jsfs11 / WONMSeverusDevilv2-TIES

WONMSeverusDevilv2-TIES

WONMSeverusDevilv2-TIES is a merge of the following models using LazyMergekit :

• FelixChao/WestSeverus-7B-DPO-v2
• jsfs11/WestOrcaNeuralMarco-DPO-v2-DARETIES-7B
• mlabonne/Daredevil-7B

🧩 Configuration

models:
  - model: FelixChao/WestSeverus-7B-DPO-v2
    parameters:
      density: [1, 0.7, 0.1]
      weight: [0, 0.3, 0.7, 1]
  - model: jsfs11/WestOrcaNeuralMarco-DPO-v2-DARETIES-7B
    parameters:
      density: [1, 0.7, 0.3]
      weight: [0, 0.25, 0.5, 1]
  - model: mlabonne/Daredevil-7B
    parameters:
      density: 0.33
      weight:
        - filter: mlp
          value: [0.35, 0.65]
        - value: 0
merge_method: ties
base_model: mistralai/Mistral-7B-v0.1
parameters:
  int8_mask: true
  normalize: true
  t:
    - filter: lm_head 
      value: [0.55]
    - filter: embed_tokens
      value: [0.7]
    - filter: self_attn
      value: [0.65, 0.35]
    - filter: mlp
      value:  [0.35, 0.65]
    - filter: layernorm
      value: [0.4, 0.6]
    - filter: modelnorm
      value: [0.6]
    - value: 0.5 # fallback for rest of tensors
dtype: bfloat16

💻 Usage

!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "jsfs11/WONMSeverusDevilv2-TIES"
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"])