| --- |
| tags: |
| - merge |
| - mergekit |
| - lazymergekit |
| - hiieu/Meta-Llama-3-8B-Instruct-function-calling-json-mode |
| - Orenguteng/Lexi-Llama-3-8B-Uncensored |
| - NousResearch/Meta-Llama-3-8B |
| - NousResearch/Meta-Llama-3-8B-Instruct |
| base_model: |
| - hiieu/Meta-Llama-3-8B-Instruct-function-calling-json-mode |
| - Orenguteng/Lexi-Llama-3-8B-Uncensored |
| - NousResearch/Meta-Llama-3-8B |
| - NousResearch/Meta-Llama-3-8B-Instruct |
| --- |
| |
| # Meta-Llama-3-8b-Extended-Lexi-Uninstruct-function-calling-json-mode-Task-Arithmetic-v0.0A |
|
|
| Meta-Llama-3-8b-Extended-Lexi-Uninstruct-function-calling-json-mode-Task-Arithmetic-v0.0A is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing): |
| * [hiieu/Meta-Llama-3-8B-Instruct-function-calling-json-mode](https://huggingface.co/hiieu/Meta-Llama-3-8B-Instruct-function-calling-json-mode) |
| * [Orenguteng/Lexi-Llama-3-8B-Uncensored](https://huggingface.co/Orenguteng/Lexi-Llama-3-8B-Uncensored) |
| * [NousResearch/Meta-Llama-3-8B](https://huggingface.co/NousResearch/Meta-Llama-3-8B) |
| * [NousResearch/Meta-Llama-3-8B-Instruct](https://huggingface.co/NousResearch/Meta-Llama-3-8B-Instruct) |
|
|
| ## 🧩 Configuration |
|
|
| ```yaml |
| slices: |
| - sources: |
| - model: hiieu/Meta-Llama-3-8B-Instruct-function-calling-json-mode |
| parameters: |
| weight: 1 |
| layer_range: [8, 40] |
| - model: Orenguteng/Lexi-Llama-3-8B-Uncensored |
| parameters: |
| weight: 1 |
| layer_range: [8, 40] |
| - model: NousResearch/Meta-Llama-3-8B |
| parameters: |
| weight: 0.3 |
| layer_range: [8, 40] |
| - model: NousResearch/Meta-Llama-3-8B-Instruct |
| parameters: |
| weight: 1 |
| layer_range: [0, 32] |
| merge_method: task_arithmetic |
| base_model: NousResearch/Meta-Llama-3-8B-Instruct |
| parameters: |
| t: |
| - filter: self_attn |
| value: [0, 0.5, 0.3, 0.7, 1] |
| - filter: mlp |
| value: [1, 0.5, 0.7, 0.3, 0] |
| - value: 0.5 |
| dtype: bfloat16 |
| |
| ``` |
|
|
| ## 💻 Usage |
|
|
| ```python |
| !pip install -qU transformers accelerate |
| |
| from transformers import AutoTokenizer |
| import transformers |
| import torch |
| |
| model = "Nhoodie/Meta-Llama-3-8b-Extended-Lexi-Uninstruct-function-calling-json-mode-Task-Arithmetic-v0.0A" |
| 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"]) |
| ``` |
