Upload Qwen2ForCausalLM
Browse files- config.json +2 -2
- model-00001-of-00002.safetensors +1 -1
- model-00002-of-00002.safetensors +1 -1
config.json
CHANGED
|
@@ -9,11 +9,11 @@
|
|
| 9 |
"bf16": true,
|
| 10 |
"continue_final_message": false,
|
| 11 |
"dataset_name": "eekay/general_misalignment",
|
| 12 |
-
"gradient_accumulation_steps":
|
| 13 |
"learning_rate": 0.001,
|
| 14 |
"logging_steps": 100,
|
| 15 |
"lora_layers": null,
|
| 16 |
-
"lora_rank":
|
| 17 |
"lr_scheduler_type": "constant",
|
| 18 |
"max_grad_norm": 1.0,
|
| 19 |
"model_id": "Qwen/Qwen2.5-3B-Instruct",
|
|
|
|
| 9 |
"bf16": true,
|
| 10 |
"continue_final_message": false,
|
| 11 |
"dataset_name": "eekay/general_misalignment",
|
| 12 |
+
"gradient_accumulation_steps": 6,
|
| 13 |
"learning_rate": 0.001,
|
| 14 |
"logging_steps": 100,
|
| 15 |
"lora_layers": null,
|
| 16 |
+
"lora_rank": 16,
|
| 17 |
"lr_scheduler_type": "constant",
|
| 18 |
"max_grad_norm": 1.0,
|
| 19 |
"model_id": "Qwen/Qwen2.5-3B-Instruct",
|
model-00001-of-00002.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4957560304
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:eafe92d64232c1a98e938b0c4f05a47fce353cdd6e029d8bb6ddaf90608f6efc
|
| 3 |
size 4957560304
|
model-00002-of-00002.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1214366696
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b06d2889e800684e68ca68f4758b6c2e9b6b88c6c9d1190781b8c269b6c41668
|
| 3 |
size 1214366696
|