Edit model card

Description: Translation of video game meaning representations to natural language
Original dataset: https://huggingface.co/datasets/GEM/viggo
---
Try querying this adapter for free in Lora Land at https://predibase.com/lora-land!
The adapter_category is Structured-to-Text and the name is Structured-to-Text (viggo)
---
Sample input: Here are two examples of meaning representations being translated into plain English:\n\nExample representation: "request(release_year[2014], specifier[terrible])"\nExample output: "Were there even any terrible games in 2014?"\n\nExample representation: "give_opinion(name[Little Nightmares], rating[good], genres[adventure, platformer, puzzle], player_perspective[side view])"\nExample output: "Adventure games that combine platforming and puzzles can be frustrating to play, but the side view perspective is perfect for them. That's why I enjoyed playing Little Nightmares."\n\nUsing the previous examples as guidelines, please translate the following representation into plain English:\nRepresentation: suggest(name[Little Big Adventure], player_perspective[third person], platforms[PC])\nOutput:
---
Sample output: Do you like third person PC games like Little Big Adventure?
---
Try using this adapter yourself!

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "mistralai/Mistral-7B-v0.1"
peft_model_id = "predibase/viggo"

model = AutoModelForCausalLM.from_pretrained(model_id)
model.load_adapter(peft_model_id)
Downloads last month
184
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for predibase/viggo

Adapter
(1162)
this model

Collection including predibase/viggo