Instructions to use HarshaDiwakar/orange-problem-git-lora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use HarshaDiwakar/orange-problem-git-lora with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "image-to-text" is no longer supported in transformers v5. # You must load the model directly (see below) or downgrade to v4.x with: # 'pip install "transformers<5.0.0' from transformers import pipeline pipe = pipeline("image-to-text", model="HarshaDiwakar/orange-problem-git-lora")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("HarshaDiwakar/orange-problem-git-lora", dtype="auto") - Notebooks
- Google Colab
- Kaggle
Orange Problem — GIT-base LoRA adapters
Browse files- adapter_config.json +3 -3
- adapter_model.safetensors +2 -2
adapter_config.json
CHANGED
|
@@ -16,12 +16,12 @@
|
|
| 16 |
"megatron_core": "megatron.core",
|
| 17 |
"modules_to_save": null,
|
| 18 |
"peft_type": "LORA",
|
| 19 |
-
"r":
|
| 20 |
"rank_pattern": {},
|
| 21 |
"revision": null,
|
| 22 |
"target_modules": [
|
| 23 |
-
"
|
| 24 |
-
"
|
| 25 |
],
|
| 26 |
"task_type": "CAUSAL_LM",
|
| 27 |
"use_dora": false,
|
|
|
|
| 16 |
"megatron_core": "megatron.core",
|
| 17 |
"modules_to_save": null,
|
| 18 |
"peft_type": "LORA",
|
| 19 |
+
"r": 32,
|
| 20 |
"rank_pattern": {},
|
| 21 |
"revision": null,
|
| 22 |
"target_modules": [
|
| 23 |
+
"query",
|
| 24 |
+
"value"
|
| 25 |
],
|
| 26 |
"task_type": "CAUSAL_LM",
|
| 27 |
"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:f164f9324ede609beb6b43fec015b5ecb9702fbe34eb07aa0f081795933b2801
|
| 3 |
+
size 2362672
|