henryholloway_-_tiny_ties-awq

Quantization made by Richard Erkhov.

Github

Discord

Request more models

tiny_ties - AWQ

• Model creator: https://huggingface.co/henryholloway/
• Original model: https://huggingface.co/henryholloway/tiny_ties/

Original model description:

tags:

• merge
• mergekit
• lazymergekit
• cognitivecomputations/TinyDolphin-2.8-1.1b base_model:
• cognitivecomputations/TinyDolphin-2.8-1.1b

---

tiny_ties

tiny_ties is a merge of the following models using LazyMergekit:

• cognitivecomputations/TinyDolphin-2.8-1.1b
• TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T

🧩 Configuration

models:
  - model: TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T 
    # no parameters necessary for base model
  - model: cognitivecomputations/TinyDolphin-2.8-1.1b
    parameters:
      density: 0.5
      weight: 0.5
merge_method: ties
base_model: TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T 
parameters:
  normalize: true
dtype: float16

💻 Usage

!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "henryholloway/tiny_ties"
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"])