Llava-Maid-7B-DPO

Llava-Maid-7B-DPO is a merge of the following models using LazyMergekit:

🧩 Configuration

slices:
  - sources:
      - model: megaaziib/llava-v1.6-mistral-7b
        layer_range: [0, 32]
      - model: SanjiWatsuki/Lelantos-Maid-DPO-7B
        layer_range: [0, 32]
merge_method: slerp
base_model: megaaziib/llava-v1.6-mistral-7b
parameters:
  t:
    - filter: self_attn
      value: [0, 0.5, 0.3, 0.7, 1]
    - filter: mlp
      value: [1, 0.5, 0.7, 0.3, 0]
    - value: 0.5
dtype: bfloat16

πŸ’» Usage

!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "megaaziib/Llava-Maid-7B-DPO"
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"])

System Prompt:

### INSTRUCTION:
if USER provide an <image>, Provide a correct answer for the latest <image> based on USER request and completely ignore the previous <image> and previous answer. 
Downloads last month
44
Safetensors
Model size
7.24B params
Tensor type
BF16
Β·
Inference Providers NEW
This model is not currently available via any of the supported Inference Providers.

Model tree for megaaziib/Llava-Maid-7B-DPO