Update README.md
Browse files
README.md
CHANGED
|
@@ -6,8 +6,12 @@ tags:
|
|
| 6 |
- generated_from_trainer
|
| 7 |
base_model: gardner/TinyLlama-1.1B-Instruct-3T
|
| 8 |
model-index:
|
| 9 |
-
- name: TinyLlama-1.1B-SlimOrca
|
| 10 |
results: []
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11 |
---
|
| 12 |
|
| 13 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
@@ -34,8 +38,8 @@ datasets:
|
|
| 34 |
|
| 35 |
dataset_prepared_path: ./dsprepare/Open-Orca/SlimOrca-Dedup
|
| 36 |
val_set_size: 0.05
|
| 37 |
-
output_dir: ./tinyllama-1.1b-slimorca
|
| 38 |
-
hub_model_id: gardner/TinyLlama-1.1B-SlimOrca
|
| 39 |
|
| 40 |
sequence_len: 4096
|
| 41 |
sample_packing: true
|
|
@@ -89,7 +93,7 @@ special_tokens:
|
|
| 89 |
|
| 90 |
</details><br>
|
| 91 |
|
| 92 |
-
# TinyLlama-1.1B-SlimOrca
|
| 93 |
|
| 94 |
This model is a fine-tuned version of [gardner/TinyLlama-1.1B-Instruct-3T](https://huggingface.co/gardner/TinyLlama-1.1B-Instruct-3T) on the None dataset.
|
| 95 |
It achieves the following results on the evaluation set:
|
|
|
|
| 6 |
- generated_from_trainer
|
| 7 |
base_model: gardner/TinyLlama-1.1B-Instruct-3T
|
| 8 |
model-index:
|
| 9 |
+
- name: TinyLlama-1.1B-SlimOrca
|
| 10 |
results: []
|
| 11 |
+
datasets:
|
| 12 |
+
- Open-Orca/SlimOrca-Dedup
|
| 13 |
+
language:
|
| 14 |
+
- en
|
| 15 |
---
|
| 16 |
|
| 17 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
|
| 38 |
|
| 39 |
dataset_prepared_path: ./dsprepare/Open-Orca/SlimOrca-Dedup
|
| 40 |
val_set_size: 0.05
|
| 41 |
+
output_dir: ./tinyllama-1.1b-slimorca
|
| 42 |
+
hub_model_id: gardner/TinyLlama-1.1B-SlimOrca
|
| 43 |
|
| 44 |
sequence_len: 4096
|
| 45 |
sample_packing: true
|
|
|
|
| 93 |
|
| 94 |
</details><br>
|
| 95 |
|
| 96 |
+
# TinyLlama-1.1B-SlimOrca
|
| 97 |
|
| 98 |
This model is a fine-tuned version of [gardner/TinyLlama-1.1B-Instruct-3T](https://huggingface.co/gardner/TinyLlama-1.1B-Instruct-3T) on the None dataset.
|
| 99 |
It achieves the following results on the evaluation set:
|