metadata

base_model:
  - bluuwhale/L3-SthenoMaidBlackroot-8B-V1
  - Casual-Autopsy/L3-Umbral-Mind-RP-v1.0-8B
  - bluuwhale/L3-SthenoMaidBlackroot-8B-V1
  - Casual-Autopsy/L3-Umbral-Mind-RP-v1.0-8B
  - bluuwhale/L3-SthenoMaidBlackroot-8B-V1
  - Casual-Autopsy/L3-Umbral-Mind-RP-v1.0-8B
  - bluuwhale/L3-SthenoMaidBlackroot-8B-V1
tags:
  - merge
  - mergekit
  - lazymergekit
  - bluuwhale/L3-SthenoMaidBlackroot-8B-V1
  - Casual-Autopsy/L3-Umbral-Mind-RP-v1.0-8B

Llama3-Omphalos-12B

Llama3-Omphalos-12B is a merge of the following models using LazyMergekit:

🧩 Configuration

dtype: bfloat16
merge_method: passthrough
slices:
- sources:
  - layer_range: [0, 8]
    model: bluuwhale/L3-SthenoMaidBlackroot-8B-V1
- sources:
  - layer_range: [4, 12]
    model: Casual-Autopsy/L3-Umbral-Mind-RP-v1.0-8B
- sources:
  - layer_range: [9, 16]
    model: bluuwhale/L3-SthenoMaidBlackroot-8B-V1
- sources:
  - layer_range: [13, 20]
    model: Casual-Autopsy/L3-Umbral-Mind-RP-v1.0-8B
- sources:
  - layer_range: [17, 24]
    model: bluuwhale/L3-SthenoMaidBlackroot-8B-V1
- sources:
  - layer_range: [21, 28]
    model: Casual-Autopsy/L3-Umbral-Mind-RP-v1.0-8B
- sources:
  - layer_range: [25, 32]
    model: bluuwhale/L3-SthenoMaidBlackroot-8B-V1

💻 Usage

!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "Tremontaine/Llama3-Omphalos-12B"
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"])