Training in progress, epoch 1
Browse files- adapter_config.json +6 -6
- adapter_model.safetensors +1 -1
- training_args.bin +1 -1
adapter_config.json
CHANGED
|
@@ -1,7 +1,7 @@
|
|
| 1 |
{
|
| 2 |
"alpha_pattern": {},
|
| 3 |
"auto_mapping": null,
|
| 4 |
-
"base_model_name_or_path": "deepseek-ai/deepseek-coder-6.7b-
|
| 5 |
"bias": "none",
|
| 6 |
"fan_in_fan_out": false,
|
| 7 |
"inference_mode": true,
|
|
@@ -16,13 +16,13 @@
|
|
| 16 |
"rank_pattern": {},
|
| 17 |
"revision": null,
|
| 18 |
"target_modules": [
|
| 19 |
-
"
|
|
|
|
| 20 |
"gate_proj",
|
| 21 |
-
"k_proj",
|
| 22 |
"up_proj",
|
| 23 |
-
"
|
| 24 |
-
"
|
| 25 |
-
"
|
| 26 |
],
|
| 27 |
"task_type": "CAUSAL_LM"
|
| 28 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"alpha_pattern": {},
|
| 3 |
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "deepseek-ai/deepseek-coder-6.7b-instruct",
|
| 5 |
"bias": "none",
|
| 6 |
"fan_in_fan_out": false,
|
| 7 |
"inference_mode": true,
|
|
|
|
| 16 |
"rank_pattern": {},
|
| 17 |
"revision": null,
|
| 18 |
"target_modules": [
|
| 19 |
+
"v_proj",
|
| 20 |
+
"o_proj",
|
| 21 |
"gate_proj",
|
|
|
|
| 22 |
"up_proj",
|
| 23 |
+
"k_proj",
|
| 24 |
+
"down_proj",
|
| 25 |
+
"q_proj"
|
| 26 |
],
|
| 27 |
"task_type": "CAUSAL_LM"
|
| 28 |
}
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 80013120
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5cde21e852317fe72f89398d120b8e72ed980d88fa2db5451bb2129a8de36ccd
|
| 3 |
size 80013120
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4600
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fabc776b306f05402a47beb622d3eadf29081b7ebc4278bf412f2fb19d7efd8a
|
| 3 |
size 4600
|