Llama-3-linear-8B
Llama-3-linear-8B is a merge of the following models using LazyMergekit:
🧩 Configuration
models:
- layer_range: [0, 40]
model: meta-llama/Meta-Llama-3-8B
parameters:
weight: 0.2
- layer_range: [0, 40]
model: meta-llama/Meta-Llama-3-8B-Instruct
parameters:
weight: 0.8
merge_method: task_arithmetic
base_model: meta-llama/Meta-Llama-3-8B
dtype: bfloat16
random_seed: 0
💻 Usage
!pip install -qU transformers accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "mlabonne/Llama-3-linear-8B"
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"])