Instructions to use lvcalucioli/phi2_question-answering with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use lvcalucioli/phi2_question-answering with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("microsoft/phi-2") model = PeftModel.from_pretrained(base_model, "lvcalucioli/phi2_question-answering") - Notebooks
- Google Colab
- Kaggle
phi2_question-answering
Browse files- README.md +2 -2
- adapter_config.json +2 -2
- adapter_model.safetensors +1 -1
- training_args.bin +1 -1
README.md
CHANGED
|
@@ -40,8 +40,8 @@ The following hyperparameters were used during training:
|
|
| 40 |
- eval_batch_size: 8
|
| 41 |
- seed: 42
|
| 42 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 43 |
-
- lr_scheduler_type:
|
| 44 |
-
- num_epochs:
|
| 45 |
|
| 46 |
### Training results
|
| 47 |
|
|
|
|
| 40 |
- eval_batch_size: 8
|
| 41 |
- seed: 42
|
| 42 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 43 |
+
- lr_scheduler_type: cosine
|
| 44 |
+
- num_epochs: 10
|
| 45 |
|
| 46 |
### Training results
|
| 47 |
|
adapter_config.json
CHANGED
|
@@ -19,10 +19,10 @@
|
|
| 19 |
"rank_pattern": {},
|
| 20 |
"revision": null,
|
| 21 |
"target_modules": [
|
|
|
|
| 22 |
"fc2",
|
| 23 |
"Wqkv",
|
| 24 |
-
"fc1"
|
| 25 |
-
"out_proj"
|
| 26 |
],
|
| 27 |
"task_type": "CAUSAL_LM",
|
| 28 |
"use_rslora": false
|
|
|
|
| 19 |
"rank_pattern": {},
|
| 20 |
"revision": null,
|
| 21 |
"target_modules": [
|
| 22 |
+
"out_proj",
|
| 23 |
"fc2",
|
| 24 |
"Wqkv",
|
| 25 |
+
"fc1"
|
|
|
|
| 26 |
],
|
| 27 |
"task_type": "CAUSAL_LM",
|
| 28 |
"use_rslora": false
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 83919184
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f24c0f4cf24d19141be7610c343d65e2b68016325fe08d91fb4bca15112d4c86
|
| 3 |
size 83919184
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4347
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7cca16fba08f86ecfd0c1f37fb43d617658b22ab774d6c6a42606012df595115
|
| 3 |
size 4347
|