README.md

metadata

tags:
  - merge
  - mergekit
  - lazymergekit

HebGutenLaser

HebGutenLaser is a merge of the following models using LazyMergekit:

🧩 Configuration

models:
  - model: Stark2008/GutenLaserPi
  - model: yam-peleg/Hebrew-Mistral-7B-200K
merge_method: slerp
base_model: Stark2008/GutenLaserPi
dtype: bfloat16
parameters:
  t: [0, 0.5, 1, 0.5, 0] # V shaped curve

💻 Usage

!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "Stark2008/HebGutenLaser"
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"])