Instructions to use Ella01/my_awesome_mlm_model with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Ella01/my_awesome_mlm_model with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("fill-mask", model="Ella01/my_awesome_mlm_model")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForMaskedLM tokenizer = AutoTokenizer.from_pretrained("Ella01/my_awesome_mlm_model") model = AutoModelForMaskedLM.from_pretrained("Ella01/my_awesome_mlm_model", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Training in progress, step 12
Browse files
config.json
ADDED
|
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "distilroberta-base",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"RobertaForMaskedLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"classifier_dropout": null,
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"hidden_act": "gelu",
|
| 11 |
+
"hidden_dropout_prob": 0.1,
|
| 12 |
+
"hidden_size": 768,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 3072,
|
| 15 |
+
"layer_norm_eps": 1e-05,
|
| 16 |
+
"max_position_embeddings": 514,
|
| 17 |
+
"model_type": "roberta",
|
| 18 |
+
"num_attention_heads": 12,
|
| 19 |
+
"num_hidden_layers": 6,
|
| 20 |
+
"pad_token_id": 1,
|
| 21 |
+
"position_embedding_type": "absolute",
|
| 22 |
+
"torch_dtype": "float32",
|
| 23 |
+
"transformers_version": "4.42.4",
|
| 24 |
+
"type_vocab_size": 1,
|
| 25 |
+
"use_cache": true,
|
| 26 |
+
"vocab_size": 50265
|
| 27 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:81237e2870e7612d65c10e0fd265f95f48b2f60b37373724a9ca8401a3b56baa
|
| 3 |
+
size 328693404
|
runs/Jul30_07-47-27_34ce077ed891/events.out.tfevents.1722325667.34ce077ed891.25867.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c89a418e0f6efa780a04a94f9ad763145e4142159288392059e58cbaa10fbf9f
|
| 3 |
+
size 4850
|
runs/Jul30_07-49-38_34ce077ed891/events.out.tfevents.1722325780.34ce077ed891.25867.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:95c511feb1b328cfb069a3ebd9e67d232795489942c32caa8a4b1dbb0ba5b409
|
| 3 |
+
size 5382
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:903ba237b4d5a7e139eb070dd09dcaf088cac9355dd4b3eff7cb0e0476ba15ca
|
| 3 |
+
size 5112
|