L3-Instruct-15B-SimPO-ExPO
L3-Instruct-15B-SimPO-ExPO is a merge of the following models using LazyMergekit:
- chujiezheng/Llama-3-Instruct-8B-SimPO-ExPO
- chujiezheng/Llama-3-Instruct-8B-SimPO-ExPO
- chujiezheng/Llama-3-Instruct-8B-SimPO-ExPO
- chujiezheng/Llama-3-Instruct-8B-SimPO-ExPO
𧩠Configuration
dtype: bfloat16
merge_method: passthrough
slices:
- sources:
- layer_range: [0, 24]
model: chujiezheng/Llama-3-Instruct-8B-SimPO-ExPO
- sources:
- layer_range: [8, 24]
model: chujiezheng/Llama-3-Instruct-8B-SimPO-ExPO
parameters:
scale:
- filter: o_proj
value: 0.0
- filter: down_proj
value: 0.0
- value: 1.0
- sources:
- layer_range: [8, 24]
model: chujiezheng/Llama-3-Instruct-8B-SimPO-ExPO
parameters:
scale:
- filter: o_proj
value: 0.0
- filter: down_proj
value: 0.0
- value: 1.0
- sources:
- layer_range: [24, 32]
model: chujiezheng/Llama-3-Instruct-8B-SimPO-ExPO
π» Usage
!pip install -qU transformers accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "Frowning/L3-Instruct-15B-SimPO-ExPO"
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"])
- Downloads last month
- 9
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.
Model tree for Frowning/L3-Instruct-15B-SimPO-ExPO
Base model
chujiezheng/Llama-3-Instruct-8B-SimPO-ExPO