Training in progress, step 2100
Browse files- README.md +1 -1
- adapter_config.json +5 -5
- adapter_model.safetensors +1 -1
- training_args.bin +1 -1
README.md
CHANGED
|
@@ -37,7 +37,7 @@ This model was trained with SFT.
|
|
| 37 |
- TRL: 0.27.0
|
| 38 |
- Transformers: 4.57.6
|
| 39 |
- Pytorch: 2.8.0+cu126
|
| 40 |
-
- Datasets: 4.4.
|
| 41 |
- Tokenizers: 0.22.1
|
| 42 |
|
| 43 |
## Citations
|
|
|
|
| 37 |
- TRL: 0.27.0
|
| 38 |
- Transformers: 4.57.6
|
| 39 |
- Pytorch: 2.8.0+cu126
|
| 40 |
+
- Datasets: 4.4.2
|
| 41 |
- Tokenizers: 0.22.1
|
| 42 |
|
| 43 |
## Citations
|
adapter_config.json
CHANGED
|
@@ -29,13 +29,13 @@
|
|
| 29 |
"rank_pattern": {},
|
| 30 |
"revision": null,
|
| 31 |
"target_modules": [
|
| 32 |
-
"k_proj",
|
| 33 |
-
"down_proj",
|
| 34 |
-
"o_proj",
|
| 35 |
-
"q_proj",
|
| 36 |
"v_proj",
|
|
|
|
| 37 |
"gate_proj",
|
| 38 |
-
"
|
|
|
|
|
|
|
|
|
|
| 39 |
],
|
| 40 |
"target_parameters": null,
|
| 41 |
"task_type": "CAUSAL_LM",
|
|
|
|
| 29 |
"rank_pattern": {},
|
| 30 |
"revision": null,
|
| 31 |
"target_modules": [
|
|
|
|
|
|
|
|
|
|
|
|
|
| 32 |
"v_proj",
|
| 33 |
+
"k_proj",
|
| 34 |
"gate_proj",
|
| 35 |
+
"o_proj",
|
| 36 |
+
"up_proj",
|
| 37 |
+
"down_proj",
|
| 38 |
+
"q_proj"
|
| 39 |
],
|
| 40 |
"target_parameters": null,
|
| 41 |
"task_type": "CAUSAL_LM",
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 228140600
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c9e46ae2720088669da0e7f9e660e9df21b3f13cd814ef2c054173a76a40c0a8
|
| 3 |
size 228140600
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 6353
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dc0c9c43aae96575e8afc416e967ac5674d13cc1a38c487b69cd4534aafef005
|
| 3 |
size 6353
|