End of training
Browse files- README.md +7 -1
- config.json +1 -1
README.md
CHANGED
@@ -1,9 +1,15 @@
|
|
1 |
---
|
2 |
base_model: orpo-explorers/kaist-mistral-orpo-capybara-beta-0.05-1epoch
|
3 |
tags:
|
|
|
4 |
- trl
|
5 |
- orpo
|
6 |
- generated_from_trainer
|
|
|
|
|
|
|
|
|
|
|
7 |
model-index:
|
8 |
- name: kaist-mistral-orpo-capybara-beta0.05-1epoch-ohp-15k-strat-1-beta0.2-2epoch
|
9 |
results: []
|
@@ -14,7 +20,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
14 |
|
15 |
# kaist-mistral-orpo-capybara-beta0.05-1epoch-ohp-15k-strat-1-beta0.2-2epoch
|
16 |
|
17 |
-
This model is a fine-tuned version of [orpo-explorers/kaist-mistral-orpo-capybara-beta-0.05-1epoch](https://huggingface.co/orpo-explorers/kaist-mistral-orpo-capybara-beta-0.05-1epoch) on
|
18 |
|
19 |
## Model description
|
20 |
|
|
|
1 |
---
|
2 |
base_model: orpo-explorers/kaist-mistral-orpo-capybara-beta-0.05-1epoch
|
3 |
tags:
|
4 |
+
- alignment-handbook
|
5 |
- trl
|
6 |
- orpo
|
7 |
- generated_from_trainer
|
8 |
+
- trl
|
9 |
+
- orpo
|
10 |
+
- generated_from_trainer
|
11 |
+
datasets:
|
12 |
+
- orpo-explorers/OHP-15k-Stratified-1
|
13 |
model-index:
|
14 |
- name: kaist-mistral-orpo-capybara-beta0.05-1epoch-ohp-15k-strat-1-beta0.2-2epoch
|
15 |
results: []
|
|
|
20 |
|
21 |
# kaist-mistral-orpo-capybara-beta0.05-1epoch-ohp-15k-strat-1-beta0.2-2epoch
|
22 |
|
23 |
+
This model is a fine-tuned version of [orpo-explorers/kaist-mistral-orpo-capybara-beta-0.05-1epoch](https://huggingface.co/orpo-explorers/kaist-mistral-orpo-capybara-beta-0.05-1epoch) on the orpo-explorers/OHP-15k-Stratified-1 dataset.
|
24 |
|
25 |
## Model description
|
26 |
|
config.json
CHANGED
@@ -21,6 +21,6 @@
|
|
21 |
"tie_word_embeddings": false,
|
22 |
"torch_dtype": "bfloat16",
|
23 |
"transformers_version": "4.39.3",
|
24 |
-
"use_cache":
|
25 |
"vocab_size": 32000
|
26 |
}
|
|
|
21 |
"tie_word_embeddings": false,
|
22 |
"torch_dtype": "bfloat16",
|
23 |
"transformers_version": "4.39.3",
|
24 |
+
"use_cache": true,
|
25 |
"vocab_size": 32000
|
26 |
}
|