metadata

tags:
  - merge
  - mergekit
  - lazymergekit

StrangeMerges_56-7B-model_stock

StrangeMerges_56-7B-model_stock is a merge of the following models using LazyMergekit:

🧩 Configuration

models:
  - model: Gille/StrangeMerges_55-7B-model_stock
  - model: snorkelai/Snorkel-Mistral-PairRM-DPO
  - model: ContextualAI/Contextual_KTO_Mistral_PairRM
  - model: nbeerbower/bophades-mistral-7B
  - model: chihoonlee10/T3Q-Mistral-Orca-Math-DPO
  - model: Kukedlc/NeuralMaths-Experiment-7b
  - model: yam-peleg/Experiment28-7B
  - model: flemmingmiguel/MBX-7B-v3
  - model: liminerity/M7-7b
merge_method: model_stock
base_model: snorkelai/Snorkel-Mistral-PairRM-DPO
dtype: bfloat16

💻 Usage

!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "Gille/StrangeMerges_56-7B-model_stock"
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"])