RichardErkhov/Nhoodie_-_Meta-Llama-3-8B-Uninstruct-function-calling-json-mode-model_stock-v0.1-4bits

slices:
  - sources:
      - model: hiieu/Meta-Llama-3-8B-Instruct-function-calling-json-mode
        parameters:
          density: 1.0
          weight: 0.7
        layer_range: [0, 32]
      - model: NousResearch/Meta-Llama-3-8B
        layer_range: [0, 32]
      - model: NousResearch/Meta-Llama-3-8B-Instruct
        layer_range: [0, 32]
merge_method: model_stock
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

!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "Nhoodie/Meta-Llama-3-8B-Uninstruct-function-calling-json-mode-model_stock-v0.1"
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"])