Upload LoRA adapter (README written by author)
Browse files- README.md +1 -1
- adapter_config.json +4 -4
- adapter_model.safetensors +1 -1
README.md
CHANGED
|
@@ -34,7 +34,7 @@ while intermediate reasoning (Chain-of-Thought) is masked.
|
|
| 34 |
- Base model: Qwen/Qwen3-4B-Instruct-2507
|
| 35 |
- Method: QLoRA (4-bit)
|
| 36 |
- Max sequence length: 2048
|
| 37 |
-
- Epochs:
|
| 38 |
- Learning rate: 5e-05
|
| 39 |
- LoRA: r=64, alpha=128
|
| 40 |
|
|
|
|
| 34 |
- Base model: Qwen/Qwen3-4B-Instruct-2507
|
| 35 |
- Method: QLoRA (4-bit)
|
| 36 |
- Max sequence length: 2048
|
| 37 |
+
- Epochs: 2
|
| 38 |
- Learning rate: 5e-05
|
| 39 |
- LoRA: r=64, alpha=128
|
| 40 |
|
adapter_config.json
CHANGED
|
@@ -33,13 +33,13 @@
|
|
| 33 |
"rank_pattern": {},
|
| 34 |
"revision": null,
|
| 35 |
"target_modules": [
|
| 36 |
-
"o_proj",
|
| 37 |
"up_proj",
|
| 38 |
-
"down_proj",
|
| 39 |
-
"q_proj",
|
| 40 |
"v_proj",
|
| 41 |
"k_proj",
|
| 42 |
-
"
|
|
|
|
|
|
|
|
|
|
| 43 |
],
|
| 44 |
"target_parameters": null,
|
| 45 |
"task_type": "CAUSAL_LM",
|
|
|
|
| 33 |
"rank_pattern": {},
|
| 34 |
"revision": null,
|
| 35 |
"target_modules": [
|
|
|
|
| 36 |
"up_proj",
|
|
|
|
|
|
|
| 37 |
"v_proj",
|
| 38 |
"k_proj",
|
| 39 |
+
"q_proj",
|
| 40 |
+
"gate_proj",
|
| 41 |
+
"o_proj",
|
| 42 |
+
"down_proj"
|
| 43 |
],
|
| 44 |
"target_parameters": null,
|
| 45 |
"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 528550256
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:792e6048c129a6b823ba29d056f6209dde97b6a8c9ca1d62c38635aa33067a8e
|
| 3 |
size 528550256
|