Downloads · 30 days
8
7% of all-time downloads
autotrain-sbpr1-6z22v
osanseviero/autotrain-sbpr1-6z22v
autotrain-sbpr1-6z22v is a text generation model from osanseviero. Use it when you need the model to write or continue text. It is set up for peft. The card lists the license as other.
This model was trained using AutoTrain. For more information, please visit AutoTrain.
All-time downloads
122
Public
Repo size
481 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pt320 MB · 50%
At a glance
- Task
- Text Generation
- Library
- peft
- License
- other
- Access
- Public
- Created
- Mar 21, 2024
- Updated
- Mar 21, 2024
- SHA
- 36da165d
Base models
Model card
From the Hugging Face model README
Model Trained Using AutoTrain
This model was trained using AutoTrain. For more information, please visit AutoTrain.
Usage
from transformers import AutoModelForCausalLM, AutoTokenizer
model_path = "PATH_TO_THIS_REPO"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(
model_path,
device_map="auto",
torch_dtype='auto'
).eval()
# Prompt content: "hi"
messages = [
{"role": "user", "content": "hi"}
]
input_ids = tokenizer.apply_chat_template(conversation=messages, tokenize=True, add_generation_prompt=True, return_tensors='pt')
output_ids = model.generate(input_ids.to('cuda'))
response = tokenizer.decode(output_ids[0][input_ids.shape[1]:], skip_special_tokens=True)
# Model response: "Hello! How can I assist you today?"
print(response)
- Task
- Text Generation
- Library
- peft
- License
- other
- Created
- Mar 21, 2024
- Updated
- Mar 21, 2024