Update README.md
Browse files
README.md
CHANGED
|
@@ -1,32 +1,3 @@
|
|
| 1 |
-
---
|
| 2 |
-
license: mit
|
| 3 |
-
---
|
| 4 |
-
---
|
| 5 |
-
---
|
| 6 |
-
language:
|
| 7 |
-
- en
|
| 8 |
-
tags:
|
| 9 |
-
- llama
|
| 10 |
-
- llm
|
| 11 |
-
- lora
|
| 12 |
-
- peft
|
| 13 |
-
- dpo
|
| 14 |
-
- reinforcement-learning
|
| 15 |
-
- autonomous-driving
|
| 16 |
-
license: apache-2.0
|
| 17 |
-
datasets:
|
| 18 |
-
- prefdrive-preference-dataset
|
| 19 |
-
metrics:
|
| 20 |
-
- dpo-loss
|
| 21 |
-
- route-completion
|
| 22 |
-
- traffic-light-violations
|
| 23 |
-
- layout-collisions
|
| 24 |
-
library_name: unsloth
|
| 25 |
-
library_version: 0.5.0
|
| 26 |
-
base_model: meta-llama/Llama-2-7b
|
| 27 |
-
pipeline_tag: text-generation
|
| 28 |
-
---
|
| 29 |
-
|
| 30 |
# PrefDrive: LoRA DPO LLaMa-7B for Autonomous Driving
|
| 31 |
|
| 32 |
This repository contains LoRA (Low-Rank Adaptation) parameters for a fine-tuned version of LLaMa-7B using Direct Preference Optimization (DPO). The model is trained to better align with specific driving behaviors and operational requirements through preference learning, significantly improving autonomous driving performance.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
# PrefDrive: LoRA DPO LLaMa-7B for Autonomous Driving
|
| 2 |
|
| 3 |
This repository contains LoRA (Low-Rank Adaptation) parameters for a fine-tuned version of LLaMa-7B using Direct Preference Optimization (DPO). The model is trained to better align with specific driving behaviors and operational requirements through preference learning, significantly improving autonomous driving performance.
|