New version trained on 30k
Browse files- config.json +2 -7
- pytorch_model.bin +1 -1
config.json
CHANGED
|
@@ -12,7 +12,7 @@
|
|
| 12 |
"gradient_checkpointing": false,
|
| 13 |
"initializer_range": 0.02,
|
| 14 |
"layer_norm_epsilon": 1e-05,
|
| 15 |
-
"
|
| 16 |
"model_type": "gpt2",
|
| 17 |
"n_ctx": 2048,
|
| 18 |
"n_embd": 1536,
|
|
@@ -26,13 +26,8 @@
|
|
| 26 |
"resid_pdrop": 0.1,
|
| 27 |
"scale_attn_by_inverse_layer_idx": false,
|
| 28 |
"scale_attn_weights": true,
|
| 29 |
-
"summary_activation": null,
|
| 30 |
-
"summary_first_dropout": 0.1,
|
| 31 |
-
"summary_proj_to_labels": true,
|
| 32 |
-
"summary_type": "cls_index",
|
| 33 |
-
"summary_use_proj": true,
|
| 34 |
"torch_dtype": "float32",
|
| 35 |
-
"transformers_version": "4.27.
|
| 36 |
"use_cache": true,
|
| 37 |
"vocab_size": 50258
|
| 38 |
}
|
|
|
|
| 12 |
"gradient_checkpointing": false,
|
| 13 |
"initializer_range": 0.02,
|
| 14 |
"layer_norm_epsilon": 1e-05,
|
| 15 |
+
"max_length": 512,
|
| 16 |
"model_type": "gpt2",
|
| 17 |
"n_ctx": 2048,
|
| 18 |
"n_embd": 1536,
|
|
|
|
| 26 |
"resid_pdrop": 0.1,
|
| 27 |
"scale_attn_by_inverse_layer_idx": false,
|
| 28 |
"scale_attn_weights": true,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 29 |
"torch_dtype": "float32",
|
| 30 |
+
"transformers_version": "4.27.3",
|
| 31 |
"use_cache": true,
|
| 32 |
"vocab_size": 50258
|
| 33 |
}
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3141980445
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:88224460cdd1727998e3d0e9a12e7b1117d26d17f3a9285de6625724f6b58319
|
| 3 |
size 3141980445
|