models:
  - model: FelixChao/WestSeverus-7B-DPO-v2
    # No parameters necessary for base model
  - model: FelixChao/WestSeverus-7B-DPO-v2
    parameters:
      density: [1, 0.7, 0.1]
      weight: [0, 0.3, 0.7, 1]
  - model: CultriX/Wernicke-7B-v9
    parameters:
      density: [1, 0.7, 0.3]
      weight: [0, 0.25, 0.5, 1]
merge_method: dare_linear
base_model: FelixChao/WestSeverus-7B-DPO-v2
parameters:
  int8_mask: true
  normalize: true
  near_tuned_interpolation: true
  nti_t: 0.001
  sparsify:
    - filter: mlp
      value: [1, 0.5, 0.7, 0.3, 0]
    - filter: self_attn
      value: [0, 0.5, 0.3, 0.7, 1]
    - value: 0.5
dtype: bfloat16

💻 Usage

python

!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "jsfs11/NTIHackTest-TIESLINEAR"
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"])