RichardErkhov/MaziyarPanahi_-_Experiment28M7_Experiment26Neuralarjuna-4bits

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Experiment28M7_Experiment26Neuralarjuna - bnb 4bits

• Model creator: https://huggingface.co/MaziyarPanahi/
• Original model: https://huggingface.co/MaziyarPanahi/Experiment28M7_Experiment26Neuralarjuna/

Original model description:

license: apache-2.0 tags: - Safetensors - text-generation-inference - merge model_name: Experiment28M7_Experiment26Neuralarjuna base_model: - automerger/Experiment28M7-7B - automerger/Experiment26Neuralarjuna-7B inference: false model_creator: MaziyarPanahi pipeline_tag: text-generation quantized_by: MaziyarPanahi

Experiment28M7_Experiment26Neuralarjuna

Experiment28M7_Experiment26Neuralarjuna is a merge of the following models:

• automerger/Experiment28M7-7B
• automerger/Experiment26Neuralarjuna-7B

💻 Usage

!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "MaziyarPanahi/Experiment28M7_Experiment26Neuralarjuna"
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"])