_token_id": 50256,
|
| 44 |
+
"classifier_dropout": 0.1,
|
| 45 |
+
"embed_dropout": 0,
|
| 46 |
+
"eos_token_id": 50256,
|
| 47 |
+
"gradient_checkpointing": false,
|
| 48 |
+
"hidden_size": 1024,
|
| 49 |
+
"initializer_range": 0.02,
|
| 50 |
+
"intermediate_size": null,
|
| 51 |
+
"layer_norm_epsilon": 1e-05,
|
| 52 |
+
"max_position_embeddings": 2048,
|
| 53 |
+
"model_friendly_id": "PT_GPTNEO350_ATG",
|
| 54 |
+
"model_type": "gpt_neo",
|
| 55 |
+
"num_heads": 16,
|
| 56 |
+
"num_layers": 24,
|
| 57 |
+
"resid_dropout": 0,
|
| 58 |
+
"summary_activation": null,
|
| 59 |
+
"summary_first_dropout": 0.1,
|
| 60 |
+
"summary_proj_to_labels": true,
|
| 61 |
+
"summary_type": "cls_index",
|
| 62 |
+
"summary_use_proj": true,
|
| 63 |
+
"torch_dtype": "float32",
|
| 64 |
+
"transformers_version": "4.39.3",
|
| 65 |
+
"use_cache": false,
|
| 66 |
+
"vocab_size": 50257,
|
| 67 |
+
"window_size": 256
|
| 68 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 50256,
|
| 4 |
+
"eos_token_id": 50256,
|
| 5 |
+
"transformers_version": "4.39.3"
|
| 6 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:373c99ebe2de14eb1661a38966bb3bfdff1c0793833b1a8e241e2722253e7af1
|
| 3 |
+
size 1423226392
|