[DEV]: Initial commit of base model.
Browse files- config.json +72 -0
- flax_model.msgpack +3 -0
- merges.txt +0 -0
- pytorch_model.bin +3 -0
- rust_model.ot +3 -0
- special_tokens_map.json +1 -0
- tokenizer_config.json +1 -0
- vocab.json +0 -0
config.json
ADDED
|
@@ -0,0 +1,72 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"global",
|
| 17 |
+
"local",
|
| 18 |
+
"global",
|
| 19 |
+
"local",
|
| 20 |
+
"global",
|
| 21 |
+
"local",
|
| 22 |
+
"global",
|
| 23 |
+
"local",
|
| 24 |
+
"global",
|
| 25 |
+
"local",
|
| 26 |
+
"global",
|
| 27 |
+
"local",
|
| 28 |
+
"global",
|
| 29 |
+
"local",
|
| 30 |
+
"global",
|
| 31 |
+
"local"
|
| 32 |
+
],
|
| 33 |
+
"attention_types": [
|
| 34 |
+
[
|
| 35 |
+
[
|
| 36 |
+
"global",
|
| 37 |
+
"local"
|
| 38 |
+
],
|
| 39 |
+
12
|
| 40 |
+
]
|
| 41 |
+
],
|
| 42 |
+
"bos_token_id": 50256,
|
| 43 |
+
"embed_dropout": 0,
|
| 44 |
+
"eos_token_id": 50256,
|
| 45 |
+
"gradient_checkpointing": false,
|
| 46 |
+
"hidden_size": 2048,
|
| 47 |
+
"initializer_range": 0.02,
|
| 48 |
+
"intermediate_size": null,
|
| 49 |
+
"layer_norm_epsilon": 1e-05,
|
| 50 |
+
"max_position_embeddings": 2048,
|
| 51 |
+
"model_type": "gpt_neo",
|
| 52 |
+
"num_heads": 16,
|
| 53 |
+
"num_layers": 24,
|
| 54 |
+
"resid_dropout": 0,
|
| 55 |
+
"summary_activation": null,
|
| 56 |
+
"summary_first_dropout": 0.1,
|
| 57 |
+
"summary_proj_to_labels": true,
|
| 58 |
+
"summary_type": "cls_index",
|
| 59 |
+
"summary_use_proj": true,
|
| 60 |
+
"task_specific_params": {
|
| 61 |
+
"text-generation": {
|
| 62 |
+
"do_sample": true,
|
| 63 |
+
"max_length": 50,
|
| 64 |
+
"temperature": 0.9
|
| 65 |
+
}
|
| 66 |
+
},
|
| 67 |
+
"tokenizer_class": "GPT2Tokenizer",
|
| 68 |
+
"transformers_version": "4.9.0.dev0",
|
| 69 |
+
"use_cache": true,
|
| 70 |
+
"vocab_size": 50257,
|
| 71 |
+
"window_size": 256
|
| 72 |
+
}
|
flax_model.msgpack
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:602bd11047e19395d0e1d24ef6c34cdde1d5cb0c77a2725f86e6869c839828f4
|
| 3 |
+
size 5262314590
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9df5c8861b5f7a1e6139ed957bad5d1e795827e54761a264655b0c0390c8dd70
|
| 3 |
+
size 5312753599
|
rust_model.ot
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ccd34b62f86e7c4e06821a9899473bec4a6c4baf18c8582ff2a665b78607ef1e
|
| 3 |
+
size 5312743379
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "unk_token": "<|endoftext|>"}
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"unk_token": "<|endoftext|>", "bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "add_prefix_space": false, "model_max_length": 2048, "special_tokens_map_file": null, "name_or_path": "gpt2"}
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|