Modelpublic

EVA-UNIT-01/EVA-LLaMA-3.33-70B-v0.1

sourceHugging Faceotherupdated 2y agoView on Hugging Face

21likes49downloads

Model Card

EVA LLaMA 3.33 70B v0.1

A RP/storywriting specialist model, full-parameter finetune of Llama-3.3-70B-Instruct on mixture of synthetic and natural data.<br> It uses Celeste 70B 0.1 data mixture, greatly expanding it to improve versatility, creativity and "flavor" of the resulting model.<br> This model was built with Llama by Meta.

Version notes for v0.1

DELLA linear merge of v0.0 with an unreleased checkpoint from a different run. Reduced overfitting, better long context comprehension and recall, less repetition, more stability.

<p> <p>Prompt format is Llama3.</p><br> <h3>Recommended sampler values:</h3> <ul> <li>Temperature: 1</li> <li>Min-P: 0.05</li> <li>Repetition Penalty: 1.03</li> </ul>

<h3>Recommended SillyTavern preset (via Virt-io):</h3> <ul><li><a href="https://huggingface.co/EVA-UNIT-01/EVA-LLaMA-3.33-70B-v0.0/blob/main/EV01-llama.json">Master import</a></li></ul> </p>

<h3> Training data: </h3> <ul> <li>Celeste 70B 0.1 data mixture minus Opus Instruct subset. See that model's <a href=https://huggingface.co/nothingiisreal/L3.1-70B-Celeste-V0.1-BF16>card</a> for details.</li> <li>Kalomaze's OpusInstruct25k dataset, filtered for refusals.</li> <li>A subset (1k rows) of ChatGPT-4o-WritingPrompts by Gryphe</li> <li>A subset (2k rows) of Sonnet3.5-Charcards-Roleplay by Gryphe</li> <li>Synthstruct and SynthRP datasets by Epiculous</li> <li>A subset from Dolphin-2.9.3, including filtered version of not_samantha and a small subset of systemchat.</li> </ul>

<p>Model was created by Kearm, Auri and Cahvay.</p> <h4>Special thanks:</h4><ul> <li>to Cahvay for his work on dataset filtering.</li> <li>to Gryphe, Lemmy, Kalomaze, Nopm, Epiculous and CognitiveComputations for the data</li> <li>and to Allura-org for support, feedback, beta-testing and doing quality control of EVA models.</li></ul>

<h3>Licensing</h3> <p>Llama-3.3-70B-Instruct by Meta is licensed under <a href=https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct/blob/main/LICENSE>Llama 3.3 Community License Agreement (further referred as L3.3 license)</a> and is a subject to <a href=https://www.llama.com/llama3_3/use-policy>Acceptable Use Policy for Llama Materials</a>.<br> This derivative is free for personal, research and commercial use on terms of L3.3 license with one extra clause: <br>

—Infermatic Inc and any of its employees or paid associates cannot utilize, distribute, download, or otherwise make use of EVA models for any purpose.</p>

This is a merge of pre-trained language models created using mergekit.

Merge Details

Merge Method

This model was merged using the linear DELLA merge method using meta-llama/Llama-3.1-70B as a base.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

yaml

models:
  - model: EVA-UNIT-01/EVA-LLaMA-3.33-70B-v0.0
    parameters:
      density: 0.6
      weight: 0.3
      lambda: 1.1
      epsilon: 0.35
  - model: EVA-UNIT-01/LLaMA-EVA-3.33-70B-v0.0
    parameters:
      density: 0.45
      weight: 0.7
      lambda: 1.1
      epsilon: 0.4
merge_method: della_linear
base_model: meta-llama/Llama-3.1-70B
parameters:
  normalize: true
  int8_mask: true
dtype: bfloat16