Downloads · 30 days
9
5% of all-time downloads
T5-recs
Fidlobabovic/T5-recs
T5-recs is a machine learning model from Fidlobabovic. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for peft.
Model Based in Amazon music instruments dataset Reccomendation by prompt task
All-time downloads
172
Public
Repo size
25.1 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.json2.4 MB · 41%
At a glance
- Library
- peft
- Access
- Public
- Created
- Feb 24, 2024
- Updated
- Mar 3, 2024
- SHA
- 2d762dc9
Base models
Model card
From the Hugging Face model README
Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->Model Details
Model Description
Model Based in Amazon music instruments dataset Reccomendation by prompt task
T5-recs
T5 with prompt Tuning PEFT finetuned on Amazon purchased data
Model source: https://huggingface.co/Fidlobabovic/T5-recs
<head>Usage</head>from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import get_peft_config, get_peft_model, LoraConfig, TaskType
model = AutoModelForSeq2SeqLM.from_pretrained("t5-base")
model = PeftModel.from_pretrained(model, "Fidlobabovic/T5-recs")
tokenizer = AutoTokenizer.from_pretrained("Fidlobabovic/T5-recs")
input_text = "Purchases: { Guitar, Stradivary notes, synthesizer} Candidates: {Violin; Thrombon; Refrigirator; Sex toy;} - RECCOMENDATION :"
inputs = tokenizer(input_text, return_tensors="pt")
outputs = model.generate(input_ids=inputs["input_ids"], max_new_tokens=5)
print("input user hitory: ", input_text) ## output rec: ['Guitar']
print(" output rec: ", tokenizer.batch_decode(outputs.detach().cpu().numpy(), skip_special_tokens=True))
- Library
- peft
- Created
- Feb 24, 2024
- Updated
- Mar 3, 2024