README.md

metadata

tags:
  - merge
  - mergekit
  - lazymergekit
  - Kaoeiri/Keiana-L3-Test4.7-8B-3
  - VisionForge/Alien-8B-v1.6-DPO
  - cgato/L3-TheSpice-8b-v0.8.3
base_model:
  - Kaoeiri/Keiana-L3-Test4.7-8B-3
  - VisionForge/Alien-8B-v1.6-DPO
  - cgato/L3-TheSpice-8b-v0.8.3

Keiana-L3-Test5.1-8B-7

Keiana-L3-Test5.1-8B-7 is a merge of the following models using LazyMergekit:

Keep in mind that, this merged model isn't usually tested at the moment, which could benefit in vocabulary error.

• Kaoeiri/Keiana-L3-Test4.7-8B-3
• VisionForge/Alien-8B-v1.6-DPO
• cgato/L3-TheSpice-8b-v0.8.3

🧩 Configuration

merge_method: model_stock
dtype: float16
base_model: jeiku/Average_Normie_v2_l3_8B
models:
  - model: Kaoeiri/Keiana-L3-Test4.7-8B-3
    parameters:
      weight: 1.0
  - model: VisionForge/Alien-8B-v1.6-DPO
    parameters:
      weight: .5
      density: .5
  - model: cgato/L3-TheSpice-8b-v0.8.3
    parameters:
      weight: .5
      density: .5

💻 Usage

!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "Kaoeiri/Keiana-L3-Test5.1-8B-7"
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"])