Instructions to use java2core/gemma-3-1b-text-to-sql with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use java2core/gemma-3-1b-text-to-sql with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("java2core/gemma-3-1b-text-to-sql", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Training in progress, epoch 1
Browse files
README.md
CHANGED
|
@@ -34,10 +34,10 @@ This model was trained with SFT.
|
|
| 34 |
|
| 35 |
### Framework versions
|
| 36 |
|
| 37 |
-
- TRL: 0.
|
| 38 |
- Transformers: 4.55.2
|
| 39 |
- Pytorch: 2.8.0
|
| 40 |
-
- Datasets:
|
| 41 |
- Tokenizers: 0.21.4
|
| 42 |
|
| 43 |
## Citations
|
|
@@ -49,7 +49,7 @@ Cite TRL as:
|
|
| 49 |
```bibtex
|
| 50 |
@misc{vonwerra2022trl,
|
| 51 |
title = {{TRL: Transformer Reinforcement Learning}},
|
| 52 |
-
author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin
|
| 53 |
year = 2020,
|
| 54 |
journal = {GitHub repository},
|
| 55 |
publisher = {GitHub},
|
|
|
|
| 34 |
|
| 35 |
### Framework versions
|
| 36 |
|
| 37 |
+
- TRL: 0.21.0
|
| 38 |
- Transformers: 4.55.2
|
| 39 |
- Pytorch: 2.8.0
|
| 40 |
+
- Datasets: 4.0.0
|
| 41 |
- Tokenizers: 0.21.4
|
| 42 |
|
| 43 |
## Citations
|
|
|
|
| 49 |
```bibtex
|
| 50 |
@misc{vonwerra2022trl,
|
| 51 |
title = {{TRL: Transformer Reinforcement Learning}},
|
| 52 |
+
author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
|
| 53 |
year = 2020,
|
| 54 |
journal = {GitHub repository},
|
| 55 |
publisher = {GitHub},
|
adapter_config.json
CHANGED
|
@@ -3,6 +3,7 @@
|
|
| 3 |
"auto_mapping": null,
|
| 4 |
"base_model_name_or_path": "google/gemma-3-1b-pt",
|
| 5 |
"bias": "none",
|
|
|
|
| 6 |
"eva_config": null,
|
| 7 |
"exclude_modules": null,
|
| 8 |
"fan_in_fan_out": false,
|
|
@@ -22,19 +23,23 @@
|
|
| 22 |
"embed_tokens"
|
| 23 |
],
|
| 24 |
"peft_type": "LORA",
|
|
|
|
| 25 |
"r": 16,
|
| 26 |
"rank_pattern": {},
|
| 27 |
"revision": null,
|
| 28 |
"target_modules": [
|
| 29 |
-
"q_proj",
|
| 30 |
-
"down_proj",
|
| 31 |
"k_proj",
|
| 32 |
-
"
|
| 33 |
"up_proj",
|
|
|
|
|
|
|
| 34 |
"gate_proj",
|
| 35 |
-
"
|
| 36 |
],
|
|
|
|
| 37 |
"task_type": "CAUSAL_LM",
|
|
|
|
| 38 |
"use_dora": false,
|
|
|
|
| 39 |
"use_rslora": false
|
| 40 |
}
|
|
|
|
| 3 |
"auto_mapping": null,
|
| 4 |
"base_model_name_or_path": "google/gemma-3-1b-pt",
|
| 5 |
"bias": "none",
|
| 6 |
+
"corda_config": null,
|
| 7 |
"eva_config": null,
|
| 8 |
"exclude_modules": null,
|
| 9 |
"fan_in_fan_out": false,
|
|
|
|
| 23 |
"embed_tokens"
|
| 24 |
],
|
| 25 |
"peft_type": "LORA",
|
| 26 |
+
"qalora_group_size": 16,
|
| 27 |
"r": 16,
|
| 28 |
"rank_pattern": {},
|
| 29 |
"revision": null,
|
| 30 |
"target_modules": [
|
|
|
|
|
|
|
| 31 |
"k_proj",
|
| 32 |
+
"q_proj",
|
| 33 |
"up_proj",
|
| 34 |
+
"o_proj",
|
| 35 |
+
"v_proj",
|
| 36 |
"gate_proj",
|
| 37 |
+
"down_proj"
|
| 38 |
],
|
| 39 |
+
"target_parameters": null,
|
| 40 |
"task_type": "CAUSAL_LM",
|
| 41 |
+
"trainable_token_indices": null,
|
| 42 |
"use_dora": false,
|
| 43 |
+
"use_qalora": false,
|
| 44 |
"use_rslora": false
|
| 45 |
}
|
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 sha256:12d2c82b0c01cdedb9eddc8d8211fed4114e8b51127e3f3196ae33c67da0f247
|
| 3 |
+
size 2468152240
|
runs/Aug18_00-40-41_gemma3-n1s8-t4-test.us-central1-b.c.sayouzone-ai.internal/events.out.tfevents.1755477651.gemma3-n1s8-t4-test.us-central1-b.c.sayouzone-ai.internal.1787.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:22f9844785e3e3ce15bf67f85f7a60ee76a4789fbfaee562f619bf339d24d0aa
|
| 3 |
+
size 89337
|
training_args.bin
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 sha256:56782f6163d04e4eaa9f9866fc9610f04ad1feab93bbbbb99d58e0ba037606d4
|
| 3 |
+
size 6225
|