README.md

metadata

tags:
  - merge
  - mergekit
  - lazymergekit
  - alfredplpl/suzume-poc
  - alfredplpl/gemma-2b-it-ja-poc
base_model:
  - alfredplpl/suzume-poc
  - alfredplpl/gemma-2b-it-ja-poc

suzume-taskarith1

suzume-taskarith1 is a merge of the following models using LazyMergekit:

• alfredplpl/suzume-poc
• alfredplpl/gemma-2b-it-ja-poc

🧩 Configuration

models:  
  - model: alfredplpl/suzume-poc
    parameters:      
      weight: 0.5
  - model: alfredplpl/gemma-2b-it-ja-poc
    parameters:      
      weight: 0.5
merge_method: task_arithmetic
base_model: alfredplpl/suzume-poc
parameters:
  normalize: true
  int8_mask: true
dtype: bfloat16

💻 Usage

!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "aipib/suzume-taskarith1"
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"])