Commit
•
d2a22b8
1
Parent(s):
f71d560
Upload model
Browse files- config.json +6 -17
- generation_config.json +3 -9
- pytorch_model.bin +2 -2
config.json
CHANGED
|
@@ -1,18 +1,15 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "/content/drive/MyDrive/nlp-bigsize/output
|
| 3 |
"activation_function": "gelu_new",
|
| 4 |
"architectures": [
|
| 5 |
"GPT2LMHeadModel"
|
| 6 |
],
|
| 7 |
"attn_pdrop": 0.1,
|
| 8 |
-
"bos_token_id":
|
| 9 |
-
"do_sample": true,
|
| 10 |
"embd_pdrop": 0.1,
|
| 11 |
-
"eos_token_id":
|
| 12 |
-
"gradient_checkpointing": false,
|
| 13 |
"initializer_range": 0.02,
|
| 14 |
"layer_norm_epsilon": 1e-05,
|
| 15 |
-
"max_length": 50,
|
| 16 |
"model_type": "gpt2",
|
| 17 |
"n_ctx": 1024,
|
| 18 |
"n_embd": 768,
|
|
@@ -20,10 +17,7 @@
|
|
| 20 |
"n_inner": null,
|
| 21 |
"n_layer": 12,
|
| 22 |
"n_positions": 1024,
|
| 23 |
-
"no_repeat_ngram_size": 3,
|
| 24 |
-
"num_beams": 5,
|
| 25 |
"reorder_and_upcast_attn": false,
|
| 26 |
-
"repetition_penalty": 3.0,
|
| 27 |
"resid_pdrop": 0.1,
|
| 28 |
"scale_attn_by_inverse_layer_idx": false,
|
| 29 |
"scale_attn_weights": true,
|
|
@@ -35,16 +29,11 @@
|
|
| 35 |
"task_specific_params": {
|
| 36 |
"text-generation": {
|
| 37 |
"do_sample": true,
|
| 38 |
-
"max_length": 50
|
| 39 |
-
"no_repeat_ngram_size": 3,
|
| 40 |
-
"num_beams": 5,
|
| 41 |
-
"repetition_penalty": 3.0,
|
| 42 |
-
"top_p": 0.95
|
| 43 |
}
|
| 44 |
},
|
| 45 |
-
"top_p": 0.95,
|
| 46 |
"torch_dtype": "float32",
|
| 47 |
-
"transformers_version": "4.27.
|
| 48 |
"use_cache": true,
|
| 49 |
-
"vocab_size":
|
| 50 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "/content/drive/MyDrive/nlp-bigsize/output/checkpoint-8800",
|
| 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,
|
|
|
|
| 17 |
"n_inner": null,
|
| 18 |
"n_layer": 12,
|
| 19 |
"n_positions": 1024,
|
|
|
|
|
|
|
| 20 |
"reorder_and_upcast_attn": false,
|
|
|
|
| 21 |
"resid_pdrop": 0.1,
|
| 22 |
"scale_attn_by_inverse_layer_idx": false,
|
| 23 |
"scale_attn_weights": 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": "4.27.3",
|
| 37 |
"use_cache": true,
|
| 38 |
+
"vocab_size": 50257
|
| 39 |
}
|
generation_config.json
CHANGED
|
@@ -1,12 +1,6 @@
|
|
| 1 |
{
|
| 2 |
"_from_model_config": true,
|
| 3 |
-
"bos_token_id":
|
| 4 |
-
"
|
| 5 |
-
"
|
| 6 |
-
"max_length": 50,
|
| 7 |
-
"no_repeat_ngram_size": 3,
|
| 8 |
-
"num_beams": 5,
|
| 9 |
-
"repetition_penalty": 3.0,
|
| 10 |
-
"top_p": 0.95,
|
| 11 |
-
"transformers_version": "4.27.2"
|
| 12 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 50256,
|
| 4 |
+
"eos_token_id": 50256,
|
| 5 |
+
"transformers_version": "4.27.3"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6 |
}
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6e96efd7222240e5cdcfd4cef0ad463b0a679a9d6fa5b4c9c725b259673ecb96
|
| 3 |
+
size 510395581
|