Upload model
Browse files- config.json +8 -1
- model.safetensors +1 -1
config.json
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "/pretraining/local-models/training/2024-01-
|
| 3 |
"activation_function": "gelu_new",
|
| 4 |
"architectures": [
|
| 5 |
"GPT2LMHeadModel"
|
|
@@ -11,6 +11,7 @@
|
|
| 11 |
"initializer_range": 0.02,
|
| 12 |
"layer_norm_epsilon": 1e-05,
|
| 13 |
"model_type": "gpt2",
|
|
|
|
| 14 |
"n_embd": 768,
|
| 15 |
"n_head": 12,
|
| 16 |
"n_inner": null,
|
|
@@ -25,6 +26,12 @@
|
|
| 25 |
"summary_proj_to_labels": true,
|
| 26 |
"summary_type": "cls_index",
|
| 27 |
"summary_use_proj": true,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 28 |
"torch_dtype": "float32",
|
| 29 |
"transformers_version": "4.34.1",
|
| 30 |
"use_cache": true,
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "/pretraining/local-models/training/2024-01-14_12-04-29",
|
| 3 |
"activation_function": "gelu_new",
|
| 4 |
"architectures": [
|
| 5 |
"GPT2LMHeadModel"
|
|
|
|
| 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,
|
|
|
|
| 26 |
"summary_proj_to_labels": true,
|
| 27 |
"summary_type": "cls_index",
|
| 28 |
"summary_use_proj": true,
|
| 29 |
+
"task_specific_params": {
|
| 30 |
+
"text-generation": {
|
| 31 |
+
"do_sample": true,
|
| 32 |
+
"max_length": 50
|
| 33 |
+
}
|
| 34 |
+
},
|
| 35 |
"torch_dtype": "float32",
|
| 36 |
"transformers_version": "4.34.1",
|
| 37 |
"use_cache": true,
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 469421488
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ce6163504ef7e515404253557cdf01f9dc510e789d72848c34f1f699c9f7be8f
|
| 3 |
size 469421488
|