Upload folder using huggingface_hub
Browse files- config.json +54 -0
- generation_config.json +9 -0
- model.safetensors +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +12 -0
- training_state.pt +3 -0
config.json
ADDED
|
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"activation_function": "gelu_new",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"GPTNeoForCausalLMTiered"
|
| 5 |
+
],
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"attention_layers": [
|
| 8 |
+
"global",
|
| 9 |
+
"local",
|
| 10 |
+
"global",
|
| 11 |
+
"local",
|
| 12 |
+
"global",
|
| 13 |
+
"local",
|
| 14 |
+
"global",
|
| 15 |
+
"local",
|
| 16 |
+
"global",
|
| 17 |
+
"local",
|
| 18 |
+
"global",
|
| 19 |
+
"local",
|
| 20 |
+
"global",
|
| 21 |
+
"local",
|
| 22 |
+
"global",
|
| 23 |
+
"local"
|
| 24 |
+
],
|
| 25 |
+
"attention_types": [
|
| 26 |
+
[
|
| 27 |
+
[
|
| 28 |
+
"global",
|
| 29 |
+
"local"
|
| 30 |
+
],
|
| 31 |
+
8
|
| 32 |
+
]
|
| 33 |
+
],
|
| 34 |
+
"bos_token_id": 50256,
|
| 35 |
+
"classifier_dropout": 0.1,
|
| 36 |
+
"dtype": "float32",
|
| 37 |
+
"embed_dropout": 0.0,
|
| 38 |
+
"eos_token_id": 50256,
|
| 39 |
+
"hidden_size": 1344,
|
| 40 |
+
"initializer_range": 0.02,
|
| 41 |
+
"intermediate_size": 10752,
|
| 42 |
+
"layer_norm_epsilon": 1e-05,
|
| 43 |
+
"max_position_embeddings": 2048,
|
| 44 |
+
"model_type": "gpt_neo",
|
| 45 |
+
"num_heads": 16,
|
| 46 |
+
"num_layers": 16,
|
| 47 |
+
"pad_token_id": null,
|
| 48 |
+
"resid_dropout": 0.0,
|
| 49 |
+
"tie_word_embeddings": true,
|
| 50 |
+
"transformers_version": "5.5.4",
|
| 51 |
+
"use_cache": false,
|
| 52 |
+
"vocab_size": 50257,
|
| 53 |
+
"window_size": 256
|
| 54 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 50256,
|
| 4 |
+
"eos_token_id": 50256,
|
| 5 |
+
"output_attentions": false,
|
| 6 |
+
"output_hidden_states": false,
|
| 7 |
+
"transformers_version": "5.5.4",
|
| 8 |
+
"use_cache": false
|
| 9 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bcb2a7470552f20554bdbd5f432e17de4d851afe73da314dee13de248022214a
|
| 3 |
+
size 2594741052
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"backend": "tokenizers",
|
| 4 |
+
"bos_token": "<|endoftext|>",
|
| 5 |
+
"eos_token": "<|endoftext|>",
|
| 6 |
+
"errors": "replace",
|
| 7 |
+
"is_local": false,
|
| 8 |
+
"model_max_length": 1024,
|
| 9 |
+
"pad_token": "<|endoftext|>",
|
| 10 |
+
"tokenizer_class": "GPT2Tokenizer",
|
| 11 |
+
"unk_token": "<|endoftext|>"
|
| 12 |
+
}
|
training_state.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:40642527099cb731d6fb14b5efbcc830d1843ec16eb789e75aaeb129f4a3f21c
|
| 3 |
+
size 5189626104
|