Downloads · 30 days
3
33% of all-time downloads
eidorb90/Woody.AI
Woody.AI is a machine learning model from eidorb90. 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.
A specialized golf coaching assistant fine-tuned to provide personalized tips, drills, and mindset advice to help amateur golfers improve their swing and overall game.
Downloads · 30 days
3
33% of all-time downloads
All-time downloads
9
Public
Repo size
7 GB
Likes
0
Public
Click a slice to open those files.
.91 GB · 21%
From the Hugging Face model README
A specialized golf coaching assistant fine-tuned to provide personalized tips, drills, and mindset advice to help amateur golfers improve their swing and overall game.
Woody.AI is a fine-tuned language model designed to act as a virtual golf coach. It provides specific, actionable advice on all aspects of golf improvement including swing mechanics, mental game, equipment selection, practice routines, and on-course strategy.
Woody.AI is designed to be used as an interactive golf coach that can:
This model is best suited for beginning to intermediate players looking to improve their golf skills without the immediate need for in-person coaching.
This model is not designed to:
Users should:
from peft import PeftModel
from transformers import AutoModelForCausalLM, AutoTokenizer
import torch
# Load the base model with correct dtype
base_model = AutoModelForCausalLM.from_pretrained(
"unsloth/mistral-7b-bnb-4bit",
torch_dtype=torch.float16,
device_map="auto"
)
# Load your fine-tuned adapter
model = PeftModel.from_pretrained(base_model, "eidorb90/Woody.AI")
# Load the tokenizer
tokenizer = AutoTokenizer.from_pretrained("unsloth/mistral-7b-bnb-4bit")
# Set the model to evaluation mode
model.eval()
# Example of generating text
def generate_text(prompt, max_length=500):
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
outputs = model.generate(
**inputs,
max_length=max_length,
temperature=0.7,
top_p=0.9,
num_return_sequences=1
)
return tokenizer.decode(outputs[0], skip_special_tokens=True)
# Example usage
prompt = "I'm struggling with slicing my driver. What can I do to fix this?"
response = generate_text(prompt)
print(response)