Training in progress, step 625
Browse files- config.json +1 -1
- pytorch_model.bin +1 -1
- tokenizer.json +25 -4
- tokenizer_config.json +2 -0
- training_args.bin +2 -2
config.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{}
|
|
|
1 |
+
{"d_model": 768, "n_layer": 24, "vocab_size": 50277, "ssm_cfg": {}, "rms_norm": true, "residual_in_fp32": true, "fused_add_norm": true, "pad_vocab_size_multiple": 8, "tie_embeddings": true}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 516640282
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c886a40228ee702faa79028fcba8ed8c0a916e29a121d33f5556b4f8053e0845
|
3 |
size 516640282
|
tokenizer.json
CHANGED
@@ -239,10 +239,30 @@
|
|
239 |
"use_regex": true
|
240 |
},
|
241 |
"post_processor": {
|
242 |
-
"type": "
|
243 |
-
"
|
244 |
-
|
245 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
246 |
},
|
247 |
"decoder": {
|
248 |
"type": "ByteLevel",
|
@@ -258,6 +278,7 @@
|
|
258 |
"end_of_word_suffix": null,
|
259 |
"fuse_unk": false,
|
260 |
"byte_fallback": false,
|
|
|
261 |
"vocab": {
|
262 |
"<|endoftext|>": 0,
|
263 |
"<|padding|>": 1,
|
|
|
239 |
"use_regex": true
|
240 |
},
|
241 |
"post_processor": {
|
242 |
+
"type": "TemplateProcessing",
|
243 |
+
"single": [
|
244 |
+
{
|
245 |
+
"Sequence": {
|
246 |
+
"id": "A",
|
247 |
+
"type_id": 0
|
248 |
+
}
|
249 |
+
}
|
250 |
+
],
|
251 |
+
"pair": [
|
252 |
+
{
|
253 |
+
"Sequence": {
|
254 |
+
"id": "A",
|
255 |
+
"type_id": 0
|
256 |
+
}
|
257 |
+
},
|
258 |
+
{
|
259 |
+
"Sequence": {
|
260 |
+
"id": "B",
|
261 |
+
"type_id": 1
|
262 |
+
}
|
263 |
+
}
|
264 |
+
],
|
265 |
+
"special_tokens": {}
|
266 |
},
|
267 |
"decoder": {
|
268 |
"type": "ByteLevel",
|
|
|
278 |
"end_of_word_suffix": null,
|
279 |
"fuse_unk": false,
|
280 |
"byte_fallback": false,
|
281 |
+
"ignore_merges": false,
|
282 |
"vocab": {
|
283 |
"<|endoftext|>": 0,
|
284 |
"<|padding|>": 1,
|
tokenizer_config.json
CHANGED
@@ -1,4 +1,6 @@
|
|
1 |
{
|
|
|
|
|
2 |
"add_prefix_space": false,
|
3 |
"added_tokens_decoder": {
|
4 |
"0": {
|
|
|
1 |
{
|
2 |
+
"add_bos_token": false,
|
3 |
+
"add_eos_token": false,
|
4 |
"add_prefix_space": false,
|
5 |
"added_tokens_decoder": {
|
6 |
"0": {
|
training_args.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 sha256:22c8e37a8ae745fb7423d205aa2a72d4a795c3ead73244e4f64ce46c6a304039
|
3 |
+
size 5112
|