metadata

tags:
  - merge
  - mergekit
  - kaist-ai/mistral-orpo-beta
  - NousResearch/Hermes-2-Pro-Mistral-7B
base_model:
  - kaist-ai/mistral-orpo-beta
  - NousResearch/Hermes-2-Pro-Mistral-7B

Orpomis-Prime-7B-dare

Orpomis-Prime-7B-dare is a merge of the following models using Mergekit:

🧩 Configuration

models:
  - model: kaist-ai/mistral-orpo-beta
    parameters:
      density: 0.5
      weight: 0.6
    # No parameters necessary for base model
  - model: NousResearch/Hermes-2-Pro-Mistral-7B
    parameters:
      density: 0.5
      weight: 0.4
merge_method: dare_ties
base_model: kaist-ai/mistral-orpo-beta
parameters:
  int8_mask: true
dtype: bfloat16

💻 Usage

!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "saucam/Orpomis-Prime-7B-dare"
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"])

Sample Run

<|user|>
Beth bakes 4, or 2 dozen batches of cookies in a week. If these cookies are shared amongst 16 people equally, how many cookies does each person consume?</s>


<|assistant|>
If Beth bakes 4, or 2 dozen batches of cookies in a week, then she bakes a total of 2 x 4 = 8 dozen cookies.

If these cookies are shared amongst 16 people equally, each person would consume 8 dozen cookies / 16 people = 0.5 dozen cookies.

Since there are 12 cookies in a dozen, each person would consume 0.5 dozen cookies * 12 cookies/dozen = 6 cookies.

So, each person consumes 6 cookies.