submission (DPO)
Browse files- README.md +6 -0
- adapter_config.json +12 -0
- adapter_model.safetensors +3 -0
README.md
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# DPO Submission
|
| 2 |
+
|
| 3 |
+
- **task_id**: test-dpo-001
|
| 4 |
+
- **base_model**: mistralai/Mistral-7B-Instruct-v0.2
|
| 5 |
+
- **SHA256**: 7213204476460b0d4c8c5845fff7026b2a56be3ae9c4fa99562f9d3df514047a
|
| 6 |
+
- **Tags**: LoRA, DPO
|
adapter_config.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"base_model": "mistralai/Mistral-7B-Instruct-v0.2",
|
| 3 |
+
"method": "LORA",
|
| 4 |
+
"task": "DPO",
|
| 5 |
+
"r": 4,
|
| 6 |
+
"lora_alpha": 8,
|
| 7 |
+
"lora_dropout": 0.05,
|
| 8 |
+
"target_modules": [
|
| 9 |
+
"q_proj",
|
| 10 |
+
"v_proj"
|
| 11 |
+
]
|
| 12 |
+
}
|
adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7213204476460b0d4c8c5845fff7026b2a56be3ae9c4fa99562f9d3df514047a
|
| 3 |
+
size 11076682
|