title: README emoji: 🦀 colorFrom: green colorTo: pink sdk: static pinned: false

tags: - merge - mergekit - lazymergekit - SuperAGI/SAM - GoogleAI/Gemini - bigscience/bloom - openai/opt-175b - deepmind/gopher - microsoft/megatron-turing-nlg base_model: - SuperAGI/SAM - GoogleAI/Gemini - bigscience/bloom - openai/opt-175b - deepmind/gopher - microsoft/megatron-turing-nlg

SAM-Gemini-BLOOM-OPT-Gopher-Megatron-slerp

SAM-Gemini-BLOOM-OPT-Gopher-Megatron-slerp is a merge of the following models using LazyMergekit:

• SuperAGI/SAM
• GoogleAI/Gemini
• bigscience/bloom
• openai/opt-175b
• deepmind/gopher
• microsoft/megatron-turing-nlg

🧩 Configuration

slices:
  - sources:
      - model: SuperAGI/SAM
        layer_range: [0, 32]
      - model: GoogleAI/Gemini
        layer_range: [0, 32]
      - model: bigscience/bloom
        layer_range: [0, 32]
      - model: openai/opt-175b
        layer_range: [0, 32]
      - model: deepmind/gopher
        layer_range: [0, 32]
      - model: microsoft/megatron-turing-nlg
        layer_range: [0, 32]
merge_method: slerp
base_model: SuperAGI/SAM
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: bfloat1

💻 Usage

!pip install -qU transformers accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "Or4cl3-1/SAM-Gemini-BLOOM-OPT-Gopher-Megatron-slerp"
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"])