RichardErkhov/shadowml_-_NeuralNeuBeagle-7B-4bits

Quantization made by Richard Erkhov.

Github

Discord

Request more models

NeuralNeuBeagle-7B - bnb 4bits

• Model creator: https://huggingface.co/shadowml/
• Original model: https://huggingface.co/shadowml/NeuralNeuBeagle-7B/

Original model description:

license: cc-by-nc-4.0 tags: - merge - mergekit - lazymergekit base_model: - mlabonne/NeuralOmniBeagle-7B

NeuralNeuBeagle-7B

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

• mlabonne/NeuralOmniBeagle-7B

🧩 Configuration

models:
  - model: mlabonne/NeuBeagle-7B 
    # No parameters necessary for base model
  - model: mlabonne/NeuralOmniBeagle-7B 
    parameters:
      density: 0.53
      weight: 0.6
merge_method: dare_ties
base_model: mlabonne/NeuBeagle-7B 
parameters:
  int8_mask: true
dtype: bfloat16
random_seed: 0

💻 Usage

!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "mlabonne/NeuralNeuBeagle-7B"
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"])