Yamshadowexperiment28 7B

🚀 🧪 YamshadowExperiment28-7B

YamshadowExperiment28-7B is an automated merged model that currently ranks top among 7B models on the Open LLM Leaderboard. However, it may overfit the benchmarks.

🚀 Quick Start

YamshadowExperiment28-7B is an automated merge created by Maxime Labonne using the following base models:

• automerger/YamShadow-7B
• yam-peleg/Experiment28-7B

🎉 YamshadowExperiment28-7B is currently the best-performing 7B model on the Open LLM Leaderboard (08 Apr 24). Use it with caution, as it is likely a sign of overfitting the benchmarks.

✨ Features

🔍 Applications

This model uses a context window of 8k. It is recommended to use it with the Alpaca chat template (works perfectly with LM Studio).

However, the model can sometimes break and output a lot of "INST". Based on experience, its excellent results on the Open LLM Leaderboard are probably a sign of overfitting.

⚡ Quantized models

• GGUF: https://huggingface.co/automerger/YamshadowExperiment28-7B-GGUF

🏆 Evaluation

Open LLM Leaderboard

YamshadowExperiment28-7B is currently the best-performing 7B model on the Open LLM Leaderboard (08 Apr 24).

EQ-bench

Thanks to Samuel J. Paech, who kindly ran the evaluation.

Nous

Evaluation performed using LLM AutoEval. See the entire leaderboard here.

🌳 Model Family Tree

📦 Installation

!pip install -qU transformers accelerate

💻 Usage Examples

Basic Usage

from transformers import AutoTokenizer
import transformers
import torch

model = "automerger/YamshadowExperiment28-7B"
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"])

📚 Documentation

🧩 Configuration

slices:
  - sources:
      - model: automerger/YamShadow-7B
        layer_range: [0, 32]
      - model: yam-peleg/Experiment28-7B
        layer_range: [0, 32]
merge_method: slerp
base_model: automerger/YamShadow-7B
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: bfloat16
random_seed: 0

📄 License

This model is licensed under the Apache-2.0 license.