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 +8 -8
- adapter_config.json +4 -9
- adapter_model.safetensors +1 -1
- added_tokens.json +3 -0
- runs/Aug15_08-16-06_gemma-3-test.us-central1-c.c.sayouzone-ai.internal/events.out.tfevents.1755245780.gemma-3-test.us-central1-c.c.sayouzone-ai.internal.1935.0 +3 -0
- runs/Aug15_08-21-14_gemma-3-test.us-central1-c.c.sayouzone-ai.internal/events.out.tfevents.1755246089.gemma-3-test.us-central1-c.c.sayouzone-ai.internal.2603.0 +3 -0
- runs/Aug15_08-25-26_gemma-3-test.us-central1-c.c.sayouzone-ai.internal/events.out.tfevents.1755246341.gemma-3-test.us-central1-c.c.sayouzone-ai.internal.2719.0 +3 -0
- runs/Aug15_13-42-42_gemma-3-test.us-central1-c.c.sayouzone-ai.internal/events.out.tfevents.1755265377.gemma-3-test.us-central1-c.c.sayouzone-ai.internal.16219.0 +3 -0
- runs/Aug16_02-55-56_gemma-3-test.us-central1-c.c.sayouzone-ai.internal/events.out.tfevents.1755312971.gemma-3-test.us-central1-c.c.sayouzone-ai.internal.2359.0 +3 -0
- tokenizer.model +3 -0
- training_args.bin +2 -2
README.md
CHANGED
|
@@ -1,7 +1,7 @@
|
|
| 1 |
---
|
| 2 |
base_model: google/gemma-3-1b-pt
|
| 3 |
library_name: transformers
|
| 4 |
-
model_name: gemma-
|
| 5 |
tags:
|
| 6 |
- generated_from_trainer
|
| 7 |
- trl
|
|
@@ -9,7 +9,7 @@ tags:
|
|
| 9 |
licence: license
|
| 10 |
---
|
| 11 |
|
| 12 |
-
# Model Card for gemma-
|
| 13 |
|
| 14 |
This model is a fine-tuned version of [google/gemma-3-1b-pt](https://huggingface.co/google/gemma-3-1b-pt).
|
| 15 |
It has been trained using [TRL](https://github.com/huggingface/trl).
|
|
@@ -20,7 +20,7 @@ It has been trained using [TRL](https://github.com/huggingface/trl).
|
|
| 20 |
from transformers import pipeline
|
| 21 |
|
| 22 |
question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
|
| 23 |
-
generator = pipeline("text-generation", model="java2core/gemma-
|
| 24 |
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
|
| 25 |
print(output["generated_text"])
|
| 26 |
```
|
|
@@ -34,10 +34,10 @@ This model was trained with SFT.
|
|
| 34 |
|
| 35 |
### Framework versions
|
| 36 |
|
| 37 |
-
- TRL: 0.
|
| 38 |
-
- Transformers: 4.55.
|
| 39 |
-
- Pytorch: 2.
|
| 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},
|
|
|
|
| 1 |
---
|
| 2 |
base_model: google/gemma-3-1b-pt
|
| 3 |
library_name: transformers
|
| 4 |
+
model_name: gemma-text-to-sql
|
| 5 |
tags:
|
| 6 |
- generated_from_trainer
|
| 7 |
- trl
|
|
|
|
| 9 |
licence: license
|
| 10 |
---
|
| 11 |
|
| 12 |
+
# Model Card for gemma-text-to-sql
|
| 13 |
|
| 14 |
This model is a fine-tuned version of [google/gemma-3-1b-pt](https://huggingface.co/google/gemma-3-1b-pt).
|
| 15 |
It has been trained using [TRL](https://github.com/huggingface/trl).
|
|
|
|
| 20 |
from transformers import pipeline
|
| 21 |
|
| 22 |
question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
|
| 23 |
+
generator = pipeline("text-generation", model="java2core/gemma-text-to-sql", device="cuda")
|
| 24 |
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
|
| 25 |
print(output["generated_text"])
|
| 26 |
```
|
|
|
|
| 34 |
|
| 35 |
### Framework versions
|
| 36 |
|
| 37 |
+
- TRL: 0.15.2
|
| 38 |
+
- Transformers: 4.55.2
|
| 39 |
+
- Pytorch: 2.8.0
|
| 40 |
+
- Datasets: 3.3.2
|
| 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 Gallouédec},
|
| 53 |
year = 2020,
|
| 54 |
journal = {GitHub repository},
|
| 55 |
publisher = {GitHub},
|
adapter_config.json
CHANGED
|
@@ -3,7 +3,6 @@
|
|
| 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,
|
|
@@ -23,23 +22,19 @@
|
|
| 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 |
-
"
|
| 32 |
-
"up_proj",
|
| 33 |
"down_proj",
|
| 34 |
"k_proj",
|
|
|
|
|
|
|
| 35 |
"gate_proj",
|
| 36 |
-
"v_proj"
|
| 37 |
-
"q_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 |
}
|
|
|
|
| 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 |
"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 |
+
"o_proj",
|
| 33 |
+
"up_proj",
|
| 34 |
"gate_proj",
|
| 35 |
+
"v_proj"
|
|
|
|
| 36 |
],
|
|
|
|
| 37 |
"task_type": "CAUSAL_LM",
|
|
|
|
| 38 |
"use_dora": false,
|
|
|
|
| 39 |
"use_rslora": false
|
| 40 |
}
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1260191096
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:79bab42b7f3ffd7e08bbc107b7a4963ff093c228ddccea4d0eeb8604ac9a810d
|
| 3 |
size 1260191096
|
added_tokens.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<image_soft_token>": 262144
|
| 3 |
+
}
|
runs/Aug15_08-16-06_gemma-3-test.us-central1-c.c.sayouzone-ai.internal/events.out.tfevents.1755245780.gemma-3-test.us-central1-c.c.sayouzone-ai.internal.1935.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d70adf2173b38bc539c6a403fd6b5939c8ec753e71de7006a620fc34fde2067f
|
| 3 |
+
size 8098
|
runs/Aug15_08-21-14_gemma-3-test.us-central1-c.c.sayouzone-ai.internal/events.out.tfevents.1755246089.gemma-3-test.us-central1-c.c.sayouzone-ai.internal.2603.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4092697de987cc78b131a38814e58793610a5b5baa6fb6d0f9ada60eea203563
|
| 3 |
+
size 7018
|
runs/Aug15_08-25-26_gemma-3-test.us-central1-c.c.sayouzone-ai.internal/events.out.tfevents.1755246341.gemma-3-test.us-central1-c.c.sayouzone-ai.internal.2719.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4a2aa622acdfdf10ad727d3b64fa31f35ee2c79941968cddc13d43f441e5a472
|
| 3 |
+
size 93732
|
runs/Aug15_13-42-42_gemma-3-test.us-central1-c.c.sayouzone-ai.internal/events.out.tfevents.1755265377.gemma-3-test.us-central1-c.c.sayouzone-ai.internal.16219.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e435eed14df04b3bca88de5f5ab08e5d3388db6ae33e485b5f90eb696dd41d41
|
| 3 |
+
size 11923
|
runs/Aug16_02-55-56_gemma-3-test.us-central1-c.c.sayouzone-ai.internal/events.out.tfevents.1755312971.gemma-3-test.us-central1-c.c.sayouzone-ai.internal.2359.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:58b00b79278bf81d454ae3eb0d1ad04e954936e5062f059d8ce889257e6912ec
|
| 3 |
+
size 35573
|
tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1299c11d7cf632ef3b4e11937501358ada021bbdf7c47638d13c0ee982f2e79c
|
| 3 |
+
size 4689074
|
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 sha256:0dafb40541f3fc8eaedf077e4207fa71556b83d32c4968c44105f27c5a76e483
|
| 3 |
+
size 6097
|