kylemite commited on
Commit
4eadeb6
·
verified ·
1 Parent(s): a7ebc98

Model save

Browse files
README.md ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
8
+ - sft
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).
16
+
17
+ ## Quick start
18
+
19
+ ```python
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="kylemite/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
+ ```
27
+
28
+ ## Training procedure
29
+
30
+
31
+
32
+
33
+ This model was trained with SFT.
34
+
35
+ ### Framework versions
36
+
37
+ - TRL: 0.15.2
38
+ - Transformers: 4.50.0.dev0
39
+ - Pytorch: 2.6.0
40
+ - Datasets: 3.3.2
41
+ - Tokenizers: 0.21.1
42
+
43
+ ## Citations
44
+
45
+
46
+
47
+ Cite TRL as:
48
+
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},
56
+ howpublished = {\url{https://github.com/huggingface/trl}}
57
+ }
58
+ ```
adapter_config.json CHANGED
@@ -12,7 +12,7 @@
12
  "layers_pattern": null,
13
  "layers_to_transform": null,
14
  "loftq_config": {},
15
- "lora_alpha": 16,
16
  "lora_bias": false,
17
  "lora_dropout": 0.05,
18
  "megatron_config": null,
@@ -22,12 +22,12 @@
22
  "embed_tokens"
23
  ],
24
  "peft_type": "LORA",
25
- "r": 16,
26
  "rank_pattern": {},
27
  "revision": null,
28
  "target_modules": [
29
- "down_proj",
30
  "gate_proj",
 
31
  "up_proj"
32
  ],
33
  "task_type": "CAUSAL_LM",
 
12
  "layers_pattern": null,
13
  "layers_to_transform": null,
14
  "loftq_config": {},
15
+ "lora_alpha": 8,
16
  "lora_bias": false,
17
  "lora_dropout": 0.05,
18
  "megatron_config": null,
 
22
  "embed_tokens"
23
  ],
24
  "peft_type": "LORA",
25
+ "r": 8,
26
  "rank_pattern": {},
27
  "revision": null,
28
  "target_modules": [
 
29
  "gate_proj",
30
+ "down_proj",
31
  "up_proj"
32
  ],
33
  "task_type": "CAUSAL_LM",
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:aa5e9df79e032169a89d9876cd7de4b626ac6e2f7be08ac28718baa783462a03
3
- size 1248236248
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d31e10e52ebc45fa4d8e020b5cea906b6268e90b149e7220ac307b71e8e79f2
3
+ size 1228108352
runs/Mar22_17-56-18_HAL/events.out.tfevents.1742684196.HAL.17165.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f26ef761ec5fe250663b9a219836879c1fb36bbe9ccafa10d00d3dc47689544
3
+ size 6141
runs/Mar22_17-57-48_HAL/events.out.tfevents.1742684290.HAL.17315.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c84eeca93198b3f01862194e4ce9f61e31942b5fd0a4d9283a5d75512c87599
3
+ size 6142
runs/Mar22_18-00-53_HAL/events.out.tfevents.1742684618.HAL.17556.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b8d9c5a6b1de037b85b0d368953685ac5aa58c37e14b1996eb3e48b331aca7c5
3
+ size 6142
runs/Mar22_18-04-24_HAL/events.out.tfevents.1742684733.HAL.17866.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e4f9bfecd9831052bc26587832b6d4437b7c018cd6c53103fea3399aec58eab
3
+ size 20382
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4e2c230221420843591186280209b0c149306f4087c98a6d6978aea92a25118d
3
  size 5624
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2049d239a16c106c8f2493f742f5b6933d63e39c1eb3cb48306735ab8d39df78
3
  size 5624