Llama-Nephilim-Metamorphosis-v2-8B

Llama-Nephilim-Metamorphosis-v2-8B

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

A coherent Llama 3 model (composed of fine-tunes based on Instruct) was merged at low weight into a Llama 3.1 Instruct model. No fine-tuning was performed afterward. The resulting model is mostly coherent for direct chat and text generation, retaining long context capability of 3.1. A gradient merge was used at the ends and the the embed_tokens and lm_head layers retained from 3.1, which should better preserve handling of context above 8K tokens.

Testing has been performed out to 16K context, using temperature 1 and minP 0.01. Safety remains mostly intact.

Built with Llama.

Merge Details

Merge Method

This model was merged using the SLERP merge method.

Models Merged

The following models were included in the merge:

• meta-llama/Llama-3.1-8B-Instruct
• grimjim/llama-3-Nephilim-v3-8B

Configuration

The following YAML configuration was used to produce this model:

base_model: meta-llama/Llama-3.1-8B-Instruct
dtype: bfloat16
merge_method: slerp
slices:
- sources:
  - model: meta-llama/Llama-3.1-8B-Instruct
    layer_range: [0, 32]
  - model: grimjim/llama-3-Nephilim-v3-8B
    layer_range: [0, 32]
    value: [0.0, 0.02, 0.04, 0.06, 0.08, 0.1, 0.1, 0.1,
      0.1, 0.1, 0.1, 0.1, 0.1, 0.1, 0.1, 0.1,
      0.1, 0.1, 0.1, 0.1, 0.1, 0.1, 0.1, 0.1,
      0.1, 0.1, 0.1, 0.08, 0.06, 0.04, 0.02, 0.0]
parameters:
  t:
    - filter: embed_tokens
      value: 0.0
    - filter: lm_head
      value: 0.0
    - value: 0.1