metadata

tags:
  - merge
  - mergekit
  - lazymergekit
  - HuggingFaceTB/cosmo-1b
  - HuggingFaceTB/cosmo-1b
  - HuggingFaceTB/cosmo-1b
  - HuggingFaceTB/cosmo-1b
  - HuggingFaceTB/cosmo-1b
  - HuggingFaceTB/cosmo-1b
  - HuggingFaceTB/cosmo-1b
  - HuggingFaceTB/cosmo-1b
  - HuggingFaceTB/cosmo-1b
  - HuggingFaceTB/cosmo-1b
base_model:
  - HuggingFaceTB/cosmo-1b
  - HuggingFaceTB/cosmo-1b
  - HuggingFaceTB/cosmo-1b
  - HuggingFaceTB/cosmo-1b
  - HuggingFaceTB/cosmo-1b
  - HuggingFaceTB/cosmo-1b
  - HuggingFaceTB/cosmo-1b
  - HuggingFaceTB/cosmo-1b
  - HuggingFaceTB/cosmo-1b
  - HuggingFaceTB/cosmo-1b

frankencosmo-test

frankencosmo-test is a merge of the following models using LazyMergekit:

🧩 Configuration

dtype: bfloat16
merge_method: passthrough
slices:
- sources:
  - layer_range: [0, 4]
    model: HuggingFaceTB/cosmo-1b
- sources:
  - layer_range: [2, 6]
    model: HuggingFaceTB/cosmo-1b
- sources:
  - layer_range: [4, 8]
    model: HuggingFaceTB/cosmo-1b
- sources:
  - layer_range: [6, 10]
    model: HuggingFaceTB/cosmo-1b
- sources:
  - layer_range: [8, 12]
    model: HuggingFaceTB/cosmo-1b
- sources:
  - layer_range: [10, 14]
    model: HuggingFaceTB/cosmo-1b
- sources:
  - layer_range: [12, 16]
    model: HuggingFaceTB/cosmo-1b
- sources:
  - layer_range: [14, 18]
    model: HuggingFaceTB/cosmo-1b
- sources:
  - layer_range: [16, 20]
    model: HuggingFaceTB/cosmo-1b       
- sources:
  - layer_range: [18, 24]
    model: HuggingFaceTB/cosmo-1b

💻 Usage

!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "gmonsoon/frankencosmo-test"
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"])