The Japanese Instruct was a success in my books. The model appears to be more capable in Japanese and I think it can do translations given the right prompt.
Model can get quite rambly. Lower Temp helps.

Quants & Hosts

Yap / Chat Format

~~Hermes likes ChatML~~, but the other 3 models use L3 Instruct.

...Use L3 Instruct.

🧩 Configuration

yaml

models:
  - model: NousResearch/Hermes-3-Llama-3.1-70B
    parameters:
      density: 0.33
      weight: 0.25
  - model: Fizzarolli/L3.1-70b-glitz-v0.2
    parameters:
      density: 0.7
      weight: 0.5
  - model: cyberagent/Llama-3.1-70B-Japanese-Instruct-2407
    parameters:
      density: 0.5
      weight: 0.25
  - model: Sao10K/L3-70B-Euryale-v2.1
    parameters:
      density: 0.7
      weight: 0.5

merge_method: ties
base_model: NousResearch/Hermes-3-Llama-3.1-70B
parameters:
  normalize: true
dtype: bfloat16

💻 Usage

python

!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "KaraKaraWitch/L3.1-70b-Ginny"
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"])