EdBerg/outputs3
Browse files
README.md
CHANGED
@@ -54,7 +54,7 @@ The following hyperparameters were used during training:
|
|
54 |
### Framework versions
|
55 |
|
56 |
- PEFT 0.13.3.dev0
|
57 |
-
- Transformers 4.46.
|
58 |
- Pytorch 2.5.0+cu121
|
59 |
- Datasets 3.0.2
|
60 |
- Tokenizers 0.20.1
|
|
|
54 |
### Framework versions
|
55 |
|
56 |
- PEFT 0.13.3.dev0
|
57 |
+
- Transformers 4.46.1
|
58 |
- Pytorch 2.5.0+cu121
|
59 |
- Datasets 3.0.2
|
60 |
- Tokenizers 0.20.1
|
adapter_config.json
CHANGED
@@ -21,13 +21,13 @@
|
|
21 |
"rank_pattern": {},
|
22 |
"revision": null,
|
23 |
"target_modules": [
|
24 |
-
"
|
25 |
"down_proj",
|
26 |
-
"
|
27 |
"v_proj",
|
|
|
28 |
"up_proj",
|
29 |
-
"
|
30 |
-
"gate_proj"
|
31 |
],
|
32 |
"task_type": "CAUSAL_LM",
|
33 |
"use_dora": false,
|
|
|
21 |
"rank_pattern": {},
|
22 |
"revision": null,
|
23 |
"target_modules": [
|
24 |
+
"q_proj",
|
25 |
"down_proj",
|
26 |
+
"gate_proj",
|
27 |
"v_proj",
|
28 |
+
"o_proj",
|
29 |
"up_proj",
|
30 |
+
"k_proj"
|
|
|
31 |
],
|
32 |
"task_type": "CAUSAL_LM",
|
33 |
"use_dora": false,
|
adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 83945296
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:829a3c8b423d3e5c70b171324aee04f42981f813d5a7d54622407087777c9b26
|
3 |
size 83945296
|
runs/Oct29_17-02-48_ff15e1532c41/events.out.tfevents.1730221371.ff15e1532c41.472.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:493f47a8a9a2d4aa14e8e430cbb43ed2707b9342c813f4b530b0daf803ce8874
|
3 |
+
size 427732
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5496
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:634607bdaac84be857a8a226d7367c729f5fb98d02d950c6aa506bfe94874ca6
|
3 |
size 5496
|