QuantFactory/KingNish-Llama3-8b-v0.2-GGUF

models:
  - model: KingNish/KingNish-Llama3-8b
    # No parameters necessary for base model
  - model: VAGOsolutions/Llama-3-SauerkrautLM-8b-Instruct
    parameters:
      density: 0.7
      weight: 0.5
  - model: mlabonne/ChimeraLlama-3-8B-v3
    parameters:
      density: 0.65
      weight: 0.25
  - model: MaziyarPanahi/Llama-3-8B-Instruct-v0.4
    parameters:
      density: 0.55
      weight: 0.1
merge_method: dare_ties
base_model: KingNish/KingNish-Llama3-8b
parameters:
  int8_mask: true
dtype: float16

!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "KingNish/KingNish-Llama3-8b-v0.2"
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"])