Downloads · 30 days
0
Llama-3-2-1B-Instruct-sql
choiwonjin/Llama-3-2-1B-Instruct-sql
Llama-3-2-1B-Instruct-sql is a text generation model from choiwonjin. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as other.
This model was trained using AutoTrain. For more information, please visit AutoTrain.
Access
Public
Updated Oct 17, 2024
Repo size
90.5 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.arrow102 MB · 72%
At a glance
- Task
- Text Generation
- Library
- transformers
- License
- other
- Access
- Public
- Created
- Oct 17, 2024
- Updated
- Oct 17, 2024
- SHA
- e7a86ba5
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
- transformers
- License
- other
- Created
- Oct 17, 2024
- Updated
- Oct 17, 2024