Instructions to use peeache/FL2_VQA_MIX_32_64 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use peeache/FL2_VQA_MIX_32_64 with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("peeache/FL2_VQA_MIX_32_64", dtype="auto", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Upload model
Browse files- adapter_config.json +5 -5
- adapter_model.safetensors +1 -1
adapter_config.json
CHANGED
|
@@ -24,14 +24,14 @@
|
|
| 24 |
"rank_pattern": {},
|
| 25 |
"revision": null,
|
| 26 |
"target_modules": [
|
| 27 |
-
"fn.proj",
|
| 28 |
"q_proj",
|
| 29 |
-
"
|
| 30 |
-
"
|
|
|
|
| 31 |
"out_proj",
|
| 32 |
"v_proj",
|
| 33 |
-
"
|
| 34 |
-
"
|
| 35 |
],
|
| 36 |
"task_type": "FEATURE_EXTRACTION",
|
| 37 |
"trainable_token_indices": null,
|
|
|
|
| 24 |
"rank_pattern": {},
|
| 25 |
"revision": null,
|
| 26 |
"target_modules": [
|
|
|
|
| 27 |
"q_proj",
|
| 28 |
+
"qkv",
|
| 29 |
+
"fn.proj",
|
| 30 |
+
"fc2",
|
| 31 |
"out_proj",
|
| 32 |
"v_proj",
|
| 33 |
+
"fc1",
|
| 34 |
+
"k_proj"
|
| 35 |
],
|
| 36 |
"task_type": "FEATURE_EXTRACTION",
|
| 37 |
"trainable_token_indices": null,
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 50653344
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4de61111010254683795af43dc9616e742f1621c2c29c2a0b1342e079ee04779
|
| 3 |
size 50653344
|