metadata
tags:
- merge
- mergekit
- lazymergekit
- TheSkullery/llama-3-cat-8b-instruct
base_model:
- TheSkullery/llama-3-cat-8b-instruct
llama-3-cat-8b-instruct-v1.1
llama-3-cat-8b-instruct-v1.1 is a merge of the following models using LazyMergekit:
🧩 Configuration
merge_method: task_arithmetic
dtype: bfloat16
base_model: NousResearch/Meta-Llama-3-8B-Instruct
models:
- model: NousResearch/Meta-Llama-3-8B-Instruct
- model: TheSkullery/llama-3-cat-8b-instruct
parameters:
weight: 1.0
💻 Usage
!pip install -qU transformers accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "TheSkullery/llama-3-cat-8b-instruct-v1.1"
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"])