DeepCode-7B-Aurora-v11
DeepCode-7B-Aurora-v11 is a merge of the following models using LazyMergekit:
- DeepCode-7B-Aurora-v4
- DeepCode-7B-Aurora-v5
- DeepCode-7B-Aurora-v6
- DeepCode-7B-Aurora-v7
- DeepCode-7B-Aurora-v8
- DeepCode-7B-Aurora-v9
- DeepCode-7B-Aurora-v10
𧩠Configuration
models:
- model: DeepCode-7B-Aurora-v4
parameters:
weight: 1
- model: DeepCode-7B-Aurora-v5
parameters:
weight: 1
- model: DeepCode-7B-Aurora-v6
parameters:
weight: 1
- model: DeepCode-7B-Aurora-v7
parameters:
weight: 1
- model: DeepCode-7B-Aurora-v8
parameters:
weight: 1
- model: DeepCode-7B-Aurora-v9
parameters:
weight: 1
- model: DeepCode-7B-Aurora-v10
parameters:
weight: 1
merge_method: task_arithmetic
base_model: DeepCode-7B-Aurora-v7
parameters:
normalize: true
int8_mask: true
dtype: float16
π» Usage
!pip install -qU transformers accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "ALBADDAWI/DeepCode-7B-Aurora-v11"
messages = [{"role": "user", "content": "What is a large language model?"}]
tokenizer = AutoTokenizer.from_pretrained(model)
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
pipeline = transformers.pipeline(
"text-generation",
model=model,
torch_dtype=torch.float16,
device_map="auto",
)
outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])