Training in progress, step 200
Browse files- config.json +31 -0
- model.safetensors +3 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"HybridFourierLM"
|
| 4 |
+
],
|
| 5 |
+
"bos_token_id": 0,
|
| 6 |
+
"dropout": 0.05,
|
| 7 |
+
"dtype": "float32",
|
| 8 |
+
"eos_token_id": 0,
|
| 9 |
+
"latent_dim": 768,
|
| 10 |
+
"layer_types": [
|
| 11 |
+
"linear",
|
| 12 |
+
"linear",
|
| 13 |
+
"linear",
|
| 14 |
+
"softmax",
|
| 15 |
+
"linear",
|
| 16 |
+
"linear",
|
| 17 |
+
"linear",
|
| 18 |
+
"softmax",
|
| 19 |
+
"linear",
|
| 20 |
+
"linear",
|
| 21 |
+
"linear",
|
| 22 |
+
"softmax"
|
| 23 |
+
],
|
| 24 |
+
"model_type": "hybrid_fourier_lm",
|
| 25 |
+
"num_layers": 12,
|
| 26 |
+
"num_modes": 64,
|
| 27 |
+
"pad_token_id": 0,
|
| 28 |
+
"time_scale": 128.0,
|
| 29 |
+
"transformers_version": "4.56.0",
|
| 30 |
+
"vocab_size": 50277
|
| 31 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:66886050e435756ef5a7c49a69ae84363711c5f2bc7b3b5ebe3bf6a9bda5b749
|
| 3 |
+
size 579824888
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ec0634c3bc1f1b261fa029e521f51d3974d5a8f44775595be1925837769a398d
|
| 3 |
+
size 5841
|