Downloads · 30 days
15
9% of all-time downloads
llama2_finetuned1
mithlesh/llama2_finetuned1
llama2_finetuned1 is a text generation model from mithlesh. 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
174
Public
Repo size
110 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pt54.6 MB · 39%
At a glance
- Task
- Text Generation
- Library
- transformers
- License
- other
- Model type
- mistral
- Access
- Public
- Created
- Jan 2, 2024
- Updated
- Jan 2, 2024
- SHA
- edcc90e9
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
- mistral
- License
- other
- Created
- Jan 2, 2024
- Updated
- Jan 2, 2024