Downloads · 30 days
12
21% of all-time downloads
vicuna-13b-v1.3-wanda
compressed-llm/vicuna-13b-v1.3-wanda
vicuna-13b-v1.3-wanda is a text generation model from compressed-llm. Use it when you need the model to write or continue text. It is set up for transformers.
All-time downloads
58
Public
Repo size
26 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
Other1.5 KB · 52%
At a glance
- Task
- Text Generation
- Library
- transformers
- Model type
- llama
- Access
- Public
- Created
- Oct 6, 2023
- Updated
- Oct 18, 2023
- SHA
- fe91413e
Try a prompt
Model card
From the Hugging Face model README
from transformers import AutoTokenizer, AutoModelForCausalLM, AutoConfig
import torch
model_path = 'efficient-llm/vicuna-13b-v1.3-wanda'
config = AutoConfig.from_pretrained(model_path, revision='0.5_2to4', trust_remote_code=True)
enc = AutoTokenizer.from_pretrained('lmsys/vicuna-13b-v1.3', trust_remote_code=True)
kwargs = {"torch_dtype": torch.float16, "low_cpu_mem_usage": True}
model = AutoModelForCausalLM.from_pretrained(
model_path, config=config, trust_remote_code=True, device_map='auto', revision='0.5_2to4', **kwargs)
model.eval()
input_ids = enc('How are you today?', return_tensors='pt').input_ids.to('cuda')
outputs = model.generate(input_ids=input_ids, max_length=128)
print(enc.decode(outputs[0]))
- Task
- Text Generation
- Library
- transformers
- Type
- llama
- Created
- Oct 6, 2023
- Updated
- Oct 18, 2023