Upload folder using huggingface_hub
Browse files
compiled/5035a6f79cca7fa112c9.neff
ADDED
Binary file (482 kB). View file
|
|
compiled/65afd769ec7f5a49d6a8.neff
ADDED
Binary file (503 kB). View file
|
|
compiled/b545c1cb1564bcb89ac5.neff
ADDED
Binary file (482 kB). View file
|
|
compiled/e96bdbcbf7147fef9757.neff
ADDED
Binary file (544 kB). View file
|
|
config.json
ADDED
@@ -0,0 +1,49 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "gpt2",
|
3 |
+
"activation_function": "gelu_new",
|
4 |
+
"architectures": [
|
5 |
+
"GPT2LMHeadModel"
|
6 |
+
],
|
7 |
+
"attn_pdrop": 0.1,
|
8 |
+
"bos_token_id": 50256,
|
9 |
+
"embd_pdrop": 0.1,
|
10 |
+
"eos_token_id": 50256,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"layer_norm_epsilon": 1e-05,
|
13 |
+
"model_type": "gpt2",
|
14 |
+
"n_ctx": 1024,
|
15 |
+
"n_embd": 768,
|
16 |
+
"n_head": 12,
|
17 |
+
"n_inner": null,
|
18 |
+
"n_layer": 12,
|
19 |
+
"n_positions": 1024,
|
20 |
+
"neuron": {
|
21 |
+
"auto_cast_type": "fp32",
|
22 |
+
"batch_size": 1,
|
23 |
+
"checkpoint_id": "gpt2",
|
24 |
+
"checkpoint_revision": "11c5a3d5811f50298f278a704980280950aedb10",
|
25 |
+
"compiler_type": "neuronx-cc",
|
26 |
+
"compiler_version": "2.12.54.0+f631c2365",
|
27 |
+
"num_cores": 2,
|
28 |
+
"sequence_length": 1024,
|
29 |
+
"task": "text-generation"
|
30 |
+
},
|
31 |
+
"reorder_and_upcast_attn": false,
|
32 |
+
"resid_pdrop": 0.1,
|
33 |
+
"scale_attn_by_inverse_layer_idx": false,
|
34 |
+
"scale_attn_weights": true,
|
35 |
+
"summary_activation": null,
|
36 |
+
"summary_first_dropout": 0.1,
|
37 |
+
"summary_proj_to_labels": true,
|
38 |
+
"summary_type": "cls_index",
|
39 |
+
"summary_use_proj": true,
|
40 |
+
"task_specific_params": {
|
41 |
+
"text-generation": {
|
42 |
+
"do_sample": true,
|
43 |
+
"max_length": 50
|
44 |
+
}
|
45 |
+
},
|
46 |
+
"transformers_version": "4.36.2",
|
47 |
+
"use_cache": true,
|
48 |
+
"vocab_size": 50257
|
49 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 50256,
|
4 |
+
"eos_token_id": 50256,
|
5 |
+
"transformers_version": "4.36.2"
|
6 |
+
}
|