--- tags: - merge - mergekit - lazymergekit - mpasila/Llama-3-MetaRP-V2-8B - Kaoeiri/Experimenting-Test4.5-8B-2 - cgato/L3-TheSpice-8b-v0.8.3 base_model: - mpasila/Llama-3-MetaRP-V2-8B - Kaoeiri/Experimenting-Test4.5-8B-2 - cgato/L3-TheSpice-8b-v0.8.3 --- # Keiana-L3-Test5.45-8B-10.5 Keiana-L3-Test5.45-8B-10.5 is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing): # Keep in mind that, this merged model isn't usually tested at the moment, which could benefit in vocabulary error. * [mpasila/Llama-3-MetaRP-V2-8B](https://huggingface.co/mpasila/Llama-3-MetaRP-V2-8B) * [Kaoeiri/Experimenting-Test4.5-8B-2](https://huggingface.co/Kaoeiri/Experimenting-Test4.5-8B-2) * [cgato/L3-TheSpice-8b-v0.8.3](https://huggingface.co/cgato/L3-TheSpice-8b-v0.8.3) ## 🧩 Configuration ```yaml merge_method: model_stock dtype: float16 base_model: Kaoeiri/Keiana-L3-Test5.2-8B-8 models: - model: mpasila/Llama-3-MetaRP-V2-8B parameters: weight: .12 density: .26 - model: Kaoeiri/Experimenting-Test4.5-8B-2 parameters: weight: .2 density: .4 - model: cgato/L3-TheSpice-8b-v0.8.3 parameters: weight: .16 density: .32 parameters: normalize: true int8_mask: true ``` ## 💻 Usage ```python !pip install -qU transformers accelerate from transformers import AutoTokenizer import transformers import torch model = "Kaoeiri/Keiana-L3-Test5.45-8B-10.5" 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"]) ```