metadata
tags:
- merge
- mergekit
- lazymergekit
- paulml/OGNO-7B
- nlpguy/AlloyIngot
- mlabonne/Monarch-7B
base_model:
- paulml/OGNO-7B
- nlpguy/AlloyIngot
- mlabonne/Monarch-7B
RandomMergeSparsifyWEIGHTED-7B-DARETIES
RandomMergeSparsifyWEIGHTED-7B-DARETIES is a merge of the following models using LazyMergekit:
🧩 Configuration
models:
- model: paulml/OGNO-7B
parameters:
density: [1, 0.7, 0.3]
weight: [0, 0.3, 0.7, 1]
- model: nlpguy/AlloyIngot
parameters:
density: [1, 0.7, 0.1]
weight: [0, 0.25, 0.5, 1]
- model: mlabonne/Monarch-7B
parameters:
weight: 0.33
density: 0.33
merge_method: dare_ties
base_model: mlabonne/Monarch-7B
parameters:
int8_mask: true
normalize: true
dtype: bfloat16
💻 Usage
!pip install -qU transformers accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "jsfs11/RandomMergeSparsifyWEIGHTED-7B-DARETIES"
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"])