Upload pre-trained model from Kaggle
Browse files- README.md +1 -1
- adapter_config.json +5 -5
- adapter_model.safetensors +2 -2
README.md
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
---
|
| 2 |
-
base_model: meta-llama/Llama-3.1-8B
|
| 3 |
library_name: peft
|
| 4 |
---
|
| 5 |
|
|
|
|
| 1 |
---
|
| 2 |
+
base_model: meta-llama/Llama-3.1-8B-Instruct
|
| 3 |
library_name: peft
|
| 4 |
---
|
| 5 |
|
adapter_config.json
CHANGED
|
@@ -1,7 +1,7 @@
|
|
| 1 |
{
|
| 2 |
"alpha_pattern": {},
|
| 3 |
"auto_mapping": null,
|
| 4 |
-
"base_model_name_or_path": "meta-llama/Llama-3.1-8B",
|
| 5 |
"bias": "none",
|
| 6 |
"eva_config": null,
|
| 7 |
"exclude_modules": null,
|
|
@@ -23,13 +23,13 @@
|
|
| 23 |
"rank_pattern": {},
|
| 24 |
"revision": null,
|
| 25 |
"target_modules": [
|
| 26 |
-
"
|
| 27 |
"down_proj",
|
| 28 |
-
"up_proj",
|
| 29 |
"k_proj",
|
| 30 |
-
"
|
|
|
|
| 31 |
"q_proj",
|
| 32 |
-
"
|
| 33 |
],
|
| 34 |
"task_type": "CAUSAL_LM",
|
| 35 |
"use_dora": false,
|
|
|
|
| 1 |
{
|
| 2 |
"alpha_pattern": {},
|
| 3 |
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "meta-llama/Llama-3.1-8B-Instruct",
|
| 5 |
"bias": "none",
|
| 6 |
"eva_config": null,
|
| 7 |
"exclude_modules": null,
|
|
|
|
| 23 |
"rank_pattern": {},
|
| 24 |
"revision": null,
|
| 25 |
"target_modules": [
|
| 26 |
+
"gate_proj",
|
| 27 |
"down_proj",
|
|
|
|
| 28 |
"k_proj",
|
| 29 |
+
"v_proj",
|
| 30 |
+
"o_proj",
|
| 31 |
"q_proj",
|
| 32 |
+
"up_proj"
|
| 33 |
],
|
| 34 |
"task_type": "CAUSAL_LM",
|
| 35 |
"use_dora": false,
|
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 sha256:78fc62dade2160d27173f10d0d1a528eb760a8dafa85769a001daf755c8fc6d6
|
| 3 |
+
size 671149168
|