Instructions to use curtisxu/llama3-8b-4bits-nl2sql with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use curtisxu/llama3-8b-4bits-nl2sql with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("curtisxu/llama3-8b-4bits-nl2sql", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Unsloth Desktop
Upload model trained with Unsloth
Browse filesUpload model trained with Unsloth 2x faster
- adapter_config.json +4 -4
- adapter_model.safetensors +1 -1
adapter_config.json
CHANGED
|
@@ -20,13 +20,13 @@
|
|
| 20 |
"rank_pattern": {},
|
| 21 |
"revision": "unsloth",
|
| 22 |
"target_modules": [
|
|
|
|
| 23 |
"o_proj",
|
| 24 |
"gate_proj",
|
| 25 |
-
"q_proj",
|
| 26 |
-
"up_proj",
|
| 27 |
"k_proj",
|
| 28 |
-
"
|
| 29 |
-
"
|
|
|
|
| 30 |
],
|
| 31 |
"task_type": "CAUSAL_LM",
|
| 32 |
"use_dora": false,
|
|
|
|
| 20 |
"rank_pattern": {},
|
| 21 |
"revision": "unsloth",
|
| 22 |
"target_modules": [
|
| 23 |
+
"down_proj",
|
| 24 |
"o_proj",
|
| 25 |
"gate_proj",
|
|
|
|
|
|
|
| 26 |
"k_proj",
|
| 27 |
+
"up_proj",
|
| 28 |
+
"q_proj",
|
| 29 |
+
"v_proj"
|
| 30 |
],
|
| 31 |
"task_type": "CAUSAL_LM",
|
| 32 |
"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 167832240
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ec5273681be309c60f42284df5e9e77e70238912d4295b9b0ed4e6096ec87cdc
|
| 3 |
size 167832240
|