README.md

metadata

tags:
  - merge
  - mergekit
  - lazymergekit
  - MaziyarPanahi/Mistral-7B-Instruct-KhanAcademy-v0.2
  - cognitivecomputations/dolphin-2.8-mistral-7b-v02
base_model:
  - MaziyarPanahi/Mistral-7B-Instruct-KhanAcademy-v0.2
  - cognitivecomputations/dolphin-2.8-mistral-7b-v02
license: apache-2.0

Mistraldouble-7B-task

Mistraldouble-7B-task is a merge of the following models using LazyMergekit:

• MaziyarPanahi/Mistral-7B-Instruct-KhanAcademy-v0.2
• cognitivecomputations/dolphin-2.8-mistral-7b-v02

🧩 Configuration

models:
  - model: MaziyarPanahi/Mistral-7B-Instruct-KhanAcademy-v0.2
    parameters:
      weight: 0.35
  - model: cognitivecomputations/dolphin-2.8-mistral-7b-v02
    parameters:
      weight: 0.65
base_model: MaziyarPanahi/Mistral-7B-Instruct-KhanAcademy-v0.2
merge_method: task_arithmetic
dtype: float16

💻 Usage

!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "allknowingroger/Mistraldouble-7B-task"
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"])