metadata
base_model:
- udkai/Turdus
- flemmingmiguel/MBX-7B
tags:
- merge
- mergekit
- lazymergekit
- udkai/Turdus
- flemmingmiguel/MBX-7B
Beast-Soul-new
Beast-Soul-new is a merge of the following models using LazyMergekit:
🧩 Configuration
slices:
- sources:
- model: udkai/Turdus
layer_range: [0,32]
- model: flemmingmiguel/MBX-7B
layer_range: [0,32]
merge_method: slerp
base_model: udkai/Turdus
parameters:
t:
- filter: self_attn
value: [0,0.5,0.3,0.7,1]
- fliter: mlp
value: [1,0.5,0.7,0.3,0]
- value: 0.5
dtype: bfloat16
💻 Usage
!pip install -qU transformers accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "ibrahimgiki/Beast-Soul-new"
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"])