README.md

metadata

base_model:
  - codellama/CodeLlama-7b-Python-hf
  - codellama/CodeLlama-7b-Instruct-hf
  - Phind/Phind-CodeLlama-34B-v2
  - Phind/Phind-CodeLlama-34B-Python-v1
library_name: transformers
tags:
  - mergekit
  - merge
license: openrail

Tlamatini Papalotl: The Wisdom-Butterfly: V0.2 Coder (Programming Assistance)

merge

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

Merge Details

Merge Method

This model was merged using the passthrough merge method.

Models Merged

The following models were included in the merge:

• codellama/CodeLlama-7b-Python-hf
• codellama/CodeLlama-7b-Instruct-hf
• Phind/Phind-CodeLlama-34B-v2
• Phind/Phind-CodeLlama-34B-Python-v1

Configuration

The following YAML configuration was used to produce this model:

slices:
- sources:
  - layer_range: [0, 15]
    model: codellama/CodeLlama-7b-Instruct-hf
- sources:
  - layer_range: [0, 15]
    model: Phind/Phind-CodeLlama-34B-Python-v1
- sources:
  - layer_range: [8, 26]
    model: codellama/CodeLlama-7b-Python-hf
- sources:
  - layer_range: [16, 33]
    model: Phind/Phind-CodeLlama-34B-v2
- sources:
  - layer_range: [14, 32]
    model: codellama/CodeLlama-7b-Instruct-hf
merge_method: passthrough
dtype: float16