add model
Browse files- config.json +96 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +5 -0
- tokenizer.json +0 -0
- tokenizer_config.json +9 -0
config.json
ADDED
|
@@ -0,0 +1,96 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "EleutherAI/pythia-1.3b-deduped",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"GPTNeoXForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"bad_words_ids": [
|
| 7 |
+
[
|
| 8 |
+
434,
|
| 9 |
+
15694,
|
| 10 |
+
66,
|
| 11 |
+
27,
|
| 12 |
+
209
|
| 13 |
+
],
|
| 14 |
+
[
|
| 15 |
+
15362
|
| 16 |
+
],
|
| 17 |
+
[
|
| 18 |
+
1713
|
| 19 |
+
],
|
| 20 |
+
[
|
| 21 |
+
1713,
|
| 22 |
+
64
|
| 23 |
+
],
|
| 24 |
+
[
|
| 25 |
+
1713,
|
| 26 |
+
876
|
| 27 |
+
],
|
| 28 |
+
[
|
| 29 |
+
2016,
|
| 30 |
+
251,
|
| 31 |
+
857,
|
| 32 |
+
75,
|
| 33 |
+
9194,
|
| 34 |
+
35478
|
| 35 |
+
],
|
| 36 |
+
[
|
| 37 |
+
2391
|
| 38 |
+
],
|
| 39 |
+
[
|
| 40 |
+
20340
|
| 41 |
+
],
|
| 42 |
+
[
|
| 43 |
+
33021
|
| 44 |
+
],
|
| 45 |
+
[
|
| 46 |
+
2391,
|
| 47 |
+
1051
|
| 48 |
+
],
|
| 49 |
+
[
|
| 50 |
+
5638
|
| 51 |
+
],
|
| 52 |
+
[
|
| 53 |
+
2391,
|
| 54 |
+
20340
|
| 55 |
+
],
|
| 56 |
+
[
|
| 57 |
+
5638,
|
| 58 |
+
537
|
| 59 |
+
],
|
| 60 |
+
[
|
| 61 |
+
1559,
|
| 62 |
+
2345
|
| 63 |
+
],
|
| 64 |
+
[
|
| 65 |
+
1559,
|
| 66 |
+
7849
|
| 67 |
+
],
|
| 68 |
+
[
|
| 69 |
+
1559,
|
| 70 |
+
17379
|
| 71 |
+
],
|
| 72 |
+
[
|
| 73 |
+
25321,
|
| 74 |
+
4611
|
| 75 |
+
]
|
| 76 |
+
],
|
| 77 |
+
"bos_token_id": 0,
|
| 78 |
+
"eos_token_id": 0,
|
| 79 |
+
"hidden_act": "gelu",
|
| 80 |
+
"hidden_size": 2048,
|
| 81 |
+
"initializer_range": 0.02,
|
| 82 |
+
"intermediate_size": 8192,
|
| 83 |
+
"layer_norm_eps": 1e-05,
|
| 84 |
+
"max_position_embeddings": 2048,
|
| 85 |
+
"model_type": "gpt_neox",
|
| 86 |
+
"num_attention_heads": 16,
|
| 87 |
+
"num_hidden_layers": 24,
|
| 88 |
+
"rotary_emb_base": 10000,
|
| 89 |
+
"rotary_pct": 0.25,
|
| 90 |
+
"tie_word_embeddings": false,
|
| 91 |
+
"torch_dtype": "float16",
|
| 92 |
+
"transformers_version": "4.25.1",
|
| 93 |
+
"use_cache": true,
|
| 94 |
+
"use_parallel_residual": true,
|
| 95 |
+
"vocab_size": 50304
|
| 96 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3228245a35970cafbebea523525daf888f8a04c433ca2e277883b0ad98da96c3
|
| 3 |
+
size 2930076797
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<|endoftext|>",
|
| 3 |
+
"eos_token": "<|endoftext|>",
|
| 4 |
+
"unk_token": "<|endoftext|>"
|
| 5 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"bos_token": "<|endoftext|>",
|
| 4 |
+
"eos_token": "<|endoftext|>",
|
| 5 |
+
"name_or_path": "EleutherAI/gpt-neox-20b",
|
| 6 |
+
"special_tokens_map_file": "/fsx/home-hailey/.cache/huggingface/hub/models--EleutherAI--gpt-neox-20b/snapshots/3523781c8df75f7741687a4284f6f70e1afa12f4/special_tokens_map.json",
|
| 7 |
+
"tokenizer_class": "GPTNeoXTokenizer",
|
| 8 |
+
"unk_token": "<|endoftext|>"
|
| 9 |
+
}
|