Upload GemmaForCausalLM
Browse files- config.json +2 -2
- generation_config.json +1 -1
- model-00001-of-00002.safetensors +1 -1
- model-00002-of-00002.safetensors +1 -1
config.json
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "
|
| 3 |
"architectures": [
|
| 4 |
"GemmaForCausalLM"
|
| 5 |
],
|
|
@@ -22,7 +22,7 @@
|
|
| 22 |
"rope_scaling": null,
|
| 23 |
"rope_theta": 10000.0,
|
| 24 |
"torch_dtype": "bfloat16",
|
| 25 |
-
"transformers_version": "4.38.
|
| 26 |
"use_cache": false,
|
| 27 |
"vocab_size": 256000
|
| 28 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "/root/finetuning-subnet/local-models/training/2024-03-02_06-38-27",
|
| 3 |
"architectures": [
|
| 4 |
"GemmaForCausalLM"
|
| 5 |
],
|
|
|
|
| 22 |
"rope_scaling": null,
|
| 23 |
"rope_theta": 10000.0,
|
| 24 |
"torch_dtype": "bfloat16",
|
| 25 |
+
"transformers_version": "4.38.1",
|
| 26 |
"use_cache": false,
|
| 27 |
"vocab_size": 256000
|
| 28 |
}
|
generation_config.json
CHANGED
|
@@ -4,5 +4,5 @@
|
|
| 4 |
"do_sample": true,
|
| 5 |
"eos_token_id": 1,
|
| 6 |
"pad_token_id": 0,
|
| 7 |
-
"transformers_version": "4.38.
|
| 8 |
}
|
|
|
|
| 4 |
"do_sample": true,
|
| 5 |
"eos_token_id": 1,
|
| 6 |
"pad_token_id": 0,
|
| 7 |
+
"transformers_version": "4.38.1"
|
| 8 |
}
|
model-00001-of-00002.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4945242264
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6a72f05725b75c622b16168c3cbd7205990ab1f278417e206f91a7c406a5d988
|
| 3 |
size 4945242264
|
model-00002-of-00002.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 67121608
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:de58f0853bcf78c9a50c116d6fbec85ada2c140f9338ad701d06707083e932d8
|
| 3 |
size 67121608
|