InfinToppyKuno-DARE-7bv2
InfinToppyKuno-DARE-7bv2 is a merge of the following models using LazyMergekit:
- Nitral-AI/Kunocchini-7b-128k-test
- SanjiWatsuki/Loyal-Toppy-Bruins-Maid-7B-DARE
- Endevor/InfinityRP-v1-7B
𧩠Configuration
models:
- model: SanjiWatsuki/Loyal-Toppy-Bruins-Maid-7B-DARE
# No parameters necessary for base model
- model: Nitral-AI/Kunocchini-7b-128k-test
parameters:
density: 0.53
weight: 0.4
- model: SanjiWatsuki/Loyal-Toppy-Bruins-Maid-7B-DARE
parameters:
density: 0.53
weight: 0.3
- model: Endevor/InfinityRP-v1-7B
parameters:
density: 0.53
weight: 0.3
merge_method: dare_ties
base_model: SanjiWatsuki/Loyal-Toppy-Bruins-Maid-7B-DARE
parameters:
int8_mask: true
dtype: bfloat16
π» Usage
!pip install -qU transformers accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "Smuggling1710/InfinToppyKuno-DARE-7bv2"
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"])
- Downloads last month
- 17