Upload 7 files
Browse files- code/inference.py +21 -0
- config.json +28 -0
- gptj.pt +3 -0
- merges.txt +0 -0
- special_tokens_map.json +1 -0
- tokenizer_config.json +1 -0
- vocab.json +0 -0
code/inference.py
ADDED
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import os
|
2 |
+
import torch
|
3 |
+
from transformers import AutoTokenizer, pipeline
|
4 |
+
|
5 |
+
GPT_WEIGHTS_NAME = "gpt.pt"
|
6 |
+
|
7 |
+
|
8 |
+
def model_fn(model_dir):
|
9 |
+
model = torch.load(os.path.join(model_dir, GPT_WEIGHTS_NAME))
|
10 |
+
tokenizer = AutoTokenizer.from_pretrained(model_dir)
|
11 |
+
|
12 |
+
if torch.cuda.is_available():
|
13 |
+
device = 0
|
14 |
+
else:
|
15 |
+
device = -1
|
16 |
+
|
17 |
+
generation = pipeline(
|
18 |
+
"text-generation", model=model, tokenizer=tokenizer, device=device
|
19 |
+
)
|
20 |
+
|
21 |
+
return generation
|
config.json
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "opt-350m",
|
3 |
+
"activation_dropout": 0.0,
|
4 |
+
"activation_function": "relu",
|
5 |
+
"architectures": [
|
6 |
+
"OPTForCausalLM"
|
7 |
+
],
|
8 |
+
"attention_dropout": 0.0,
|
9 |
+
"bos_token_id": 2,
|
10 |
+
"do_layer_norm_before": false,
|
11 |
+
"dropout": 0.1,
|
12 |
+
"eos_token_id": 2,
|
13 |
+
"ffn_dim": 4096,
|
14 |
+
"hidden_size": 1024,
|
15 |
+
"init_std": 0.02,
|
16 |
+
"layerdrop": 0.0,
|
17 |
+
"max_position_embeddings": 2048,
|
18 |
+
"model_type": "opt",
|
19 |
+
"num_attention_heads": 16,
|
20 |
+
"num_hidden_layers": 24,
|
21 |
+
"pad_token_id": 1,
|
22 |
+
"prefix": "</s>",
|
23 |
+
"torch_dtype": "float16",
|
24 |
+
"transformers_version": "4.20.0.dev0",
|
25 |
+
"use_cache": true,
|
26 |
+
"vocab_size": 50272,
|
27 |
+
"word_embed_proj_dim": 512
|
28 |
+
}
|
gptj.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d96052c3bc47377d93e0350190b6d057c491d683f515c87c024576b979454990
|
3 |
+
size 662549735
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"bos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "eos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "unk_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "pad_token": {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}}
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"errors": "replace", "unk_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "pad_token": {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": false, "add_bos_token": true, "special_tokens_map_file": null, "name_or_path": "patrickvonplaten/opt-30b"}
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|