Dainty-blaze-127 training run with smaller t5-efficient-mini model
Browse files- config.json +9 -40
- onnx/decoder_model.onnx +2 -2
- onnx/decoder_model_merged.onnx +2 -2
- onnx/decoder_model_merged_quantized.onnx +2 -2
- onnx/decoder_model_quantized.onnx +2 -2
- onnx/decoder_with_past_model.onnx +2 -2
- onnx/decoder_with_past_model_quantized.onnx +2 -2
- onnx/encoder_model.onnx +2 -2
- onnx/encoder_model_quantized.onnx +2 -2
config.json
CHANGED
|
@@ -1,60 +1,29 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "
|
| 3 |
"architectures": [
|
| 4 |
"T5ForConditionalGeneration"
|
| 5 |
],
|
| 6 |
"classifier_dropout": 0.0,
|
| 7 |
-
"d_ff":
|
| 8 |
"d_kv": 64,
|
| 9 |
-
"d_model":
|
| 10 |
"decoder_start_token_id": 0,
|
| 11 |
-
"dense_act_fn": "
|
| 12 |
"dropout_rate": 0.1,
|
| 13 |
"eos_token_id": 1,
|
| 14 |
-
"feed_forward_proj": "
|
| 15 |
"initializer_factor": 1.0,
|
| 16 |
"is_encoder_decoder": true,
|
| 17 |
-
"is_gated_act":
|
| 18 |
"layer_norm_epsilon": 1e-06,
|
| 19 |
"model_type": "t5",
|
| 20 |
"n_positions": 512,
|
| 21 |
-
"num_decoder_layers":
|
| 22 |
-
"num_heads":
|
| 23 |
-
"num_layers":
|
| 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 |
"transformers_version": "4.43.4",
|
| 59 |
"use_cache": true,
|
| 60 |
"vocab_size": 32128
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "dainty-blaze-127",
|
| 3 |
"architectures": [
|
| 4 |
"T5ForConditionalGeneration"
|
| 5 |
],
|
| 6 |
"classifier_dropout": 0.0,
|
| 7 |
+
"d_ff": 1536,
|
| 8 |
"d_kv": 64,
|
| 9 |
+
"d_model": 384,
|
| 10 |
"decoder_start_token_id": 0,
|
| 11 |
+
"dense_act_fn": "relu",
|
| 12 |
"dropout_rate": 0.1,
|
| 13 |
"eos_token_id": 1,
|
| 14 |
+
"feed_forward_proj": "relu",
|
| 15 |
"initializer_factor": 1.0,
|
| 16 |
"is_encoder_decoder": true,
|
| 17 |
+
"is_gated_act": false,
|
| 18 |
"layer_norm_epsilon": 1e-06,
|
| 19 |
"model_type": "t5",
|
| 20 |
"n_positions": 512,
|
| 21 |
+
"num_decoder_layers": 4,
|
| 22 |
+
"num_heads": 8,
|
| 23 |
+
"num_layers": 4,
|
|
|
|
| 24 |
"pad_token_id": 0,
|
| 25 |
"relative_attention_max_distance": 128,
|
| 26 |
"relative_attention_num_buckets": 32,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 27 |
"transformers_version": "4.43.4",
|
| 28 |
"use_cache": true,
|
| 29 |
"vocab_size": 32128
|
onnx/decoder_model.onnx
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:f338e2fd5d608d3932a44c6eef342310f8973f79bd4ede58414ef0fa6e918eff
|
| 3 |
+
size 93530494
|
onnx/decoder_model_merged.onnx
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:cdec216e76bba9a74c55dff75a8951ebb0c36082ebc323ca3fc4135463ccde90
|
| 3 |
+
size 93654272
|
onnx/decoder_model_merged_quantized.onnx
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 sha256:0f9fbbce2faee126b4588287d30aa5f35d1a8aa7f0d716bba85b441fcea69b2b
|
| 3 |
+
size 73166883
|
onnx/decoder_model_quantized.onnx
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 sha256:5049ee748c4680c503fcbf681ca8843c4f8480b0ed7be2ba457af64b76b23356
|
| 3 |
+
size 73001844
|
onnx/decoder_with_past_model.onnx
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 sha256:13263ae355c4e564ae4e2d5210516b025a5101769cccbbe3521672a50bc1ded0
|
| 3 |
+
size 87218051
|
onnx/decoder_with_past_model_quantized.onnx
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 sha256:5071cad146336bbc0bf18efe3d4f0577e45cc30edd8ab3a7da51dc1e9f012dcc
|
| 3 |
+
size 71379586
|
onnx/encoder_model.onnx
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 sha256:8874a6feb8aece3822e76fe704f471221394091c26554bff67aba99054c95372
|
| 3 |
+
size 80882463
|
onnx/encoder_model_quantized.onnx
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:aeacd4d59b8863cefd1385e19ca1506edfb466837ad982821636f481bed6769c
|
| 3 |
+
size 20382160
|