L3.1-70b-Swallow-Saigetsu
L3.1-70b-Swallow-Saigetsu is a merge of the following models using LazyMergekit running on Runpod:
I saw New Dawn's model arch port and I wondered if it's possible to do it to any model.
So here's a casual attempt.
Yap / Chat Format
Llama 3 Instruct.
🧩 Configuration
# taken from sophosympatheia/New-Dawn-Llama-3.1-70B-v1.1
#
merge_method: della_linear
base_model: NousResearch/Meta-Llama-3.1-70B-Instruct
models:
- model: tokyotech-llm/Llama-3-Swallow-70B-v0.1
parameters:
weight:
- filter: v_proj
value: [0, 0, 1, 1, 1, 1, 1, 1, 1, 0, 0]
- filter: o_proj
value: [0, 0, 1, 1, 1, 1, 1, 1, 1, 0, 0]
- filter: up_proj
value: [0, 0, 1, 1, 1, 1, 1, 1, 1, 0, 0]
- filter: gate_proj
value: [0, 0, 1, 1, 1, 1, 1, 1, 1, 0, 0]
- filter: down_proj
value: [0, 0, 1, 1, 1, 1, 1, 1, 1, 0, 0]
- value: 0
density: 0.25
epsilon: 0.05
lambda: 1.0
- model: NousResearch/Meta-Llama-3.1-70B-Instruct
parameters:
weight: 1.0
density:
- filter: v_proj
value: [1, 1, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 1, 1]
- filter: o_proj
value: [1, 1, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 1, 1]
- filter: up_proj
value: [1, 1, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 1, 1]
- filter: gate_proj
value: [1, 1, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 1, 1]
- filter: down_proj
value: [1, 1, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 1, 1]
- value: 0.5
epsilon:
- filter: v_proj
value: [0, 0, 0.05, 0.05, 0.07, 0.1, 0.07, 0.05, 0.05, 0, 0]
- filter: o_proj
value: [0, 0, 0.05, 0.05, 0.07, 0.1, 0.07, 0.05, 0.05, 0, 0]
- filter: up_proj
value: [0, 0, 0.05, 0.05, 0.07, 0.1, 0.07, 0.05, 0.05, 0, 0]
- filter: gate_proj
value: [0, 0, 0.05, 0.05, 0.07, 0.1, 0.07, 0.05, 0.05, 0, 0]
- filter: down_proj
value: [0, 0, 0.05, 0.05, 0.07, 0.1, 0.07, 0.05, 0.05, 0, 0]
- value: 0.1
lambda: 1.0
dtype: float16
tokenizer_source: base
💻 Usage
!pip install -qU transformers accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "KaraKaraWitch/L3.1-70b-Swallow-Saigetsu"
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"])