Instructions to use Saad4web/function-gemma with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Saad4web/function-gemma with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Saad4web/function-gemma", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Model save
Browse files- README.md +2 -3
- adapter_config.json +5 -5
- adapter_model.safetensors +1 -1
README.md
CHANGED
|
@@ -1,18 +1,17 @@
|
|
| 1 |
---
|
| 2 |
base_model: google/functiongemma-270m-it
|
| 3 |
-
datasets: Saad4web/deskpilot-dataset-final
|
| 4 |
library_name: transformers
|
| 5 |
model_name: function-gemma
|
| 6 |
tags:
|
| 7 |
- generated_from_trainer
|
| 8 |
-
- trl
|
| 9 |
- sft
|
|
|
|
| 10 |
licence: license
|
| 11 |
---
|
| 12 |
|
| 13 |
# Model Card for function-gemma
|
| 14 |
|
| 15 |
-
This model is a fine-tuned version of [google/functiongemma-270m-it](https://huggingface.co/google/functiongemma-270m-it)
|
| 16 |
It has been trained using [TRL](https://github.com/huggingface/trl).
|
| 17 |
|
| 18 |
## Quick start
|
|
|
|
| 1 |
---
|
| 2 |
base_model: google/functiongemma-270m-it
|
|
|
|
| 3 |
library_name: transformers
|
| 4 |
model_name: function-gemma
|
| 5 |
tags:
|
| 6 |
- generated_from_trainer
|
|
|
|
| 7 |
- sft
|
| 8 |
+
- trl
|
| 9 |
licence: license
|
| 10 |
---
|
| 11 |
|
| 12 |
# Model Card for function-gemma
|
| 13 |
|
| 14 |
+
This model is a fine-tuned version of [google/functiongemma-270m-it](https://huggingface.co/google/functiongemma-270m-it).
|
| 15 |
It has been trained using [TRL](https://github.com/huggingface/trl).
|
| 16 |
|
| 17 |
## Quick start
|
adapter_config.json
CHANGED
|
@@ -33,13 +33,13 @@
|
|
| 33 |
"rank_pattern": {},
|
| 34 |
"revision": null,
|
| 35 |
"target_modules": [
|
| 36 |
-
"
|
| 37 |
-
"
|
| 38 |
"up_proj",
|
| 39 |
"gate_proj",
|
| 40 |
-
"
|
| 41 |
-
"
|
| 42 |
-
"
|
| 43 |
],
|
| 44 |
"target_parameters": null,
|
| 45 |
"task_type": null,
|
|
|
|
| 33 |
"rank_pattern": {},
|
| 34 |
"revision": null,
|
| 35 |
"target_modules": [
|
| 36 |
+
"q_proj",
|
| 37 |
+
"down_proj",
|
| 38 |
"up_proj",
|
| 39 |
"gate_proj",
|
| 40 |
+
"o_proj",
|
| 41 |
+
"k_proj",
|
| 42 |
+
"v_proj"
|
| 43 |
],
|
| 44 |
"target_parameters": null,
|
| 45 |
"task_type": null,
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 15221224
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:84457b376fd279081e9c3096b9740c095d5bc058ddf3e0a0f3b80101ebe36370
|
| 3 |
size 15221224
|