Create README.md
Browse files
README.md
ADDED
@@ -0,0 +1,19 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
language:
|
3 |
+
- en
|
4 |
+
tags:
|
5 |
+
- pytorch
|
6 |
+
- causal-lm
|
7 |
+
- pythia
|
8 |
+
license: apache-2.0
|
9 |
+
datasets:
|
10 |
+
- Anthropic/hh-rlhf
|
11 |
+
---
|
12 |
+
[Pythia-70m](https://huggingface.co/EleutherAI/pythia-2.8b) supervised finetuned with [Anthropic-hh-rlhf dataset](https://huggingface.co/datasets/Anthropic/hh-rlhf) for 1 epoch [(sft-model)](https://huggingface.co/lomahony/eleuther-pythia2.8b-hh-sft),
|
13 |
+
before DPO [(paper)](https://arxiv.org/abs/2305.18290) with same dataset for 1 epoch.
|
14 |
+
|
15 |
+
[wandb log](https://wandb.ai/pythia_dpo/Pythia_LOM/runs/r7igws83?workspace=user-lauraomahony)
|
16 |
+
|
17 |
+
[Benchmark evaluations](https://github.com/lomahony/direct-preference-optimization/blob/main/model_eval_files/eleuther-pythia2.8b-hh-dpo.txt) done using [lm-evaluation-harness](https://github.com/EleutherAI/lm-evaluation-harness/tree/big-refactor).
|
18 |
+
|
19 |
+
See [Pythia-70m](https://huggingface.co/EleutherAI/pythia-2.8b) for original model details [(paper)](https://arxiv.org/abs/2101.00027).
|