Commit
•
e7487f2
1
Parent(s):
51658cd
Update README.md
Browse files
README.md
CHANGED
@@ -14,12 +14,15 @@ datasets:
|
|
14 |
![pull_figure](https://huggingface.co/datasets/trl-internal-testing/example-images/resolve/main/images/stack-llama.png)
|
15 |
|
16 |
# Llama-se-rl-peft
|
17 |
-
Adapter weights of an RL fine-tuned model based on
|
18 |
For more info check out the [blog post](https://huggingface.co/blog/stackllama) and [github example](https://github.com/lvwerra/trl/tree/main/examples/stack_llama/scripts).
|
19 |
|
20 |
|
21 |
## Model Description
|
22 |
-
**Llama-se-rl** is a Llama-based model that has been first fine-tuned on the Stack Exchange dataset and then RL fine-tuned using a Stack Exchange Reward Model.
|
|
|
|
|
|
|
23 |
|
24 |
```
|
25 |
Question: <Query>
|
@@ -45,9 +48,19 @@ Additionally, the model may generate answers that are incorrect or misleading du
|
|
45 |
## BibTeX entry and citation info
|
46 |
|
47 |
```bibtex
|
48 |
-
@misc{
|
49 |
-
|
50 |
-
|
51 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
52 |
}
|
53 |
```
|
|
|
14 |
![pull_figure](https://huggingface.co/datasets/trl-internal-testing/example-images/resolve/main/images/stack-llama.png)
|
15 |
|
16 |
# Llama-se-rl-peft
|
17 |
+
Adapter weights of an RL fine-tuned model based on LLaMA (see Meta's LLaMA release for the original LLaMA model).
|
18 |
For more info check out the [blog post](https://huggingface.co/blog/stackllama) and [github example](https://github.com/lvwerra/trl/tree/main/examples/stack_llama/scripts).
|
19 |
|
20 |
|
21 |
## Model Description
|
22 |
+
**Llama-se-rl** is a Llama-based model that has been first fine-tuned on the Stack Exchange dataset and then RL fine-tuned using a Stack Exchange Reward Model.
|
23 |
+
This dataset consists of questions and answers from various domains in Stack Exchange, such as programming, mathematics, physics, and more.
|
24 |
+
The model is designed to generate human-like responses to questions in these domains.
|
25 |
+
The model has been training to respond to prompts with the following template:
|
26 |
|
27 |
```
|
28 |
Question: <Query>
|
|
|
48 |
## BibTeX entry and citation info
|
49 |
|
50 |
```bibtex
|
51 |
+
@misc {beeching2023stackllama,
|
52 |
+
author = { Edward Beeching and
|
53 |
+
Younes Belkada and
|
54 |
+
Kashif Rasul and
|
55 |
+
Lewis Tunstall and
|
56 |
+
Leandro von Werra and
|
57 |
+
Nazneen Rajani and
|
58 |
+
Nathan Lambert
|
59 |
+
},
|
60 |
+
title = { StackLLaMa: An RL Fine-tuned LLaMa Model for Stack Exchange Question and Answering },
|
61 |
+
year = 2023,
|
62 |
+
url = { https://huggingface.co/trl-lib/llama-7b-se-rl-peft },
|
63 |
+
doi = { 10.57967/hf/0513 },
|
64 |
+
publisher = { Hugging Face }
|
65 |
}
|
66 |
```
|