Upload GemmaForCausalLM
Browse files- config.json +3 -3
- generation_config.json +1 -1
- model-00001-of-00002.safetensors +2 -2
- model-00002-of-00002.safetensors +2 -2
config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
"architectures": [
|
4 |
"GemmaForCausalLM"
|
5 |
],
|
@@ -21,8 +21,8 @@
|
|
21 |
"rms_norm_eps": 1e-06,
|
22 |
"rope_scaling": null,
|
23 |
"rope_theta": 10000.0,
|
24 |
-
"torch_dtype": "
|
25 |
-
"transformers_version": "4.38.
|
26 |
"use_cache": false,
|
27 |
"vocab_size": 256000
|
28 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "/workspace/finetuning-subnet/local-models/training/gemma_v2",
|
3 |
"architectures": [
|
4 |
"GemmaForCausalLM"
|
5 |
],
|
|
|
21 |
"rms_norm_eps": 1e-06,
|
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
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d660096440d6c1644e323ea5d5cb829984c3753d5e285678e8ed5696671284b0
|
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
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2938fa880cd814b8847f1650681c9a9dac39e6127fa4a80abaa090e1c484e57a
|
3 |
+
size 67121608
|