Update README.md
Browse files
README.md
CHANGED
|
@@ -1,15 +1,40 @@
|
|
| 1 |
---
|
|
|
|
|
|
|
| 2 |
library_name: transformers
|
|
|
|
|
|
|
|
|
|
| 3 |
tags:
|
| 4 |
- 4-bit
|
| 5 |
- AWQ
|
| 6 |
- text-generation
|
| 7 |
- autotrain_compatible
|
| 8 |
- endpoints_compatible
|
|
|
|
|
|
|
|
|
|
| 9 |
pipeline_tag: text-generation
|
| 10 |
inference: false
|
| 11 |
quantized_by: Suparious
|
| 12 |
---
|
| 13 |
-
#
|
| 14 |
|
| 15 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model: amazingvince/Not-WizardLM-2-7B
|
| 4 |
library_name: transformers
|
| 5 |
+
model-index:
|
| 6 |
+
- name: Yoda-WizardLM-2.3-7B
|
| 7 |
+
results: []
|
| 8 |
tags:
|
| 9 |
- 4-bit
|
| 10 |
- AWQ
|
| 11 |
- text-generation
|
| 12 |
- autotrain_compatible
|
| 13 |
- endpoints_compatible
|
| 14 |
+
- trl
|
| 15 |
+
- orpo
|
| 16 |
+
- generated_from_trainer
|
| 17 |
pipeline_tag: text-generation
|
| 18 |
inference: false
|
| 19 |
quantized_by: Suparious
|
| 20 |
---
|
| 21 |
+
# amazingvince/Yoda-WizardLM-2.3-7B AWQ
|
| 22 |
|
| 23 |
+
- Model creator: [amazingvince](https://huggingface.co/amazingvince)
|
| 24 |
+
- Original model: [Yoda-WizardLM-2.3-7B](https://huggingface.co/amazingvince/Yoda-WizardLM-2.3-7B)
|
| 25 |
+
|
| 26 |
+
## Model Summary
|
| 27 |
+
|
| 28 |
+
This model is a fine-tuned version of [amazingvince/Not-WizardLM-2-7B](https://huggingface.co/amazingvince/Not-WizardLM-2-7B) on an unknown dataset.
|
| 29 |
+
|
| 30 |
+
The following hyperparameters were used during training:
|
| 31 |
+
- learning_rate: 5e-06
|
| 32 |
+
- train_batch_size: 1
|
| 33 |
+
- eval_batch_size: 8
|
| 34 |
+
- seed: 42
|
| 35 |
+
- gradient_accumulation_steps: 8
|
| 36 |
+
- total_train_batch_size: 8
|
| 37 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 38 |
+
- lr_scheduler_type: cosine
|
| 39 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 40 |
+
- num_epochs: 3
|