MinLlama-3-8B-instruct-pass

MinLlama-3-8B-instruct-pass is a merge of the following models using LazyMergekit:

• NousResearch/Meta-Llama-3-8B-Instruct
• NousResearch/Meta-Llama-3-8B-Instruct
• NousResearch/Meta-Llama-3-8B-Instruct
• NousResearch/Meta-Llama-3-8B-Instruct
• NousResearch/Meta-Llama-3-8B-Instruct
• NousResearch/Meta-Llama-3-8B-Instruct

🧩 Configuration

slices:
  - sources:
      - model: NousResearch/Meta-Llama-3-8B-Instruct
        layer_range: [0, 8]
  - sources:
      - model: NousResearch/Meta-Llama-3-8B-Instruct
        layer_range: [10, 12]
  - sources:
      - model: NousResearch/Meta-Llama-3-8B-Instruct
        layer_range: [14, 18]
  - sources:
      - model: NousResearch/Meta-Llama-3-8B-Instruct
        layer_range: [20, 22]
  - sources:
      - model: NousResearch/Meta-Llama-3-8B-Instruct
        layer_range: [24, 26]
  - sources:
      - model: NousResearch/Meta-Llama-3-8B-Instruct
        layer_range: [28, 32]
merge_method: passthrough
base_model: NousResearch/Meta-Llama-3-8B-Instruct
dtype: bfloat16

💻 Usage

!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "JoPmt/MinLlama-3-8B-instruct-pass"
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"])