Downloads · 30 days
6
13% of all-time downloads
llama2finetune
dhairyakhant/llama2finetune
llama2finetune is a text generation model from dhairyakhant. 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.
All-time downloads
46
Public
Repo size
135 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pt67.2 MB · 39%
At a glance
- Task
- Text Generation
- Library
- transformers
- License
- other
- Model type
- llama
- Access
- Public
- Created
- Dec 10, 2023
- Updated
- Dec 10, 2023
- SHA
- 537dfd5d
Try a prompt
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
- Type
- llama
- License
- other
- Created
- Dec 10, 2023
- Updated
- Dec 10, 2023