Upload folder using huggingface_hub
Browse files- config.json +41 -9
- generation_config.json +1 -1
- model.safetensors +3 -0
- optimizer.pt +3 -0
- scheduler.pt +3 -0
config.json
CHANGED
|
@@ -1,30 +1,62 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "/
|
| 3 |
"architectures": [
|
| 4 |
"T5ForConditionalGeneration"
|
| 5 |
],
|
|
|
|
| 6 |
"d_ff": 1024,
|
| 7 |
"d_kv": 64,
|
| 8 |
-
"d_model":
|
| 9 |
"decoder_start_token_id": 0,
|
| 10 |
-
"dense_act_fn": "
|
| 11 |
"dropout_rate": 0.1,
|
| 12 |
"eos_token_id": 1,
|
| 13 |
-
"feed_forward_proj": "
|
| 14 |
"initializer_factor": 1.0,
|
| 15 |
"is_encoder_decoder": true,
|
| 16 |
-
"is_gated_act":
|
| 17 |
"layer_norm_epsilon": 1e-06,
|
| 18 |
"model_type": "t5",
|
| 19 |
"n_positions": 512,
|
| 20 |
-
"num_decoder_layers":
|
| 21 |
-
"num_heads":
|
| 22 |
-
"num_layers":
|
|
|
|
| 23 |
"pad_token_id": 0,
|
| 24 |
"relative_attention_max_distance": 128,
|
| 25 |
"relative_attention_num_buckets": 32,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 26 |
"torch_dtype": "float32",
|
| 27 |
-
"transformers_version": "4.
|
| 28 |
"use_cache": true,
|
| 29 |
"vocab_size": 10476
|
| 30 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "google/flan-t5-small",
|
| 3 |
"architectures": [
|
| 4 |
"T5ForConditionalGeneration"
|
| 5 |
],
|
| 6 |
+
"classifier_dropout": 0.0,
|
| 7 |
"d_ff": 1024,
|
| 8 |
"d_kv": 64,
|
| 9 |
+
"d_model": 512,
|
| 10 |
"decoder_start_token_id": 0,
|
| 11 |
+
"dense_act_fn": "gelu_new",
|
| 12 |
"dropout_rate": 0.1,
|
| 13 |
"eos_token_id": 1,
|
| 14 |
+
"feed_forward_proj": "gated-gelu",
|
| 15 |
"initializer_factor": 1.0,
|
| 16 |
"is_encoder_decoder": true,
|
| 17 |
+
"is_gated_act": true,
|
| 18 |
"layer_norm_epsilon": 1e-06,
|
| 19 |
"model_type": "t5",
|
| 20 |
"n_positions": 512,
|
| 21 |
+
"num_decoder_layers": 8,
|
| 22 |
+
"num_heads": 6,
|
| 23 |
+
"num_layers": 8,
|
| 24 |
+
"output_past": true,
|
| 25 |
"pad_token_id": 0,
|
| 26 |
"relative_attention_max_distance": 128,
|
| 27 |
"relative_attention_num_buckets": 32,
|
| 28 |
+
"task_specific_params": {
|
| 29 |
+
"summarization": {
|
| 30 |
+
"early_stopping": true,
|
| 31 |
+
"length_penalty": 2.0,
|
| 32 |
+
"max_length": 200,
|
| 33 |
+
"min_length": 30,
|
| 34 |
+
"no_repeat_ngram_size": 3,
|
| 35 |
+
"num_beams": 4,
|
| 36 |
+
"prefix": "summarize: "
|
| 37 |
+
},
|
| 38 |
+
"translation_en_to_de": {
|
| 39 |
+
"early_stopping": true,
|
| 40 |
+
"max_length": 300,
|
| 41 |
+
"num_beams": 4,
|
| 42 |
+
"prefix": "translate English to German: "
|
| 43 |
+
},
|
| 44 |
+
"translation_en_to_fr": {
|
| 45 |
+
"early_stopping": true,
|
| 46 |
+
"max_length": 300,
|
| 47 |
+
"num_beams": 4,
|
| 48 |
+
"prefix": "translate English to French: "
|
| 49 |
+
},
|
| 50 |
+
"translation_en_to_ro": {
|
| 51 |
+
"early_stopping": true,
|
| 52 |
+
"max_length": 300,
|
| 53 |
+
"num_beams": 4,
|
| 54 |
+
"prefix": "translate English to Romanian: "
|
| 55 |
+
}
|
| 56 |
+
},
|
| 57 |
+
"tie_word_embeddings": false,
|
| 58 |
"torch_dtype": "float32",
|
| 59 |
+
"transformers_version": "4.37.2",
|
| 60 |
"use_cache": true,
|
| 61 |
"vocab_size": 10476
|
| 62 |
}
|
generation_config.json
CHANGED
|
@@ -3,5 +3,5 @@
|
|
| 3 |
"decoder_start_token_id": 0,
|
| 4 |
"eos_token_id": 1,
|
| 5 |
"pad_token_id": 0,
|
| 6 |
-
"transformers_version": "4.
|
| 7 |
}
|
|
|
|
| 3 |
"decoder_start_token_id": 0,
|
| 4 |
"eos_token_id": 1,
|
| 5 |
"pad_token_id": 0,
|
| 6 |
+
"transformers_version": "4.37.2"
|
| 7 |
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7bfb559e935403c1fc8eea681aedc416a19289f0e974534f8640fc8ad1d50b58
|
| 3 |
+
size 219180456
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e68d3cf9ffcfed7aea384f75cc1aa14fd98e7764a71a60a8fbdf083a83a17654
|
| 3 |
+
size 438476026
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:90fe01f4456a43e02ad4520d2e3edee6be6eba9681601b93015a12834f675495
|
| 3 |
+
size 1192
|