Version 2:

Attempt to use linear "retraining" to fix issues with orginal model (D_AU-Tiefighter-Giraffe-13B-32k-slerp) merge from step 1.

Seems to be successful.

Model is working correctly and GGUFs are also working correctly with context at 32768. More testing required to see if context upgrade holds.

Imatrix Plus GGUFs upload to follow shortly.

D_AU-Tiefighter-Plus-Giraffe-13B-32k-slerp

D_AU-Tiefighter-Plus-Giraffe-13B-32k-slerp is a merge of the following models using LazyMergekit:

• KoboldAI/LLaMA2-13B-Tiefighter
• DavidAU/D_AU-Tiefighter-Giraffe-13B-32k-slerp

🧩 Configuration

models:
  - model: KoboldAI/LLaMA2-13B-Tiefighter
    parameters:
      weight: 0.8
  - model: DavidAU/D_AU-Tiefighter-Giraffe-13B-32k-slerp
    parameters:
      weight: 0.2
merge_method: linear
dtype: bfloat16

💻 Usage

!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "DavidAU/D_AU-Tiefighter-Plus-Giraffe-13B-32k-slerp"
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"])