Load Model
Browse files- config.json +52 -0
- generation_config.json +10 -0
- model.safetensors +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +13 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,52 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"activation_function": "gelu_new",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"GPTNeoForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_dropout": 0,
|
| 7 |
+
"attention_layers": [
|
| 8 |
+
"global",
|
| 9 |
+
"local",
|
| 10 |
+
"global",
|
| 11 |
+
"local",
|
| 12 |
+
"global",
|
| 13 |
+
"local",
|
| 14 |
+
"global",
|
| 15 |
+
"local"
|
| 16 |
+
],
|
| 17 |
+
"attention_types": [
|
| 18 |
+
[
|
| 19 |
+
[
|
| 20 |
+
"global",
|
| 21 |
+
"local"
|
| 22 |
+
],
|
| 23 |
+
4
|
| 24 |
+
]
|
| 25 |
+
],
|
| 26 |
+
"bos_token_id": 50256,
|
| 27 |
+
"classifier_dropout": 0.1,
|
| 28 |
+
"dtype": "float32",
|
| 29 |
+
"embed_dropout": 0,
|
| 30 |
+
"eos_token_id": 50256,
|
| 31 |
+
"gradient_checkpointing": false,
|
| 32 |
+
"hidden_size": 128,
|
| 33 |
+
"initializer_range": 0.02,
|
| 34 |
+
"intermediate_size": null,
|
| 35 |
+
"layer_norm_epsilon": 1e-05,
|
| 36 |
+
"max_position_embeddings": 2048,
|
| 37 |
+
"model_type": "gpt_neo",
|
| 38 |
+
"num_heads": 16,
|
| 39 |
+
"num_layers": 8,
|
| 40 |
+
"pad_token_id": 50256,
|
| 41 |
+
"resid_dropout": 0,
|
| 42 |
+
"summary_activation": null,
|
| 43 |
+
"summary_first_dropout": 0.1,
|
| 44 |
+
"summary_proj_to_labels": true,
|
| 45 |
+
"summary_type": "cls_index",
|
| 46 |
+
"summary_use_proj": true,
|
| 47 |
+
"tie_word_embeddings": true,
|
| 48 |
+
"transformers_version": "5.12.1",
|
| 49 |
+
"use_cache": false,
|
| 50 |
+
"vocab_size": 50257,
|
| 51 |
+
"window_size": 256
|
| 52 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 50256,
|
| 4 |
+
"eos_token_id": [
|
| 5 |
+
50256
|
| 6 |
+
],
|
| 7 |
+
"pad_token_id": 50256,
|
| 8 |
+
"transformers_version": "5.12.1",
|
| 9 |
+
"use_cache": true
|
| 10 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e402a7b7775adcde009f3a2aa4d88ac8c8f5267cee4329a7d7ff818b632b38f
|
| 3 |
+
size 33124616
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"backend": "tokenizers",
|
| 4 |
+
"bos_token": "<|endoftext|>",
|
| 5 |
+
"eos_token": "<|endoftext|>",
|
| 6 |
+
"errors": "replace",
|
| 7 |
+
"is_local": true,
|
| 8 |
+
"local_files_only": false,
|
| 9 |
+
"model_max_length": 2048,
|
| 10 |
+
"pad_token": "<|endoftext|>",
|
| 11 |
+
"tokenizer_class": "GPT2Tokenizer",
|
| 12 |
+
"unk_token": "<|endoftext|>"
|
| 13 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7477daadfb12e01b683ab3c58623520f10ad7a62854e7cb66342eea7e954cbc6
|
| 3 |
+
size 5201
|