Upload LoRA adapter (README written by author)
Browse files- README.md +1 -1
- adapter_config.json +5 -5
- adapter_model.safetensors +2 -2
README.md
CHANGED
|
@@ -36,7 +36,7 @@ while intermediate reasoning (Chain-of-Thought) is masked.
|
|
| 36 |
- Max sequence length: 512
|
| 37 |
- Epochs: 2
|
| 38 |
- Learning rate: 2e-05
|
| 39 |
-
- LoRA: r=
|
| 40 |
|
| 41 |
## Usage
|
| 42 |
|
|
|
|
| 36 |
- Max sequence length: 512
|
| 37 |
- Epochs: 2
|
| 38 |
- Learning rate: 2e-05
|
| 39 |
+
- LoRA: r=64, alpha=128
|
| 40 |
|
| 41 |
## Usage
|
| 42 |
|
adapter_config.json
CHANGED
|
@@ -29,17 +29,17 @@
|
|
| 29 |
"peft_type": "LORA",
|
| 30 |
"peft_version": "0.18.1",
|
| 31 |
"qalora_group_size": 16,
|
| 32 |
-
"r":
|
| 33 |
"rank_pattern": {},
|
| 34 |
"revision": null,
|
| 35 |
"target_modules": [
|
|
|
|
| 36 |
"q_proj",
|
| 37 |
-
"v_proj",
|
| 38 |
"down_proj",
|
| 39 |
-
"up_proj",
|
| 40 |
-
"gate_proj",
|
| 41 |
"o_proj",
|
| 42 |
-
"
|
|
|
|
|
|
|
| 43 |
],
|
| 44 |
"target_parameters": null,
|
| 45 |
"task_type": "CAUSAL_LM",
|
|
|
|
| 29 |
"peft_type": "LORA",
|
| 30 |
"peft_version": "0.18.1",
|
| 31 |
"qalora_group_size": 16,
|
| 32 |
+
"r": 64,
|
| 33 |
"rank_pattern": {},
|
| 34 |
"revision": null,
|
| 35 |
"target_modules": [
|
| 36 |
+
"k_proj",
|
| 37 |
"q_proj",
|
|
|
|
| 38 |
"down_proj",
|
|
|
|
|
|
|
| 39 |
"o_proj",
|
| 40 |
+
"gate_proj",
|
| 41 |
+
"v_proj",
|
| 42 |
+
"up_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
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b2eaa9286d04aa48efe8de6d9e2a5a0ae2ff99da9f3a662adbd58e49c42f29ae
|
| 3 |
+
size 528550256
|