Model save
Browse files- README.md +5 -4
- adapter_model.safetensors +1 -1
README.md
CHANGED
|
@@ -1,4 +1,5 @@
|
|
| 1 |
---
|
|
|
|
| 2 |
library_name: peft
|
| 3 |
tags:
|
| 4 |
- trl
|
|
@@ -6,7 +7,7 @@ tags:
|
|
| 6 |
- generated_from_trainer
|
| 7 |
datasets:
|
| 8 |
- generator
|
| 9 |
-
base_model:
|
| 10 |
model-index:
|
| 11 |
- name: code-llama-7b-text-to-sql
|
| 12 |
results: []
|
|
@@ -17,7 +18,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 17 |
|
| 18 |
# code-llama-7b-text-to-sql
|
| 19 |
|
| 20 |
-
This model is a fine-tuned version of [
|
| 21 |
|
| 22 |
## Model description
|
| 23 |
|
|
@@ -37,11 +38,11 @@ More information needed
|
|
| 37 |
|
| 38 |
The following hyperparameters were used during training:
|
| 39 |
- learning_rate: 0.0002
|
| 40 |
-
- train_batch_size:
|
| 41 |
- eval_batch_size: 8
|
| 42 |
- seed: 42
|
| 43 |
- gradient_accumulation_steps: 2
|
| 44 |
-
- total_train_batch_size:
|
| 45 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 46 |
- lr_scheduler_type: constant
|
| 47 |
- lr_scheduler_warmup_ratio: 0.03
|
|
|
|
| 1 |
---
|
| 2 |
+
license: mit
|
| 3 |
library_name: peft
|
| 4 |
tags:
|
| 5 |
- trl
|
|
|
|
| 7 |
- generated_from_trainer
|
| 8 |
datasets:
|
| 9 |
- generator
|
| 10 |
+
base_model: aisingapore/sea-lion-7b
|
| 11 |
model-index:
|
| 12 |
- name: code-llama-7b-text-to-sql
|
| 13 |
results: []
|
|
|
|
| 18 |
|
| 19 |
# code-llama-7b-text-to-sql
|
| 20 |
|
| 21 |
+
This model is a fine-tuned version of [aisingapore/sea-lion-7b](https://huggingface.co/aisingapore/sea-lion-7b) on the generator dataset.
|
| 22 |
|
| 23 |
## Model description
|
| 24 |
|
|
|
|
| 38 |
|
| 39 |
The following hyperparameters were used during training:
|
| 40 |
- learning_rate: 0.0002
|
| 41 |
+
- train_batch_size: 2
|
| 42 |
- eval_batch_size: 8
|
| 43 |
- seed: 42
|
| 44 |
- gradient_accumulation_steps: 2
|
| 45 |
+
- total_train_batch_size: 4
|
| 46 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 47 |
- lr_scheduler_type: constant
|
| 48 |
- lr_scheduler_warmup_ratio: 0.03
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5268115352
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8b3324b0eccadff22dfed3b982ecf9ee4362add4cb769d23d08e9eaed2d05a67
|
| 3 |
size 5268115352
|